Text Recognition in the Wild: A Survey
The DOI matches its Crossref record; 173 of the 173 references it cites were found in a registry or an index.
Abstract
The history of text can be traced back over thousands of years. Rich and precise semantic information carried by text is important in a wide range of vision-based application scenarios. Therefore, text recognition in natural scenes has been an active research topic in computer vision and pattern recognition. In recent years, with the rise and development of deep learning, numerous methods have shown promising results in terms of innovation, practicality, and efficiency. This article aims to (1) summarize the fundamental problems and the state-of-the-art associated with scene text recognition, (2) introduce new insights and ideas, (3) provide a comprehensive review of publicly available resources, and (4) point out directions for future work. In summary, this literature review attempts to present an entire picture of the field of scene text recognition. It provides a comprehensive reference for people entering this field and could be helpful in inspiring future research. Related resources are available at our GitHub repository: https://github.com/HCIILAB/Scene-Text-Recognition.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“nition. stage, such as the VGGNet [183], [116], [178], [133], [71], [137], [162]. For more powerful feature representation, some complex neural networks were applied in STR algorithms, such as ResNet [184] [135], [145], [148], [73], [151], [166], [152], [154], [48], [155], [157], [158], [161], [163], [164] and DenseNe…”
MethodHochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 2×
“[57] for training RNNs [29], [72] to label unsegmented sequences directly.”
BackgroundGradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“Later, inspired by the success of the deep convolutional neural network in visual understanding [90], Wang et al.”
BackgroundHistograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584 · cited 1×
“ile suppressing irrelevant features such as font, color, size, and background. Motivated by the successes of [180], [181], [68], Su et al. [131] used the histogram of oriented gradients (HOG) feature [182] in their STR system to construct sequential features of word images. Later, CNNs [138], [140], [141], [143], [72]…”
MethodA Computational Approach to Edge Detection
Canny, J. (1986) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.1986.4767851 · Cited by 30,004 · cited 1×
“lization methods are based on low-level features, such as color [35], [36], gradient [37], [38], stroke width transform [39], [40], maximally stable extremal regions (MSER) [41], [42], canny detector [43], [44], and connected component analysis [45], [46]. Most of current methods are based on deep neural networks [47]…”
MethodHe, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545 · cited 2×
“m decoding step size. At the t-th step, the output prediction o tis given by: o t= Softmax(W os t+b o); (2) where s tis the hidden state of RNN at time step t. Typically, a gated recurrent unit (GRU) [191] is used to update s tand model the longterm dependencies. Hence, s tis computed as s t= GRU(o prev;g t;s t 1); (3…”
BackgroundMethodImage Super-Resolution Using Deep Convolutional Networks
Dong, C., Loy, C. C., He, K., & Tang, X. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2439281 · Cited by 10,105
Speech recognition with deep recurrent neural networks
Graves, A., Mohamed, A.-R., & Hinton, G. (2013) · 2013 IEEE International Conference on Acoustics, Speech and Signal Processing · doi:10.1109/icassp.2013.6638947 · Cited by 8,893 · cited 1×
“tion CTC was proposed by Graves et al. [115] for training RNNs [191], [189] to label unsegmented sequences directly. CTC has achieved significant improvements in many fields, such as speech recognition [192], [193] and online handwritten text recognition [188], [194]. CTC is typically used in STR as a prediction module,…”
MethodGraves, A., Fernández, S., Gomez, F., & Schmidhuber, J. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143891 · Cited by 5,370
Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering
Anderson, P., He, X., Buehler, C., Teney, D., Johnson, M., Gould, S., & Zhang, L. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00636 · Cited by 4,948 · cited 1×
“structured data, is the main object of NLP. There is a wide range of text-based applications of NLP, including machine translation [98], [99], automatic summarization [100], [101], question answering [102], [103], and relationship extraction [104], [105]. 2.3 Applications Text, as the most important carrier of communi…”
BackgroundInfluentialHe, K., Gkioxari, G., Dollar, P., & Girshick, R. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2844175 · Cited by 3,457
Shi, B., Bai, X., & Yao, C. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2646371 · Cited by 3,172
Supervised Sequence Labelling with Recurrent Neural Networks
Graves, A. (2012) · Studies in Computational Intelligence · doi:10.1007/978-3-642-24797-2 · Cited by 3,120
A Novel Connectionist System for Unconstrained Handwriting Recognition
Graves, A., Liwicki, M., Fernandez, S., Bertolami, R., Bunke, H., & Schmidhuber, J. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.137 · Cited by 1,983 · cited 3×
“CTC has achieved significant improvements in many fields, such as speech recognition [60], [58] and online handwritten text recognition [59], [56].”
BackgroundSynthetic Data for Text Localisation in Natural Images
Gupta, A., Vedaldi, A., & Zisserman, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.254 · Cited by 1,563 · cited 4×
“The SynthText dataset [62] contains 800, 000 images with 6 million synthetic text instances.”
BackgroundMethodInfluentialDetecting text in natural scenes with stroke width transform
Epshtein, B., Ofek, E., & Wexler, Y. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5540041 · Cited by 1,492 · cited 1×
“ndidate text regions with as little background as possible [28]. Early text localization methods are based on low-level features, such as color [35], [36], gradient [37], [38], stroke width transform [39], [40], maximally stable extremal regions (MSER) [41], [42], canny detector [43], [44], and connected component ana…”
MethodVision for mobile robot navigation: a survey
Desouza, G. N., & Kak, A. C. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.982903 · Cited by 1,357 · cited 1×
“antic information carried by text is important in a wide range of vision-based application scenarios, such as image search [1], intelligent inspection [2], industrial automation [3], robot navigation [4], and instant translation [5]. Therefore, text recognition in natural scenes has drawn the attention of researchers…”
BackgroundLimits on super-resolution and how to break them
Baker, S., & Kanade, T. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2002.1033210 · Cited by 1,205
Reading text in the wild with convolutional neural networks
Jaderberg, M., Simonyan, K., Vedaldi, A., & Zisserman, A. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-015-0823-z · Cited by 1,191 · cited 5×
“berg et al. [53] - - - 86.1 - 96.2 91.5 - - - - - - - - - Su and Lu [131] - - - 83.0 - 92.0 82.0 - - - - - - - - - Gordo [126] : Mid-features 93.3 86.6 - 91.8 - - - - - - - - - - - - Jaderberg et al. [132] 97.1 92.7 - 95.4 80.7 98.7 98.6 93.3 93.1 90.8 - - - - - - Jaderberg et al. [133] 95.5 89.6 - 93.2 71.7 97.8 97.0…”
BackgroundMethodInfluentialLimits on super-resolution and how to break them
Baker, S., & Kanade, T. (2002) · Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662) · doi:10.1109/cvpr.2000.854852 · Cited by 1,184 · cited 2×
“• Text enhancement: Text enhancement [10] can recover degraded text, improve text resolution [200], remove the distortions of text, or remove the background [128], which reduces the difficulty of text recognition.”
BackgroundCharacter Region Awareness for Text Detection
Baek, Y., Lee, B., Han, D., Yun, S., & Lee, H. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00959 · Cited by 1,103 · cited 1×
“Text detection approaches can be roughly categorized as regression-based methods [116], [119], [237], [5], [207] and instance segmentation-based methods [204], [64], [213], [117].”
MethodEnd-to-end attention-based large vocabulary speech recognition
Bahdanau, D., Chorowski, J., Serdyuk, D., Brakel, P., & Bengio, Y. (2016) · 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2016.7472618 · Cited by 1,096 · cited 1×
“ii) For long text sequences, the attention mechanism is difficult to train from scratch owing to the misalignment between the input instance image and the output text sequences [7], i.”
BackgroundTwo-Phase Kernel Estimation for Robust Motion Deblurring
Xu, L., & Jia, J. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15549-9_12 · Cited by 1,027 · cited 1×
“Many algorithms have been investigated for text enhancement and achieved promising results, such as the deconvolution [212], [16], learning-based methods [10], and sparse reconstruction [221].”
BackgroundRecurrent convolutional neural network for object recognition
Liang, M., & Hu, X. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298958 · Cited by 976 · cited 1×
“ase the depth of traditional CNNs under the same parametric capacity and produce much more compact feature response. Inspired by the recurrent convolution neural network (RCNN) in image classification [186], Wang et al. [139] designed a gated recurrent convolution layer for feature sequence representation by introducin…”
BackgroundASTER: An Attentional Scene Text Recognizer with Flexible Rectification
Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., & Bai, X. (2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2848939 · Cited by 906 · cited 8×
“The second category is segmentation-free methods [173], [161], [24], [163], [127].”
BackgroundMethodInfluentialTextBoxes++: A Single-Shot Oriented Scene Text Detector
Liao, M., Shi, B., & Bai, X. (2018) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2825107 · Cited by 897 · cited 2×
“et al. [77] - - - - - - 91.0 89.0 86.0 93.0 92.0 87.0 82.0 77.0 63.0 85.0 80.0 65.0 - - Liu et al. [203] : FOTS - - - - - - 92.0 90.1 84.8 95.9 93.9 87.8 83.6 79.1 65.3 87.0 82.4 68.0 - - Liao et al. [204] : TextBoxes++ 84.0 64.0 - - - - 93.0 92.0 85.0 96.0 95.0 87.0 73.3 65.9 51.9 76.5 69.0 54.4 - - Liao et al. [165]…”
BackgroundInfluentialWeighted finite-state transducers in speech recognition
Mohri, M., Pereira, F., & Riley, M. (2002) · Computer Speech & Language · doi:10.1006/csla.2001.0184 · Cited by 885 · cited 1×
“For postprocessing, the character responses with character spacings, the beam search algorithm [104] or the weighted finite state transducer [135] based representation were applied to recognize target words in a defined lexicon.”
MethodReal-time scene text localization and recognition
Neumann, L., & Matas, J. (2012) · 2012 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2012.6248097 · Cited by 827 · cited 4×
“Early research [196], [141], [218] mainly relied on hand-crafted features.”
BackgroundMethodInfluentialA survey of methods and strategies in character segmentation
Casey, R. G., & Lecolinet, E. (1996) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.506792 · Cited by 813 · cited 1×
“presentations [147] and synthesis approaches [171], [172], an intuitive but rarely noticed solution is to separate the text content from complex backgrounds. Although traditional binarization methods [173] work well on document images, they fail to handle substantial variations in text appearance and noise in natural…”
BackgroundChowdhury, G. G. (2003) · Annual Review of Information Science and Technology · doi:10.1002/aris.1440370103 · Cited by 805 · cited 1×
“• Natural language processing: Natural language processing (NLP) [30] explores how to use computers to understand and manipulate natural language text or speech.”
BackgroundText Detection and Recognition in Imagery: A Survey
Ye, Q., & Doermann, D. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2366765 · Cited by 780 · cited 4×
“ntal Problems Text localization: The objective of text localization [34] is to localize text components precisely and to group them into candidate text regions with as little background as possible [28]. Early text localization methods are based on low-level features, such as color [35], [36], gradient [37], [38], str…”
BackgroundMethodInfluentialEESEN: End-to-end speech recognition using deep RNN models and WFST-based decoding
Miao, Y., Gowayyed, M., & Metze, F. (2015) · 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru.2015.7404790 · Cited by 707 · cited 1×
“ii) CTC suffers from the peaky distribution problems [57], [131] and its performance usually degrades for repeated patterns.”
BackgroundRobust Scene Text Recognition with Automatic Rectification
Shi, B., Wang, X., Lyu, P., Yao, C., & Bai, X. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.452 · Cited by 693 · cited 5×
“[162] : RARE 96.”
MethodInfluentialDeep Features for Text Spotting
Jaderberg, M., Vedaldi, A., & Zisserman, A. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10593-2_34 · Cited by 653 · cited 5×
“ces false positives. Approaches to text verification include prior knowledge [51], [37], [52], support vector machine (SVM) classifier [24], and conditional random fields (CRFs) [50]. Recent works [15], [53] used a convolution neural network (CNN) to improve text/non-text discrimination. Text detection: The function of t…”
BackgroundMethodInfluentialWhat Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis
Baek, J., Kim, G., Lee, J., Park, S., Han, D., Yun, S., Oh, S. J., & Lee, H. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00481 · Cited by 617 · cited 7×
“For more powerful feature representation, some complex neural networks were applied in STR algorithms, such as ResNet [66] [108], [44], [187], [163], [20], [197], [205], [94], [233], [216], [195], [4], [147], [242], [235] and DenseNet [74], [47], [48].”
BackgroundMethodInfluentialScene Classification With Recurrent Attention of VHR Remote Sensing Images
Wang, Q., Liu, S., Chanussot, J., & Li, X. (2019) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2018.2864987 · Cited by 613 · cited 1×
“Many approaches based on the attention mechanism have achieved significant improvements in various fields, such as image caption [71], text recognition [163], and scene classification of remote sensing images [194].”
BackgroundFOTS: Fast Oriented Text Spotting with a Unified Network
Liu, X., Liang, D., Yan, S., Chen, D., Qiao, Y., & Yan, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00595 · Cited by 554
A robust arbitrary text detection system for natural scene images
Risnumawan, A., Shivakumara, P., Chan, C. S., & Tan, C. L. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2014.07.008 · Cited by 531 · cited 2×
“CUTE80 [153] English 80 0 80 288 0 288 % % Irregular http://cs-chan.”
MethodFocusing Attention: Towards Accurate Text Recognition in Natural Images
Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., & Zhou, S. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.543 · Cited by 528 · cited 5×
“The second category is segmentation-free methods [173], [161], [24], [163], [127].”
BackgroundMethodInfluentialScene Text Detection and Recognition: The Deep Learning Era
Long, S., He, X., & Yao, C. (2021) · International Journal of Computer Vision · doi:10.1007/s11263-020-01369-0 · Cited by 527 · cited 1×
“ovide a comprehensive review of publicly available resources, including the standard benchmark datasets and related code. There are several STR reviews in the literature [26], [27], [28], [29], [30], [31]. However, most of the abovementioned surveys [26], [27], [28], [29], [30] are outdated. Many recent advances, such…”
BackgroundMask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes
Lyu, P., Liao, M., Yao, C., Wu, W., & Bai, X. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01264-9_5 · Cited by 522
Word Spotting and Recognition with Embedded Attributes
Almazan, J., Gordo, A., Fornes, A., & Valveny, E. (2014) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2014.2339814 · Cited by 517 · cited 2×
“han the sum of parts,” Goel et al. [130] recognized text in natural scenes by matching the scene and synthetic image features with weighted dynamic time warping (wDTW) approach. Later, Almazan et al. [117] and Rodriguez et al.´ [118] interpreted the task of recognition and retrieval as a nearest neighbor problem. They…”
BackgroundInfluentialMORAN: A Multi-Object Rectified Attention Network for scene text recognition
Luo, C., Jin, L., & Sun, Z. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.01.020 · Cited by 510
Self-citationTwenty years of document image analysis in PAMI
Nagy, G. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.824820 · Cited by 507 · cited 1×
“Although OCR in scanned documents is well developed [137], [241], STR remains challenging because of many factors, such as complex backgrounds, various fonts, and imperfect imaging conditions.”
BackgroundRecognizing Text with Perspective Distortion in Natural Scenes
Phan, T. Q., Shivakumara, P., Tian, S., & Tan, C. L. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.76 · Cited by 473 · cited 4×
“To further improve recognition performance, researchers explored robust word image representations, such as scale invariant feature transform (SIFT) descriptors [152], Strokelets [220], and mid-level features [55].”
MethodInfluentialRecursive Recurrent Nets with Attention Modeling for OCR in the Wild
Lee, C.-Y., & Osindero, S. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.245 · Cited by 458 · cited 5×
“2 Lee and Osindero [91] : R2AM 96.”
BackgroundMethodInfluentialPhotoOCR: Reading Text in Uncontrolled Conditions
Bissacco, A., Cummins, M., Netzer, Y., & Neven, H. (2013) · 2013 IEEE International Conference on Computer Vision · doi:10.1109/iccv.2013.102 · Cited by 457 · cited 5×
“vert all text regions into the target string sequences. It usually includes text detection, text recognition, and postprocessing. The construction of a real-time and efficient end-to-end systems [16], [70], [74] has become a new trend in recent years. Some researchers [68], [15], [75] interpret text detection and text…”
BackgroundMethodInfluentialABCNet: Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network
Liu, Y., Chen, H., Shen, C., He, T., Jin, L., & Wang, L. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00983 · Cited by 457
Self-citationWang, K., & Belongie, S. (2010) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-15549-9_43 · Cited by 449 · cited 3×
“is associated with a 50-word lexicon and a 1;000-word lexicon. Specifically, the lexicon consists of a ground-truth word and some randomly picked words. Street View Text (SVT). The SVT dataset [68], [180] contains 350 images: 100 for training and 250 for testing. Some images are severely corrupted by noise, blur, and l…”
BackgroundInfluentialShow, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition
Li, H., Wang, P., Shen, C., & Zhang, G. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018610 · Cited by 432
Localizing and segmenting text in images and videos
Lienhart, R., & Wernicke, A. (2002) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/76.999203 · Cited by 419 · cited 1×
“The objective of text localization [102] is to localize text components precisely and group them into candidate text regions with as little background as possible [222].”
BackgroundHe, K., Gkioxari, G., Dollár, P., & Girshick, R. (2017) · arXiv · doi:10.48550/arxiv.1703.06870 · Cited by 406
Scene text detection and recognition: recent advances and future trends
Zhu, Y., Yao, C., & Bai, X. (2016) · Frontiers of Computer Science · doi:10.1007/s11704-015-4488-0 · Cited by 402 · cited 1×
“eover, we provide a comprehensive review of publicly available resources, including the standard benchmark datasets and related code. There are several STR reviews in the literature [26], [27], [28], [29], [30], [31]. However, most of the abovementioned surveys [26], [27], [28], [29], [30] are outdated. Many recent ad…”
BackgroundSelf-citationMoving Object Detection in Spatial Domain using Background Removal Techniques - State-of-Art
Elhabian, S. Y., El-Sayed, K. M., & Ahmed, S. H. (2010) · Recent Patents on Computer Science · doi:10.2174/1874479610801010032 · Cited by 385 · cited 1×
“A combination of the background removal technique [40] with simple feature extractors may be an alternative in future research.”
MethodTowards Accurate Scene Text Recognition With Semantic Reasoning Networks
Yu, D., Li, X., Zhang, C., Liu, T., Han, J., Liu, J., & Ding, E. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01213 · Cited by 385
Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection
Liu, Y., & Jin, L. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.368 · Cited by 351 · cited 1×
“s [28]. As a basis of an end-to-end system, it provides precise and compact text instance images for text recognition. Text detection approaches can be roughly categorized as regression-based methods [55], [56], [57], [58], [59] and instance segmentation-based methods [60], [61], [62], [63]. Text segmentation: Text se…”
MethodSelf-citationTextField: Learning a Deep Direction Field for Irregular Scene Text Detection
Xu, Y., Wang, Y., Zhou, W., Wang, Y., Yang, Z., & Bai, X. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2900589 · Cited by 345 · cited 1×
“Text detection approaches can be roughly categorized as regression-based methods [116], [119], [237], [5], [207] and instance segmentation-based methods [204], [64], [213], [117].”
MethodSingle Shot Text Detector with Regional Attention
He, P., Huang, W., He, T., Zhu, Q., Qiao, Y., & Li, X. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.331 · Cited by 344 · cited 1×
“Most of current methods are based on deep neural networks [68], [233], [226].”
MethodA Unified Framework for Multioriented Text Detection and Recognition
Yao, C., Bai, X., & Liu, W. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2353813 · Cited by 343 · cited 4×
“Traditional text recognition methods rely on hand-crafted features, such as histogram of oriented gradients descriptors [196], connected components [141], and stroke width transform [218].”
BackgroundMethodInfluentialText String Detection From Natural Scenes by Structure-Based Partition and Grouping
Yi, C., & Tian, Y. (2011) · IEEE Transactions on Image Processing · doi:10.1109/tip.2011.2126586 · Cited by 335 · cited 1×
“ext components precisely and to group them into candidate text regions with as little background as possible [28]. Early text localization methods are based on low-level features, such as color [35], [36], gradient [37], [38], stroke width transform [39], [40], maximally stable extremal regions (MSER) [41], [42], cann…”
MethodFast and robust text detection in images and video frames
Ye, Q., Huang, Q., Gao, W., & Zhao, D. (2005) · Image and Vision Computing · doi:10.1016/j.imavis.2005.01.004 · Cited by 333 · cited 3×
“Apart from the applications we have mentioned above, there have been some specific STR application scenarios, such as text visual question answering (text VQA) [171], [13], e-discovery [9], multimedia retrieval [240], [224], automatic identity authentication, which are also quietly changing our life quality.”
BackgroundMethodAutomatic caption localization in compressed video
Zhong, Y., Zhang, H., & Jain, A. K. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.845381 · Cited by 333
Curved scene text detection via transverse and longitudinal sequence connection
Liu, Y., Jin, L., Zhang, S., Luo, C., & Zhang, S. (2019) · Pattern Recognition · doi:10.1016/j.patcog.2019.02.002 · Cited by 317 · cited 1×
“Text detection approaches can be roughly categorized as regression-based methods [116], [119], [237], [5], [207] and instance segmentation-based methods [204], [64], [213], [117].”
MethodSelf-citationSEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition
Qiao, Z., Zhou, Y., Yang, D., Zhou, Y., & Wang, W. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01354 · Cited by 311
Strokelets: A Learned Multi-scale Representation for Scene Text Recognition
Yao, C., Bai, X., Shi, B., & Liu, W. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.515 · Cited by 306 · cited 2×
“[220] : Strokelets 2014 ExPu ! % ! % % %”
ESIR: End-To-End Scene Text Recognition via Iterative Image Rectification
Zhan, F., & Lu, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00216 · Cited by 296 · cited 5×
“For more powerful feature representation, some complex neural networks were applied in STR algorithms, such as ResNet [66] [108], [44], [187], [163], [20], [197], [205], [94], [233], [216], [195], [4], [147], [242], [235] and DenseNet [74], [47], [48].”
MethodInfluentialDecoupled Attention Network for Text Recognition
Wang, T., Zhu, Y., Jin, L., Luo, C., Chen, X., Wu, Y., Wang, Q., & Cai, M. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6903 · Cited by 294
Self-citationScene Text Visual Question Answering
Biten, A. F., Tito, R., Mafla, A., Gomez, L., Rusinol, M., Jawahar, C. V., Valveny, E., & Karatzas, D. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00439 · Cited by 293 · cited 1×
“Examples of various applications of scene text recognition. our daily life include document understanding [106], information extraction [107], [108], text visual question answering (text VQA) [109], [110], image classification [111], historical documents digitization [21], [112], automatic geocoding systems [22], [113]…”
BackgroundAON: Towards Arbitrarily-Oriented Text Recognition
Cheng, Z., Xu, Y., Bai, F., Niu, Y., Pu, S., & Zhou, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00584 · Cited by 292 · cited 5×
“Equations 2 6, W o, b o, W s, W h, and bare all trainable parameters. Inspired by the development of neural machine translation systems, a large number of attention-based methods [134], [178], [137], [140], [73], [72], [154], [48], [33], [155], [158], [164] have emerged in STR field. Moreover, some attempts have been m…”
BackgroundInfluentialAutomatic Detection and Recognition of Signs From Natural Scenes
Chen, X., Yang, J., Zhang, J., & Waibel, A. (2004) · IEEE Transactions on Image Processing · doi:10.1109/tip.2003.819223 · Cited by 279 · cited 1×
“learning-based STR algorithms. The first factor is the advances in hardware systems. High-performance computing systems [18] can train large-scale recognition networks. Moreover, modern mobile devices [19], [20] are capable of running complex algorithms in real-time. The second is automatic feature learning in deep lea…”
BackgroundSelf-citationNayef, N., Patel, Y., Busta, M., Chowdhury, P. N., Karatzas, D., Khlif, W., Matas, J., Pal, U., Burie, J.-C., Liu, C.-L., et al. (2019) · 2019 International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2019.00254 · Cited by 274 · cited 4×
“c average of the score of precision and recall. This is a mainstream metric to evaluate detection and recognition performance simultaneously. The protocol is widely used in [228], [12], [232], [236], [233]. The second protocol measures the algorithm performance by the average NED, namely, AED. In particular, the NED b…”
MethodInfluentialSTAR-Net: A SpaTial Attention Residue Network for Scene Text Recognition
Liu, W., Chen, C., Wong, K.-Y., Su, Z., & Han, J. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.43 · Cited by 273 · cited 6×
“For more powerful feature representation, some complex neural networks were applied in STR algorithms, such as ResNet [66] [108], [44], [187], [163], [20], [197], [205], [94], [233], [216], [195], [4], [147], [242], [235] and DenseNet [74], [47], [48].”
BackgroundMethodInfluentialScene Text Recognition from Two-Dimensional Perspective
Liao, M., Zhang, J., Wan, Z., Xie, F., Liang, J., Lyu, P., Yao, C., & Bai, X. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018714 · Cited by 251
Deep TextSpotter: An End-to-End Trainable Scene Text Localization and Recognition Framework
Busta, M., Neumann, L., & Matas, J. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.242 · Cited by 244 · cited 4×
“Many recent studies [15] have shown the effectiveness of a joint optimized end-to-end model, which usually includes a detection branch and a recognition branch.”
BackgroundMethodInfluentialAn End-to-End TextSpotter with Explicit Alignment and Attention
He, T., Tian, Z., Huang, W., Shen, C., Qiao, Y., & Sun, C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00527 · Cited by 234
Towards End-to-End Text Spotting with Convolutional Recurrent Neural Networks
Li, H., Wang, P., & Shen, C. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.560 · Cited by 230 · cited 3×
“l mechanism Word-level classification % Liao et al. [201] : TextBoxes 2017 SSD-based framework CRNN https://github.com/MhLiao/TextBoxes Bsta et al. [76] : Deep TextSpotter 2017 Yolo-v2 CTC % Li et al. [74] 2017 Text Proposal Network Attention % Lyu et al. [202] : Mask TextSpotter 2018 Fast R-CNN with mask branch Charac…”
MethodInfluentialScene Text Detection via Connected Component Clustering and Nontext Filtering
Koo, H. I., & Kim, D. H. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2249082 · Cited by 228 · cited 1×
“Early text localization methods are based on low-level features, such as color [92], [225], gradient [95], [169], stroke width transform [41], [136], maximally stable extremal regions (MSER) [140], [166], canny detector [17], [28], and connected component analysis [87], [145].”
MethodTextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting
Feng, W., He, W., Yin, F., Zhang, X.-Y., & Liu, C.-L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00917 · Cited by 226 · cited 3×
“many methods used bilinear interpolation to extract text instance features, such as bilinear sampling [76], RoIRotate [203], and the text alignment layer [77]. Recent end-to-end systems [202], [165], [206], [208], [209] have focused on curved text of arbitrary shapes. For example, Liao et al. [202] and their extended…”
MethodInfluentialNRTR: A No-Recurrence Sequence-to-Sequence Model for Scene Text Recognition
Sheng, F., Chen, Z., & Xu, B. (2019) · 2019 International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2019.00130 · Cited by 207 · cited 2×
“A recent attention variant, namely Transformer [182], was widely employed in [242], [192], [159], [229] to improve parallelization and reduce complexity for STR.”
MethodText Detection, Tracking and Recognition in Video: A Comprehensive Survey
Yin, X.-C., Zuo, Z.-Y., Tian, S., & Liu, C.-L. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2554321 · Cited by 199 · cited 4×
“• Text tracking: The purpose of text tracking [228], [178] is to maintain the integrity of text location and track text across adjacent frames in the video.”
BackgroundInfluentialChargrid: Towards Understanding 2D Documents
Katti, A. R., Reisswig, C., Guder, C., Brarda, S., Bickel, S., Höhne, J., & Faddoul, J. B. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1476 · Cited by 199 · cited 1×
“A combination of NLP and STR may be an important trend in various fields, such as text VQA [171], [199], document understanding [84], and information extraction [110], [35].”
BackgroundGraph Convolution for Multimodal Information Extraction from Visually Rich Documents
Liu, X., Gao, F., Zhang, Q., & Zhao, H. (2019) · Proceedings of the 2019 Conference of the North · doi:10.18653/v1/n19-2005 · Cited by 199 · cited 1×
“XZ JXO\KXY R OIKTYKG TJX KRGZKJJUI[SKTZY Fig. 4: Examples of various applications of scene text recognition. our daily life include document understanding [106], information extraction [107], [108], text visual question answering (text VQA) [109], [110], image classification [111], historical documents digitization [21…”
BackgroundTextScanner: Reading Characters in Order for Robust Scene Text Recognition
Wan, Z., He, M., Chen, H., Bai, X., & Yao, C. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6891 · Cited by 190
Detecting Curve Text in the Wild: New Dataset and New Solution
Yuliang, L., Jin, L., Zhang, S., & Zhang, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.02170 · Cited by 189 · cited 2×
“egular https://pan.baidu.com/s/1SUODaOzV7YOPkrun0xSz6A #list/path=%2F (pw:gox9) CTW [229] Chinese/English 32285 25887 3269 1018402 812872 103519 % ! Regular https://ctwdataset.github.io/ SCUT-CTW1500 [230] Chinese/English 1500 1000 500 10751 7683 3068 % % Irregular https://github.com/Yuliang-Liu/Curve-Text-Detector LS…”
BackgroundSelf-citationHandbook of Document Image Processing and Recognition
(2014) · Springer eBooks · doi:10.1007/978-0-85729-859-1 · Cited by 186
GTC: Guided Training of CTC towards Efficient and Accurate Scene Text Recognition
Hu, W., Cai, X., Hou, J. Y., Yi, S., & Lin, Z. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6735 · Cited by 185
A Fast Uyghur Text Detector for Complex Background Images
Yan, C., Xie, H., Chen, J., Zha, Z., Hao, X., Zhang, Y., & Dai, Q. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2838320 · Cited by 183 · cited 1×
“It usually includes text detection [214], text recognition [161], and postprocessing.”
Edit Probability for Scene Text Recognition
Bai, F., Cheng, Z., Niu, Y., Pu, S., & Zhou, S. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00163 · Cited by 182
Symmetry-Constrained Rectification Network for Scene Text Recognition
Yang, M., Guan, Y., Liao, M., He, X. J., Bian, K., Bai, S., Yao, C., & Bai, X. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00924 · Cited by 176 · cited 5×
“[155] proposed a symmetry-constrained rectification network.”
MethodInfluentialLiu, C.-L., Koga, M., & Fujisawa, H. (2002) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2002.1046151 · Cited by 173 · cited 1×
“eural network with unsupervised feature learning to train a highly-accurate character recognizer module. For postprocessing, the character responses with character spacings, the beam search algorithm [122] or the weighted finite state transducer [123] based representation were applied to recognize target words in a defi…”
MethodAll You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting
Wang, H., Lu, P., Zhang, H., Yang, M., Bai, X., Xu, Y., He, M., Wang, Y., & Liu, W. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6896 · Cited by 169
A novel adaptive morphological approach for degraded character image segmentation
Nomura, S., Yamanaka, K., Katai, O., Kawakami, H., & Shiose, T. (2005) · Pattern Recognition · doi:10.1016/j.patcog.2005.01.026 · Cited by 168 · cited 1×
“It includes text line segmentation [223], [168] and character segmentation [144], [167].”
BackgroundText extraction from natural scene image: A survey
Zhang, H., Zhao, K., Song, Y.-Z., & Guo, J. (2013) · Neurocomputing · doi:10.1016/j.neucom.2013.05.037 · Cited by 167 · cited 1×
“n future work. Moreover, we provide a comprehensive review of publicly available resources, including the standard benchmark datasets and related code. There are several STR reviews in the literature [26], [27], [28], [29], [30], [31]. However, most of the abovementioned surveys [26], [27], [28], [29], [30] are outdat…”
BackgroundSpatial Fusion GAN for Image Synthesis
Zhan, F., Zhu, H., & Lu, S. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00377 · Cited by 164 · cited 3×
“For more powerful feature representation, some complex neural networks were applied in STR algorithms, such as ResNet [66] [108], [44], [187], [163], [20], [197], [205], [94], [233], [216], [195], [4], [147], [242], [235] and DenseNet [74], [47], [48].”
MethodReal-Time Lexicon-Free Scene Text Localization and Recognition
Neumann, L., & Matas, J. (2015) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2496234 · Cited by 163 · cited 2×
“In the past, text detection and recognition have been interpreted as two independent subproblems that are combined to retrieve text from images [190], [196], [81], [142], [62], [2], [78], [143], [100].”
BackgroundMethodTotal-Text: toward orientation robustness in scene text detection
Chng, C.-K., Chan, C. S., & Liu, C. (2019) · International Journal on Document Analysis and Recognition (IJDAR) · doi:10.1007/s10032-019-00334-z · Cited by 161 · cited 2×
“The Total-Text [26] contains 1, 555 images with 11, 459 cropped text instance images.”
BackgroundScene Text Recognition Using Part-Based Tree-Structured Character Detection
Shi, C., Wang, C., Xiao, B., Zhang, Y., Gao, S., & Zhang, Z. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.381 · Cited by 160 · cited 1×
“[28]. Early text localization methods are based on low-level features, such as color [35], [36], gradient [37], [38], stroke width transform [39], [40], maximally stable extremal regions (MSER) [41], [42], canny detector [43], [44], and connected component analysis [45], [46]. Most of current methods are based on deep…”
MethodXie, Z., Sun, Z., Jin, L., Ni, H., & Lyons, T. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2732978 · Cited by 159
Self-citationSu, B., & Lu, S. (2016) · Pattern Recognition · doi:10.1016/j.patcog.2016.10.016 · Cited by 157 · cited 1×
“95.5 83.6 96.9 95.3 - 89.9 89.1 94.3 83.6 73.5 - - - *Liu et al. [121] 94.1 84.7 - 92.5 - 96.8 92.2 - - - - - - - - - *Mishra et al. [120] 78.1 - 46.7 78.2 - 88.0 - - 67.7 60.2 - - - - - - *Su and Lu [136] - - - 91.0 - 95.0 89.0 - - 76.0 - - - - - - *Yang et al. [137] 97.8 96.1 - 95.2 - 97.7 - - - - 93.0 80.2 75.8 69.…”
InfluentialText From Corners: A Novel Approach to Detect Text and Caption in Videos
Zhao, X., Lin, K.-H., Fu, Y., Hu, Y., Liu, Y., & Huang, T. S. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2068553 · Cited by 149 · cited 1×
“cking algorithms for moving text must identify precise text region at pixel level or subpixel level, because false tracking may blend text with its background or noise text. Spatial-temporal analysis [94], [95] is usually used for text tracking in the video. A recent study [96] also predicts movement to track characte…”
BackgroundSequence-To-Sequence Domain Adaptation Network for Robust Text Image Recognition
Zhang, Y., Nie, S., Liu, W., Xu, X., Zhang, D., & Shen, H. T. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00285 · Cited by 141 · cited 4×
“Some researchers [47], [238], [76], [48], [98], [44] argued that directly processing the source image by CNNs would introduce extra noise.”
BackgroundMethodInfluentialPrivacyCheck: Automatic Summarization of Privacy Policies Using Data Mining
Zaeem, R. N., German, R. L., & Barber, K. S. (2018) · ACM Transactions on Internet Technology · doi:10.1145/3127519 · Cited by 140 · cited 1×
“machine translation [6], [23], automatic summarization [232], [105], question answering [3], [36], and relationship extraction [211], [96].”
BackgroundTowards Unconstrained End-to-End Text Spotting
Qin, S., Bissacco, A., Raptis, M., Fujii, Y., & Xiao, Y. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00480 · Cited by 137 · cited 3×
“05] : CharNet 2019 EAST framework CNN classifier https://github.com/MalongTech/research-charnet Feng et al. [206] : TextDragon 2019 TextSnake Sliding convolution character models with CTC % Qin et al. [207] 2019 Mask RCNN Attention % Wang et al. [208] : Boundary 2020 RPN-based framework Attention % Qiao et al. [209] :…”
MethodInfluentialScene Text Extraction with Edge Constraint and Text Collinearity
Lee, S., Cho, M., Jung, K., & Kim, J. H. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.969 · Cited by 133 · cited 1×
“lize text components precisely and to group them into candidate text regions with as little background as possible [28]. Early text localization methods are based on low-level features, such as color [35], [36], gradient [37], [38], stroke width transform [39], [40], maximally stable extremal regions (MSER) [41], [42]…”
Wu, L., Zhang, C., Liu, J., Han, J., Liu, J., Ding, E., & Bai, X. (2019) · Proceedings of the 27th ACM International Conference on Multimedia · doi:10.1145/3343031.3350929 · Cited by 130 · cited 1×
“e features of backgrounds can be visually similar to the text, which causes additional difficulties in recognition. Instead of complicated feature representations [147] and synthesis approaches [171], [172], an intuitive but rarely noticed solution is to separate the text content from complex backgrounds. Although trad…”
BackgroundScript identification in the wild via discriminative convolutional neural network
Shi, B., Bai, X., & Yao, C. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2015.11.005 · Cited by 129 · cited 1×
“Script identification can be interpreted as an image classification problem, where discriminative representations are usually designed, such as mid-level features [172], [160], convolutional features [51], [165], [130], and stroke-parts representations [52].”
BackgroundA New Approach for Overlay Text Detection and Extraction From Complex Video Scene
Kim, W., & Kim, C. (2008) · IEEE Transactions on Image Processing · doi:10.1109/tip.2008.2008225 · Cited by 126 · cited 1×
“text. It is usually used after text localization to filter the candidate regions, because text localization sometimes introduces false positives. Approaches to text verification include prior knowledge [51], [37], [52], support vector machine (SVM) classifier [24], and conditional random fields (CRFs) [50]. Recent works […”
MethodAggregation Cross-Entropy for Sequence Recognition
Xie, Z., Huang, Y., Zhu, Y., Jin, L., Liu, Y., & Xie, L. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00670 · Cited by 123 · cited 1×
“according to different application scenarios and constraints. Moreover, it is valuable to explore alternative prediction strategies in future work. For example, the aggregation cross-entropy function [215] was designed to replace CTC and the attention mechanism; it achieves competitive performance with a much quicker…”
BackgroundInfluentialSelf-citationCanny Text Detector: Fast and Robust Scene Text Localization Algorithm
Cho, H., Sung, M., & Jun, B. (2016) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2016.388 · Cited by 122 · cited 1×
“on methods are based on low-level features, such as color [35], [36], gradient [37], [38], stroke width transform [39], [40], maximally stable extremal regions (MSER) [41], [42], canny detector [43], [44], and connected component analysis [45], [46]. Most of current methods are based on deep neural networks [47], [48]…”
MethodText Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting
Liang, Q., Tang, S., Cheng, Z., Xu, Y., Niu, Y., Pu, S., & Wu, F. Q. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6864 · Cited by 117
Supervised mid-level features for word image representation
Gordo, A. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298914 · Cited by 115 · cited 3×
“ther improve recognition performance, researchers explored robust word image presentations, such as scale invariant feature transform (SIFT) descriptors [124], Strokelets [125], and midlevel features [126]. All of the aforementioned methods rely on lexicons to obtain the final recognition results. However, the query ti…”
BackgroundInfluentialVerisimilar Image Synthesis for Accurate Detection and Recognition of Texts in Scenes
Zhan, F., Lu, S., & Xue, C. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01237-3_16 · Cited by 114
Label Embedding: A Frugal Baseline for Text Recognition
Rodríguez-Serrano, J. A., Gordo, A., & Perronnin, F. (2014) · International Journal of Computer Vision · doi:10.1007/s11263-014-0793-6 · Cited by 109 · cited 4×
“be roughly classified into CTC-based [115] methods [116] and attention-based [98] methods [73], [72]. Besides, other promising ideas are also introduced in this section, such as label embedding [117], [118]. Table 1 gives a comprehensive list and categorization of these recognition methods. 3.1.1 Segmentation-Based Met…”
BackgroundMethodInfluentialScene Text Detection and Recognition: The Deep Learning EraPreprint
Long, S., He, X. J., & Yao, C. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.04256 · Cited by 109 · cited 1×
“ovide a comprehensive review of publicly available resources, including the standard benchmark datasets and related code. There are several STR reviews in the literature [26], [27], [28], [29], [30], [31]. However, most of the abovementioned surveys [26], [27], [28], [29], [30] are outdated. Many recent advances, such…”
BackgroundSelf-Organized Text Detection with Minimal Post-processing via Border Learning
Wu, Y., & Natarajan, P. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.535 · Cited by 106 · cited 1×
“ompact text instance images for text recognition. Text detection approaches can be roughly categorized as regression-based methods [55], [56], [57], [58], [59] and instance segmentation-based methods [60], [61], [62], [63]. Text segmentation: Text segmentation has been identified as one of the most challenging problems…”
MethodTextSR: Content-Aware Text Super-Resolution Guided by RecognitionPreprint
Wang, W., Xie, E., Sun, P., Wang, W., Tian, L., Shen, C., & Luo, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.07113 · Cited by 102 · cited 3×
“AM 2019 SK + ST (char-level) % ! % % ! https://github.com/MhLiao/MaskTextSpotter Wang et al. [166] : DAN 2020 SK + ST % ! % % ! https://github.com/Wang-Tianwei/Decoupled-attention-network Wang et al. [167] 2020 SK + ST % ! % % ! https://github.com/xieenze/TextSR *Wan et al. [129] : TextScanner 2020 SK + ST (char-level…”
BackgroundInfluentialEfficient Scene text localization and recognition with local character refinement
Neumann, L., & Matas, J. (2015) · IAPR International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2015.7333861 · Cited by 98 · cited 1×
“In the past, text detection and recognition have been interpreted as two independent subproblems that are combined to retrieve text from images [190], [196], [81], [142], [62], [2], [78], [143], [100].”
BackgroundIntegrating Scene Text and Visual Appearance for Fine-Grained Image Classification
Bai, X., Yang, M., Lyu, P., Xu, Y., & Luo, J. (2018) · IEEE Access · doi:10.1109/access.2018.2878899 · Cited by 95
Synthetically Supervised Feature Learning for Scene Text Recognition
Liu, Y., Wang, Z., Jin, H., & Wassell, I. J. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01228-1_27 · Cited by 92 · cited 3×
“% % ! % Fang et al. [145] 2018 SK + ST ! % % % ! https://github.com/FangShancheng/conv-ensemble-str Liu et al. [146] : EnEsCTC 2018 SK ! % % ! % https://github.com/liuhu-bigeye/enctc.crnn Liu et al. [147] 2018 SK ! % % ! % % Wang et al. [148] : MAAN 2018 SK ! % % % ! % Sheng et al. [149] : NRTR 2018 SK ! % % % ! % Gao…”
BackgroundInfluentialImproving patch-based scene text script identification with ensembles of conjoined networks
Gómez, L., Nicolaou, A., & Karatzas, D. (2017) · Pattern Recognition · doi:10.1016/j.patcog.2017.01.032 · Cited by 91 · cited 1×
“Script identification can be interpreted as an image classification problem, where discriminative representations are usually designed, such as mid-level features [172], [160], convolutional features [51], [165], [130], and stroke-parts representations [52].”
BackgroundConvolutional Attention Networks for Scene Text Recognition
Xie, H., Fang, S., Zha, Z.-J., Yang, Y., Li, Y., & Zhang, Y. (2019) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3231737 · Cited by 88 · cited 4×
“For more powerful feature representation, some complex neural networks were applied in STR algorithms, such as ResNet [66] [108], [44], [187], [163], [20], [197], [205], [94], [233], [216], [195], [4], [147], [242], [235] and DenseNet [74], [47], [48].”
BackgroundMethodInfluentialFully Convolutional Sequence Recognition Network for Water Meter Number Reading
Yang, F., Jin, L., Lai, S., Gao, X., & Li, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2891767 · Cited by 78 · cited 1×
“[240], [224], [215].”
Self-citationAccurate video text detection through classification of low and high contrast images
Shivakumara, P., Huang, W., Phan, T. Q., & Tan, C. L. (2010) · Pattern Recognition · doi:10.1016/j.patcog.2010.01.009 · Cited by 77 · cited 2×
“Approaches to text verification include prior knowledge [85], [95], [168], support vector machine (SVM) classifier [224], and conditional random fields (CRFs) [89].”
BackgroundMethodChinese Street View Text: Large-Scale Chinese Text Reading With Partially Supervised Learning
Sun, Y., Liu, J., Liu, W., Han, J., Ding, E., & Liu, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00918 · Cited by 76 · cited 2×
“LSVT [176], [175] Chinese/English 450000 30000 20000 - - % % Irregular https://rrc.”
BackgroundA Unified Framework for Tracking Based Text Detection and Recognition from Web Videos
Tian, S., Yin, X.-C., Su, Y., & Hao, H. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2692763 · Cited by 75 · cited 1×
“• Text tracking: The purpose of text tracking [228], [178] is to maintain the integrity of text location and track text across adjacent frames in the video.”
BackgroundA camera phone based currency reader for the visually impaired
Liu, X. (2008) · Proceedings of the 10th international ACM SIGACCESS conference on Computers and accessibility · doi:10.1145/1414471.1414551 · Cited by 74 · cited 1×
“Moreover, modern mobile devices [21], [109] are capable of running complex algorithms in real-time.”
BackgroundReading scene text with fully convolutional sequence modeling
Gao, Y., Chen, Y., Wang, J., Tang, M., & Lu, H. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.094 · Cited by 73 · cited 6×
“For more powerful feature representation, some complex neural networks were applied in STR algorithms, such as ResNet [66] [108], [44], [187], [163], [20], [197], [205], [94], [233], [216], [195], [4], [147], [242], [235] and DenseNet [74], [47], [48].”
BackgroundMethodInfluentialAttention and Language Ensemble for Scene Text Recognition with Convolutional Sequence Modeling
Fang, S., Xie, H., Zha, Z.-J., Sun, N., Tan, J., & Zhang, Y. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240571 · Cited by 67 · cited 5×
“al. [169] added intermediate supervisions along the network layers and successfully trained a deeper BiLSTM model to improve the encoding of contextual dependencies. However, some researchers [138], [145], [152], [160], [161] considered that BiLSTM was not an essential part of STR algorithms. They argued that although…”
BackgroundMethodInfluentialTang, Y., & Wu, X. (2018) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2018.2802644 · Cited by 66 · cited 1×
“Advanced detection [33], [177] and recognition algorithms [161] were then used to build joint end-to-end systems.”
MethodRobustly Extracting Captions in Videos Based on Stroke-Like Edges and Spatio-Temporal Analysis
Liu, X., & Wang, W.-Q. (2012) · IEEE transactions on multimedia · doi:10.1109/tmm.2011.2177646 · Cited by 62 · cited 1×
“algorithms for moving text must identify precise text region at pixel level or subpixel level, because false tracking may blend text with its background or noise text. Spatial-temporal analysis [94], [95] is usually used for text tracking in the video. A recent study [96] also predicts movement to track characters. Na…”
BackgroundConvolutional feature learning and Hybrid CNN-HMM for scene number recognition
Guo, Q., Wang, F., Lei, J. W., Tu, D., & Li, G. (2015) · Neurocomputing · doi:10.1016/j.neucom.2015.07.135 · Cited by 62 · cited 1×
“ists by adopting large dictionaries as higher-order statistical language models. Others solved STR in a lexicon-free manner by leveraging larger-scale data [70] and more complex neural networks [53], [127], e.g., convolutional Maxout network [128]. Recently, Wan et al. [129] built a recognition system based on semanti…”
MethodArbitrarily Shaped Scene Text Detection With a Mask Tightness Text Detector
Liu, Y., Jin, L., & Fang, C. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2954218 · Cited by 62 · cited 1×
“ce images for text recognition. Text detection approaches can be roughly categorized as regression-based methods [55], [56], [57], [58], [59] and instance segmentation-based methods [60], [61], [62], [63]. Text segmentation: Text segmentation has been identified as one of the most challenging problems [64]. It includes…”
MethodSelf-citationImproved text-detection methods for a camera-based text reading system for blind persons
Ezaki, N., Kiyota, K., Minh, B. T., Bulacu, M., & Schomaker, L. (2005) · IAPR International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2005.137 · Cited by 59 · cited 1×
“e classification [111], historical documents digitization [21], [112], automatic geocoding systems [22], [113], multimedia retrieval [23], [24], water meter number reading [25], text-to-speech devices [114] and so on. Figure 4 presents some representative applications. 3 METHODOLOGIES In early research, hand-crafted fe…”
MethodR-Net: A Relationship Network for Efficient and Accurate Scene Text Detection
Wang, Y., Xie, H., Zha, Z.-J., Tian, Y., Fu, Z., & Zhang, Y. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.2995290 · Cited by 57 · cited 1×
“• Text detection: The function of text detection [219], [201] is to determine whether text is present using localization and verification procedures [222].”
BackgroundAutomatic script identification in the wild
Shi, B., Yao, C., Zhang, C., Guo, X., Huang, F., & Bai, X. (2015) · IAPR International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2015.7333818 · Cited by 56 · cited 1×
“Script identification can be interpreted as an image classification problem, where discriminative representations are usually designed, such as mid-level features [172], [160], convolutional features [51], [165], [130], and stroke-parts representations [52].”
BackgroundDeRPN: Taking a Further Step toward More General Object Detection
Xie, L., Liu, Y., Jin, L., & Xie, Z. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33019046 · Cited by 56
Self-citationMobile visual search on printed documents using text and low bit-rate features
Tsai, S. S., Chen, H., Chen, D. M., Schroth, G., Grzeszczuk, R., & Girod, B. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6116198 · Cited by 55 · cited 1×
“has played an important role in human life. Specifically, rich and precise semantic information carried by text is important in a wide range of vision-based application scenarios, such as image search [1], intelligent inspection [2], industrial automation [3], robot navigation [4], and instant translation [5]. Therefor…”
BackgroundA Gradient Difference Based Technique for Video Text Detection
Shivakumara, P., Phan, T. Q., & Tan, C. L. (2009) · Proceedings of the International Conference on Document Analysis and Recognition · doi:10.1109/icdar.2009.85 · Cited by 52 · cited 1×
“ely and to group them into candidate text regions with as little background as possible [28]. Early text localization methods are based on low-level features, such as color [35], [36], gradient [37], [38], stroke width transform [39], [40], maximally stable extremal regions (MSER) [41], [42], canny detector [43], [44]…”
MethodA Fine-Grained Approach to Scene Text Script Identification
Gómez, L., & Karatzas, D. (2016) · IAPR International Workshop on Document Analysis Systems (DAS) · doi:10.1109/das.2016.64 · Cited by 52 · cited 1×
“Script identification can be interpreted as an image classification problem, where discriminative representations are usually designed, such as mid-level features [172], [160], convolutional features [51], [165], [130], and stroke-parts representations [52].”
BackgroundA New Gradient Based Character Segmentation Method for Video Text Recognition
Shivakumara, P., Bhowmick, S., Su, B., Tan, C. L., & Pal, U. (2011) · IAPR International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2011.34 · Cited by 50 · cited 1×
“It includes text line segmentation [223], [168] and character segmentation [144], [167].”
Background2D-CTC for Scene Text RecognitionPreprint
Wan, Z., Xie, F., Liu, Y., Bai, X., & Yao, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.09705 · Cited by 50 · cited 1×
“ensional (2D) prediction problems, such as irregular scene text recognition, where characters in the input text instance image are distributed in a spatial structure. To handle this issue, Wan et al. [199] extended the vanilla CTC by adding another dimension along the height direction. Although the recognition perform…”
BackgroundVD-SAN: Visual-Densely Semantic Attention Network for Image Caption Generation
He, X., Yang, Y., Shi, B., & Bai, X. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.02.106 · Cited by 49 · cited 1×
“he predicted word that are relevant to parts of a given source sentence. Many approaches based on the attention mechanism have achieved significant improvements in various fields, such as image caption [210], text recognition [73], and scene text classification of remote sensing images [211]. For STR, the attention mecha…”
Adaptive embedding gate for attention-based scene text recognition
Chen, X., Wang, T., Zhu, Y., Jin, L., & Luo, C. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.11.049 · Cited by 48
Self-citationDeep Multi-Scale Context Aware Feature Aggregation for Curved Scene Text Detection
Dai, P., Zhang, H., & Cao, X. (2019) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2019.2952978 · Cited by 46 · cited 1×
“Advanced detection [33], [177] and recognition algorithms [161] were then used to build joint end-to-end systems.”
MethodXing, W., Qi, J., Yuan, X., Li, L., Zhang, X., Fu, Y., Xiong, S., Hu, L., & Peng, J. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty263 · Cited by 40 · cited 1×
“machine translation [6], [23], automatic summarization [232], [105], question answering [3], [36], and relationship extraction [211], [96].”
BackgroundJoint Training for Neural Machine Translation
Cheng, Y. J. (2019) · Springer theses · doi:10.1007/978-981-32-9748-7 · Cited by 39
Enhancing energy minimization framework for scene text recognition with top-down cues
Mishra, A., Alahari, K., & Jawahar, C. V. (2016) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2016.01.002 · Cited by 38 · cited 3×
“et al. [73] : RARE 2016 SK % ! % % ! % Lee and Osindero [134] : R2AM 2016 SK ! % % % ! % Liu et al. [135] : STAR-Net 2016 SK + ExPr % ! % ! % % *Liu et al. [121] 2016 ExPu ! % ! % % % *Mishra et al. [120] 2016 ExPu ! % ! % % % *Su and Lu [136] 2017 SK + ExPu ! % % ! % % *Yang et al. [137] 2017 ExPu % ! % % ! % Yin et…”
BackgroundInfluentialTightness-Aware Evaluation Protocol for Scene Text Detection
Liu, Y., Jin, L., Xie, Z., Luo, C., Zhang, S., & Xie, L. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00984 · Cited by 34 · cited 1×
“Therefore, a holistic and fair comparison is necessary for future work [4], [118].”
BackgroundSelf-citationRecognition of raised characters for automatic classification of rubber tires
Ham, Y. K., Kang, M. S., Chung, H. K., Park, R., & Park, G. T. (1995) · Optical Engineering · doi:10.1117/12.184094 · Cited by 33 · cited 1×
“Specifically, rich and precise semantic information carried by text is important in a wide range of vision-based application scenarios, such as image search [179], intelligent inspection [19], industrial automation [63], robot navigation [38], and instant translation [124].”
BackgroundPatch Aggregator for Scene Text Script Identification
Cheng, C., Huang, Q., Bai, X., Feng, B., & Liu, W. (2019) · IAPR International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2019.00175 · Cited by 33 · cited 1×
“• Script identification: Script identification [22] aims to predict the script of a given text image.”
BackgroundRotation-Invariant Features for Multi-Oriented Text Detection in Natural Images
Yao, C., Zhang, X., Bai, X., Liu, W., Ma, Y., & Tu, Z. (2013) · PLoS ONE · doi:10.1371/journal.pone.0070173 · Cited by 32
EPAN: Effective parts attention network for scene text recognition
Huang, Y., Sun, Z., Jin, L., & Luo, C. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.10.010 · Cited by 29 · cited 5×
“There is the significant conflict between 2D text distribution and 1D feature representation by applying the vanilla attention directly. Therefore, Yang et al. [137], Li et al. [154], and Huang et al. [159] proposed 2D attention mechanism for irregular text recognition. ii) Improving the construction of implicit languag…”
BackgroundInfluentialSelf-citationCombined script and page orientation estimation using the Tesseract OCR engine
Unnikrishnan, R., & Smith, R. W. (2009) · doi:10.1145/1577802.1577809 · Cited by 27 · cited 1×
“en text image. It plays a increasingly important role in multilingual systems. As text recognition are language-dependent, detecting the script and language helps to select the correct language model [80]. Script identification can be interpreted as an image classification problem, where discriminative representations a…”
BackgroundText Recognition in Images Based on Transformer with Hierarchical Attention
Zhu, Y., Wang, S., Huang, Z., & Chen, K. (2019) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2019.8803203 · Cited by 27 · cited 4×
“For more powerful feature representation, some complex neural networks were applied in STR algorithms, such as ResNet [66] [108], [44], [187], [163], [20], [197], [205], [94], [233], [216], [195], [4], [147], [242], [235] and DenseNet [74], [47], [48].”
BackgroundMethodInfluentialSelf-citationA Comparative Study of Attention-Based Encoder-Decoder Approaches to Natural Scene Text Recognition
Cong, F., Hu, W., Huo, Q., & Guo, L. (2019) · IAPR International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2019.00151 · Cited by 24 · cited 1×
“e their strengths and limitations. Recently, some researchers [168], [169] applied both CTC and the attention mechanism to achieve accurate prediction and maintain a fast inference speed. Cong et al. [214] comprehensively compared these two prediction approaches on large-scale real-world scene text sentence recognitio…”
BackgroundShape-DNA: Effective Character Restoration and Enhancement for Arabic Text Documents
Caner, G., & Haritaoğlu, I. (2010) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2010.506 · Cited by 19 · cited 1×
“emove the background [89], which reduces the difficulty of text recognition. Many algorithms have been investigated for text enhancement and achieved promising results, such as the deconvolution [90], [91], learningbased methods [87], and sparse reconstruction [92]. Text tracking: The purpose of text tracking [30], [93…”
MethodScene Text Recognition via Gated Cascade Attention
Wang, S., Wang, Y., Qin, X., Zhao, Q., & Tang, Z. (2019) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2019.00179 · Cited by 19 · cited 4×
“For more powerful feature representation, some complex neural networks were applied in STR algorithms, such as ResNet [66] [108], [44], [187], [163], [20], [197], [205], [94], [233], [216], [195], [4], [147], [242], [235] and DenseNet [74], [47], [48].”
BackgroundMethodInfluentialHistorical document digitization through layout analysis and deep content classification
Corbelli, A., Baraldi, L., Grana, C., & Cucchiara, R. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7900272 · Cited by 18 · cited 1×
“The third is the growing demand for STR applications [32], [157],”
BackgroundScene text recognition with CNN classifier and WFST-based word labeling
Liu, X., Kawanishi, T., Wu, X., & Kashino, K. (2016) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.2016.7900259 · Cited by 16 · cited 2×
“[111] combined a multilayer neural network with unsupervised feature learning to train a highly-accurate character recognizer module.”
BackgroundMethodEmploying Semantic Context for Sparse Information Extraction Assessment
Li, P., Wang, H., Li, H., & Wu, X. (2018) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3201407 · Cited by 16 · cited 1×
“machine translation [6], [23], automatic summarization [232], [105], question answering [3], [36], and relationship extraction [211], [96].”
BackgroundText-Attentional Conditional Generative Adversarial Network for Super-Resolution of Text Images
Wang, Y., Su, F., & Qian, Y. (2019) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2019.00180 · Cited by 16 · cited 1×
“• Text enhancement: Text enhancement [10] can recover degraded text, improve text resolution [200], remove the distortions of text, or remove the background [128], which reduces the difficulty of text recognition.”
BackgroundQi, X., Chen, Y., Xiao, R., Li, C.-G., Zou, Q., & Cui, S. R. (2019) · International Conference on Document Analysis and Recognition Workshops (ICDARW) · doi:10.1109/icdarw.2019.40086 · Cited by 16 · cited 4×
“For more powerful feature representation, some complex neural networks were applied in STR algorithms, such as ResNet [66] [108], [44], [187], [163], [20], [197], [205], [94], [233], [216], [195], [4], [147], [242], [235] and DenseNet [74], [47], [48].”
BackgroundMethodInfluentialMemory-Augmented Attention Model for Scene Text Recognition
Wang, C., Yin, F., & Liu, C. (2018) · International Conference on Frontiers in Handwriting Recognition · doi:10.1109/icfhr-2018.2018.00020 · Cited by 12 · cited 3×
“For more powerful feature representation, some complex neural networks were applied in STR algorithms, such as ResNet [66] [108], [44], [187], [163], [20], [197], [205], [94], [233], [216], [195], [4], [147], [242], [235] and DenseNet [74], [47], [48].”
MethodDense Chained Attention Network for Scene Text Recognition
Gao, Y., Chen, Y., Wang, J., Tang, M., & Lu, H. (2018) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2018.8451273 · Cited by 11 · cited 5×
“For more powerful feature representation, some complex neural networks were applied in STR algorithms, such as ResNet [66] [108], [44], [187], [163], [20], [197], [205], [94], [233], [216], [195], [4], [147], [242], [235] and DenseNet [74], [47], [48].”
BackgroundMethodInfluentialLearning to Draw Text in Natural Images with Conditional Adversarial Networks
Fang, S., Xie, H., Chen, J., Tan, J., & Zhang, Y. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/101 · Cited by 9 · cited 1×
“Instead of complicated feature representations [120] and synthesis approaches [43], [203], an intuitive but rarely noticed solution is to separate the text content from complex backgrounds.”
BackgroundVideo text localization based on Adaboost
Yin, F., Wu, R., Yu, X., & Sun, G. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6064-8 · Cited by 8 · cited 1×
“Most of current methods are based on deep neural networks [68], [233], [226].”
MethodReELFA: A Scene Text Recognizer with Encoded Location and Focused Attention
Wang, Q., Jia, W., He, X., Lu, Y., Blumenstein, M., Huang, Y., & Lyu, S. (2019) · International Conference on Document Analysis and Recognition Workshops (ICDARW) · doi:10.1109/icdarw.2019.40084 · Cited by 6 · cited 4×
“Later, CNNs [227], [25], [107], [234], [127] have been widely used for feature representation stage, such as the VGGNet [170], [161], [162], [79], [24], [217], [193].”
BackgroundMethodInfluentialCINDI Robot: an Intelligent Web Crawler Based on Multi-level Inspection
Chen, R., Desai, B. C., & Zhou, C. (2007) · Proceedings - International Database Engineering and Applications Symposium · doi:10.1109/ideas.2007.4318093 · Cited by 5
A New CNN-Based Method for Multi-Directional Car License Plate Detection
XieLele, AhmadTasweer, JinLianwen, LiuYuliang, & ZhangSheng (2018) · IEEE Transactions on Intelligent Transportation Systems · doi:10.5555/3196158.3196225 · Cited by 4
Express Delivery System based on Fingerprint Identification
Huang, H., Ya, Z., Yin, S., Xiang, J., He, L., Lv, Y., & Huang, P. (2019) · IEEE Information Technology, Networking, Electronic and Automation Control Conference (ITNEC) · doi:10.1109/itnec.2019.8729550 · Cited by 3 · cited 1×
“For example, the number of China’s express delivery business has exceeded 40 billion [75] in 2017.”
BackgroundA Hybrid Approach to Detect and Localize Texts in Natural Scene Images
PanYi-Feng, HouXinwen, & LiuCheng-Lin (2011) · IEEE Transactions on Image Processing · doi:10.5555/2319096.2321816 · Cited by 3
Research works printed but not linked: 73
- Ouais Alsharif and Joelle Pineau . 2014 . End-to-end text recognition with hybrid HMM maxout models . In Proceedings of ICLR. Ouais Alsharif and Joelle Pineau. 2014. End-to-end text recognition with hybrid HMM maxout models. In Proceedings of ICLR.
- Dzmitry Bahdanau , Kyunghyun Cho , and Yoshua Bengio . 2015 . Neural machine translation by jointly learning to align and translate . In Proceedings of ICLR. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In Proceedings of ICLR.
- Christian Bartz , Haojin Yang , and Christoph Meinel . 2018 . SEE: Towards semi-supervised end-to-end scene text recognition . In Proceedings of AAAI. 6674--6681 . Christian Bartz, Haojin Yang, and Christoph Meinel. 2018. SEE: Towards semi-supervised end-to-end scene text recognition. In Proceedings of AAAI. 6674--6681.
- Théodore Bluche . 2016 . Joint line segmentation and transcription for end-to-end handwritten paragraph recognition . In Proceedings of NIPS. 838--846 . Théodore Bluche. 2016. Joint line segmentation and transcription for end-to-end handwritten paragraph recognition. In Proceedings of NIPS. 838--846.
- Chee-Kheng Chng , Yuliang Liu , Yipeng Sun , Chun Chet Ng , Canjie Luo , Zihan Ni , ChuanMing Fang , Shuaitao Zhang , Junyu Han , Errui Ding , et al. 2019 . ICDAR2019 robust reading challenge on arbitrary-shaped text (RRC-ArT). In Proceedings of ICDAR. 1571--1576 . Chee-Kheng Chng, Yuliang Liu, Yipeng Sun, Chun Chet Ng, Canjie Luo, Zihan Ni, ChuanMing Fang, Shuaitao Zhang, Junyu Han, Errui Ding, et al. 2019. ICDAR2019 robust reading challenge on arbitrary-shaped text (RRC-ArT). In Proceedings of ICDAR. 1571--1576.
- Tuan Anh Nguyen Dang and Dat Nguyen Thanh . 2019 . End-to-end information extraction by character-level embedding and multi-stage attentional u-net . In Proceedings of BMVC. 96 . Tuan Anh Nguyen Dang and Dat Nguyen Thanh. 2019. End-to-end information extraction by character-level embedding and multi-stage attentional u-net. In Proceedings of BMVC. 96.
- Abhishek Das , Samyak Datta , Georgia Gkioxari , Stefan Lee , Devi Parikh , and Dhruv Batra . 2018 . Embodied question answering . In Proceedings of CVPR. 2054--2063 . Abhishek Das, Samyak Datta, Georgia Gkioxari, Stefan Lee, Devi Parikh, and Dhruv Batra. 2018. Embodied question answering. In Proceedings of CVPR. 2054--2063.
- Jeffrey Dean , Greg Corrado , Rajat Monga , Kai Chen , Matthieu Devin , Mark Mao , Marc’aurelio Ranzato , Andrew Senior , Paul Tucker , Ke Yang , et al. 2012 . Large scale distributed deep networks . In Proceedings of NIPS. 1223--1231 . Jeffrey Dean, Greg Corrado, Rajat Monga, Kai Chen, Matthieu Devin, Mark Mao, Marc’aurelio Ranzato, Andrew Senior, Paul Tucker, Ke Yang, et al. 2012. Large scale distributed deep networks. In Proceedings of NIPS. 1223--1231.
- Xinjie Feng , Hongxun Yao , and Shengping Zhang . 2019. Focal CTC loss for chinese optical character recognition on unbalanced datasets. Complexity 2019 ( 2019 ), 9345861:1--9345861:11. Xinjie Feng, Hongxun Yao, and Shengping Zhang. 2019. Focal CTC loss for chinese optical character recognition on unbalanced datasets. Complexity 2019 (2019), 9345861:1--9345861:11.
- Vibhor Goel , Anand Mishra , Karteek Alahari , and C. V. Jawahar . 2013. Whole is greater than sum of parts: Recognizing scene text words . In Proceedings of ICDAR. 398--402 . Vibhor Goel, Anand Mishra, Karteek Alahari, and C. V. Jawahar. 2013. Whole is greater than sum of parts: Recognizing scene text words. In Proceedings of ICDAR. 398--402.
- Ian Goodfellow , Jean Pouget-Abadie , Mehdi Mirza , Bing Xu , David Warde-Farley , Sherjil Ozair , Aaron Courville , and Yoshua Bengio . 2014 . Generative adversarial nets . In Proceedings of NIPS. 2672--2680 . Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative adversarial nets. In Proceedings of NIPS. 2672--2680.
- Ian J. Goodfellow , David Warde-Farley , Mehdi Mirza , Aaron Courville , and Yoshua Bengio . 2013 . Maxout networks . In Proceedings of ICML. 1319--1327 . Ian J. Goodfellow, David Warde-Farley, Mehdi Mirza, Aaron Courville, and Yoshua Bengio. 2013. Maxout networks. In Proceedings of ICML. 1319--1327.
- Alex Graves and Navdeep Jaitly . 2014 . Towards end-to-end speech recognition with recurrent neural networks . In Proceedings of ICML. 1764--1772 . Alex Graves and Navdeep Jaitly. 2014. Towards end-to-end speech recognition with recurrent neural networks. In Proceedings of ICML. 1764--1772.
- Dafang He , Xiao Yang , Chen Liang , Zihan Zhou , Alexander G. Ororbi , Daniel Kifer , and C. Lee Giles . 2017. Multi-scale FCN with cascaded instance aware segmentation for arbitrary oriented word spotting in the wild . In Proceedings of CVPR. 3519--3528 . Dafang He, Xiao Yang, Chen Liang, Zihan Zhou, Alexander G. Ororbi, Daniel Kifer, and C. Lee Giles. 2017. Multi-scale FCN with cascaded instance aware segmentation for arbitrary oriented word spotting in the wild. In Proceedings of CVPR. 3519--3528.
- Mengchao He , Yuliang Liu , Zhibo Yang , Sheng Zhang , Canjie Luo , Feiyu Gao , Qi Zheng , Yongpan Wang , Xin Zhang , and Lianwen Jin . 2018 . ICPR2018 Contest on robust reading for multi-type web images. In Proceedings of ICPR. 7--12 . Mengchao He, Yuliang Liu, Zhibo Yang, Sheng Zhang, Canjie Luo, Feiyu Gao, Qi Zheng, Yongpan Wang, Xin Zhang, and Lianwen Jin. 2018. ICPR2018 Contest on robust reading for multi-type web images. In Proceedings of ICPR. 7--12.
- Pan He , Weilin Huang , Yu Qiao , Chen Change Loy , and Xiaoou Tang . 2016 . Reading scene text in deep convolutional sequences . In Proceedings of AAAI. 3501--3508 . Pan He, Weilin Huang, Yu Qiao, Chen Change Loy, and Xiaoou Tang. 2016. Reading scene text in deep convolutional sequences. In Proceedings of AAAI. 3501--3508.
- Gao Huang , Zhuang Liu , Laurens Van Der Maaten, and Kilian Q. Weinberger . 2017 . Densely connected convolutional networks. In Proceedings of CVPR. 4700--4708. Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian Q. Weinberger. 2017. Densely connected convolutional networks. In Proceedings of CVPR. 4700--4708.
- Max Jaderberg , Karen Simonyan , Andrea Vedaldi , and Andrew Zisserman . 2014 . Synthetic data and artificial neural networks for natural scene text recognition . In Proceedings of NIPS-W. Max Jaderberg, Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. 2014. Synthetic data and artificial neural networks for natural scene text recognition. In Proceedings of NIPS-W.
- Max Jaderberg , Karen Simonyan , and Andrew Zisserman . 2015 . Deep structured output learning for unconstrained text recognition . In Proceedings of ICLR. Max Jaderberg, Karen Simonyan, and Andrew Zisserman. 2015. Deep structured output learning for unconstrained text recognition. In Proceedings of ICLR.
- Max Jaderberg , Karen Simonyan , Andrew Zisserman et al . 2015 . Spatial transformer networks . In Proceedings of NIPS. 2017--2025 . Max Jaderberg, Karen Simonyan, Andrew Zisserman et al. 2015. Spatial transformer networks. In Proceedings of NIPS. 2017--2025.
- Dimosthenis Karatzas , Lluis Gomez-Bigorda , Anguelos Nicolaou , Suman Ghosh , Andrew Bagdanov , Masakazu Iwamura , Jiri Matas , Lukas Neumann , Vijay Ramaseshan Chandrasekhar , Shijian Lu , et al. 2015 . ICDAR 2015 competition on robust reading. In Proceedings of ICDAR. 1156--1160 . Dimosthenis Karatzas, Lluis Gomez-Bigorda, Anguelos Nicolaou, Suman Ghosh, Andrew Bagdanov, Masakazu Iwamura, Jiri Matas, Lukas Neumann, Vijay Ramaseshan Chandrasekhar, Shijian Lu, et al. 2015. ICDAR 2015 competition on robust reading. In Proceedings of ICDAR. 1156--1160.
- Dimosthenis Karatzas , Faisal Shafait , Seiichi Uchida , Masakazu Iwamura , Lluis Gomez i Bigorda , Sergi Robles Mestre , Joan Mas , David Fernandez Mota , Jon Almazan Almazan , and Lluis Pere De Las Heras . 2013 . ICDAR 2013 robust reading competition. In Proceedings of ICDAR. 1484--1493 . Dimosthenis Karatzas, Faisal Shafait, Seiichi Uchida, Masakazu Iwamura, Lluis Gomez i Bigorda, Sergi Robles Mestre, Joan Mas, David Fernandez Mota, Jon Almazan Almazan, and Lluis Pere De Las Heras. 2013. ICDAR 2013 robust reading competition. In Proceedings of ICDAR. 1484--1493.
- Thomas N. Kipf and Max Welling . 2017 . Semi-supervised classification with graph convolutional networks. In Proceedings of ICLR. Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of ICLR.
- John D. Lafferty , Andrew McCallum , and Fernando C. N . Pereira . 2001 . Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of ICML. 282--289. John D. Lafferty, Andrew McCallum, and Fernando C. N. Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of ICML. 282--289.
- Minhua Li and Chunheng Wang . 2008 . An adaptive text detection approach in images and video frames . In Proceedings of IJCNN. 72--77 . Minhua Li and Chunheng Wang. 2008. An adaptive text detection approach in images and video frames. In Proceedings of IJCNN. 72--77.
- Minghui Liao , Pengyuan Lyu , Minghang He , Cong Yao , Wenhao Wu , and Xiang Bai . 2019. Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes . IEEE Trans. Pattern Anal. Mach. Intell . ( 2019 ). Minghui Liao, Pengyuan Lyu, Minghang He, Cong Yao, Wenhao Wu, and Xiang Bai. 2019. Mask textspotter: An end-to-end trainable neural network for spotting text with arbitrary shapes. IEEE Trans. Pattern Anal. Mach. Intell. (2019).
- Minghui Liao , Baoguang Shi , Xiang Bai , Xinggang Wang , and Wenyu Liu . 2017 . Textboxes: A fast text detector with a single deep neural network . In Proceedings of AAAI. 4161--4167 . Minghui Liao, Baoguang Shi, Xiang Bai, Xinggang Wang, and Wenyu Liu. 2017. Textboxes: A fast text detector with a single deep neural network. In Proceedings of AAAI. 4161--4167.
- Ron Litman , Oron Anschel , Shahar Tsiper , Roee Litman , Shai Mazor , and R. Manmatha . 2020. SCATTER: Selective context attentional scene text recognizer . In Proceedings of CVPR. Ron Litman, Oron Anschel, Shahar Tsiper, Roee Litman, Shai Mazor, and R. Manmatha. 2020. SCATTER: Selective context attentional scene text recognizer. In Proceedings of CVPR.
- Fei Liu , Jeffrey Flanigan , Sam Thomson , Norman Sadeh , and Noah A . Smith . 2018 . Toward abstractive summarization using semantic representations. CoRR abs/1805.10399. Fei Liu, Jeffrey Flanigan, Sam Thomson, Norman Sadeh, and Noah A. Smith. 2018. Toward abstractive summarization using semantic representations. CoRR abs/1805.10399. · arXiv
- Hu Liu , Sheng Jin , and Changshui Zhang . 2018 . Connectionist temporal classification with maximum entropy regularization . In Proceedings of NIPS. 831--841 . Hu Liu, Sheng Jin, and Changshui Zhang. 2018. Connectionist temporal classification with maximum entropy regularization. In Proceedings of NIPS. 831--841.
- Wei Liu , Chaofeng Chen , and Kwan-Yee K. Wong . 2018. Char-Net: A character-aware neural network for distorted scene text recognition . In Proceedings of AAAI. 7154--7161 . Wei Liu, Chaofeng Chen, and Kwan-Yee K. Wong. 2018. Char-Net: A character-aware neural network for distorted scene text recognition. In Proceedings of AAAI. 7154--7161.
- Xi Liu , Rui Zhang , Yongsheng Zhou , Qianyi Jiang , Qi Song , Nan Li , Kai Zhou , Lei Wang , Dong Wang , Minghui Liao , et al. 2019 . ICDAR 2019 robust reading challenge on reading chinese text on signboard. In Proceedings of ICDAR. 1577--1581 . Xi Liu, Rui Zhang, Yongsheng Zhou, Qianyi Jiang, Qi Song, Nan Li, Kai Zhou, Lei Wang, Dong Wang, Minghui Liao, et al. 2019. ICDAR 2019 robust reading challenge on reading chinese text on signboard. In Proceedings of ICDAR. 1577--1581.
- Zichuan Liu , Yixing Li , Fengbo Ren , Wang Ling Goh , and Hao Yu . 2018 . Squeezedtext: A real-time scene text recognition by binary convolutional encoder-decoder network . In Proceedings of AAAI. 7194--7201 . Zichuan Liu, Yixing Li, Fengbo Ren, Wang Ling Goh, and Hao Yu. 2018. Squeezedtext: A real-time scene text recognition by binary convolutional encoder-decoder network. In Proceedings of AAAI. 7194--7201.
- Shangbang Long and Cong Yao . 2020 . UnrealText: Synthesizing realistic scene text images from the unreal world . In Proceedings of CVPR. Shangbang Long and Cong Yao. 2020. UnrealText: Synthesizing realistic scene text images from the unreal world. In Proceedings of CVPR.
- Fang Lu , Corey S. McCaffrey , and Elaine I. Kuo . 2011 . Foreign language abbreviation translation in an instant messaging system . U.S. Patent 7 , 890 ,525. Fang Lu, Corey S. McCaffrey, and Elaine I. Kuo. 2011. Foreign language abbreviation translation in an instant messaging system. U.S. Patent 7,890,525.
- Simon M. Lucas . 2005 . ICDAR 2005 text locating competition results. In Proceedings of ICDAR. 80--84 . Simon M. Lucas. 2005. ICDAR 2005 text locating competition results. In Proceedings of ICDAR. 80--84.
- Simon M. Lucas , Alex Panaretos , Luis Sosa , Anthony Tang , Shirley Wong , and Robert Young . 2003 . ICDAR 2003 robust reading competitions. In Proceedings of ICDAR. 682--687 . Simon M. Lucas, Alex Panaretos, Luis Sosa, Anthony Tang, Shirley Wong, and Robert Young. 2003. ICDAR 2003 robust reading competitions. In Proceedings of ICDAR. 682--687.
- Canjie Luo , Qingxiang Lin , Yuliang Liu , Jin Lianwen , and Shen Chunhua . 2020. Separating content from style using adversarial learning for recognizing text in the wild . Int. J. Comput. Vis ( 2020 ). Canjie Luo, Qingxiang Lin, Yuliang Liu, Jin Lianwen, and Shen Chunhua. 2020. Separating content from style using adversarial learning for recognizing text in the wild. Int. J. Comput. Vis (2020).
- Jieru Mei , Luo Dai , Baoguang Shi , and Xiang Bai . 2016 . Scene text script identification with convolutional recurrent neural networks . In Proceedings of ICPR. 4053--4058 . Jieru Mei, Luo Dai, Baoguang Shi, and Xiang Bai. 2016. Scene text script identification with convolutional recurrent neural networks. In Proceedings of ICPR. 4053--4058.
- Anand Mishra , Karteek Alahari , and C. V. Jawahar . 2012. Scene text recognition using higher order language priors . In Proceedings of BMVC. 1--11 . Anand Mishra, Karteek Alahari, and C. V. Jawahar. 2012. Scene text recognition using higher order language priors. In Proceedings of BMVC. 1--11.
- Anand Mishra , Karteek Alahari , and C. V. Jawahar . 2012. Top-down and bottom-up cues for scene text recognition . In Proceedings of CVPR. 2687--2694 . Anand Mishra, Karteek Alahari, and C. V. Jawahar. 2012. Top-down and bottom-up cues for scene text recognition. In Proceedings of CVPR. 2687--2694.
- Ali Mosleh , Nizar Bouguila , and A. Ben Hamza . 2012. Image text detection using a bandlet-based edge detector and stroke width transform . In Proceedings of BMVC. 1--12 . Ali Mosleh, Nizar Bouguila, and A. Ben Hamza. 2012. Image text detection using a bandlet-based edge detector and stroke width transform. In Proceedings of BMVC. 1--12.
- Yuval Netzer , Tao Wang , Adam Coates , Alessandro Bissacco , Bo Wu , and Andrew Y . Ng . 2011 . Reading digits in natural images with unsupervised feature learning. In Proceedings of NIPS. Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, and Andrew Y. Ng. 2011. Reading digits in natural images with unsupervised feature learning. In Proceedings of NIPS.
- Lukas Neumann and Jiri Matas . 2010 . A method for text localization and recognition in real-world images . In Proceedings of ACCV. 770--783 . Lukas Neumann and Jiri Matas. 2010. A method for text localization and recognition in real-world images. In Proceedings of ACCV. 770--783.
- Clément Peyrard , Moez Baccouche , Franck Mamalet , and Christophe Garcia . 2015 . ICDAR2015 competition on text image super-resolution. In Proceedings of ICDAR. 1201--1205 . Clément Peyrard, Moez Baccouche, Franck Mamalet, and Christophe Garcia. 2015. ICDAR2015 competition on text image super-resolution. In Proceedings of ICDAR. 1201--1205.
- Weichao Qiu and Alan L . Yuille . 2016 . UnrealCV: Connecting computer vision to unreal engine. In Proceedings of ECCV. 909--916. Weichao Qiu and Alan L. Yuille. 2016. UnrealCV: Connecting computer vision to unreal engine. In Proceedings of ECCV. 909--916.
- Alain Rouh and Jean Beaudet . 2019 . Method and a device for tracking characters that appear on a plurality of images of a video stream of a text . U.S. Patent App. 10/185 , 873 . Alain Rouh and Jean Beaudet. 2019. Method and a device for tracking characters that appear on a plurality of images of a video stream of a text. U.S. Patent App. 10/185,873.
- Joan Andreu Sanchez , Verónica Romero , Alejandro H. Toselli , Mauricio Villegas , and Enrique Vidal . 2017 . ICDAR2017 competition on handwritten text recognition on the read dataset. In Proceedings of ICDAR. 1383--1388 . Joan Andreu Sanchez, Verónica Romero, Alejandro H. Toselli, Mauricio Villegas, and Enrique Vidal. 2017. ICDAR2017 competition on handwritten text recognition on the read dataset. In Proceedings of ICDAR. 1383--1388.
- Pierre Sermanet , Soumith Chintala , and Yann LeCun . 2012 . Convolutional neural networks applied to house numbers digit classification . In Proceedings of ICPR. 3288--3291 . Pierre Sermanet, Soumith Chintala, and Yann LeCun. 2012. Convolutional neural networks applied to house numbers digit classification. In Proceedings of ICPR. 3288--3291.
- Asif Shahab , Faisal Shafait , and Andreas Dengel . 2011 . ICDAR 2011 robust reading competition challenge 2: Reading text in scene images. In Proceedings of ICDAR. 1491--1496 . Asif Shahab, Faisal Shafait, and Andreas Dengel. 2011. ICDAR 2011 robust reading competition challenge 2: Reading text in scene images. In Proceedings of ICDAR. 1491--1496.
- Baoguang Shi , Cong Yao , Minghui Liao , Mingkun Yang , Pei Xu , Linyan Cui , Serge Belongie , Shijian Lu , and Xiang Bai . 2017 . ICDAR2017 competition on reading Chinese text in the wild. In Proceedings of ICDAR. 1429--1434 . Baoguang Shi, Cong Yao, Minghui Liao, Mingkun Yang, Pei Xu, Linyan Cui, Serge Belongie, Shijian Lu, and Xiang Bai. 2017. ICDAR2017 competition on reading Chinese text in the wild. In Proceedings of ICDAR. 1429--1434.
- Karen Simonyan and Andrew Zisserman . 2015 . Very deep convolutional networks for large-scale image recognition . In Proceedings of ICLR. Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In Proceedings of ICLR.
- Amanpreet Singh , Vivek Natarajan , Meet Shah, Yu Jiang, Xinlei Chen, Dhruv Batra, Devi Parikh, and Marcus Rohrbach. 2019. Towards VQA models that can read. In Proceedings of CVPR. 8317--8326 . Amanpreet Singh, Vivek Natarajan, Meet Shah, Yu Jiang, Xinlei Chen, Dhruv Batra, Devi Parikh, and Marcus Rohrbach. 2019. Towards VQA models that can read. In Proceedings of CVPR. 8317--8326.
- Ajeet Kumar Singh , Anand Mishra , Pranav Dabral , and C. V. Jawahar . 2016. A simple and effective solution for script identification in the wild . In Proceedings of IAPR DAS. 428--433 . Ajeet Kumar Singh, Anand Mishra, Pranav Dabral, and C. V. Jawahar. 2016. A simple and effective solution for script identification in the wild. In Proceedings of IAPR DAS. 428--433.
- Bolan Su and Shijian Lu . 2014 . Accurate scene text recognition based on recurrent neural network . In Proceedings of ACCV. 35--48 . Bolan Su and Shijian Lu. 2014. Accurate scene text recognition based on recurrent neural network. In Proceedings of ACCV. 35--48.
- Yipeng Sun , Zihan Ni , Chee-Kheng Chng , Yuliang Liu , Canjie Luo , Chun Chet Ng , Junyu Han , Errui Ding , Jingtuo Liu , Dimosthenis Karatzas et al . 2019 . ICDAR 2019 Competition on large-scale street view text with partial labeling--RRC-LSVT. In Proceedings of ICDAR. 1557--1562 . Yipeng Sun, Zihan Ni, Chee-Kheng Chng, Yuliang Liu, Canjie Luo, Chun Chet Ng, Junyu Han, Errui Ding, Jingtuo Liu, Dimosthenis Karatzas et al. 2019. ICDAR 2019 Competition on large-scale street view text with partial labeling--RRC-LSVT. In Proceedings of ICDAR. 1557--1562.
- Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N. Gomez , Łukasz Kaiser , and Illia Polosukhin . 2017 . Attention is all you need . In Proceedings of NIPS. 5998--6008 . Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of NIPS. 5998--6008.
- Andreas Veit , Tomas Matera , Lukas Neumann , Jiri Matas , and Serge Belongie . 2016 . Coco-text: Dataset and benchmark for text detection and recognition in natural images. CoRR abs/1601.07140. Andreas Veit, Tomas Matera, Lukas Neumann, Jiri Matas, and Serge Belongie. 2016. Coco-text: Dataset and benchmark for text detection and recognition in natural images. CoRR abs/1601.07140. · arXiv
- Luis Von Ahn , Benjamin Maurer , Colin McMillen , David Abraham , and Manuel Blum . 2008 . Recaptcha: Human-based character recognition via web security measures. Science 321, 5895 (2008), 1465--1468. Luis Von Ahn, Benjamin Maurer, Colin McMillen, David Abraham, and Manuel Blum. 2008. Recaptcha: Human-based character recognition via web security measures. Science 321, 5895 (2008), 1465--1468.
- Jianfeng Wang and Xiaolin Hu . 2017 . Gated recurrent convolution neural network for OCR . In Proceedings of NIPS. 335--344 . Jianfeng Wang and Xiaolin Hu. 2017. Gated recurrent convolution neural network for OCR. In Proceedings of NIPS. 335--344.
- Kai Wang , Boris Babenko , and Serge Belongie . 2011 . End-to-end scene text recognition . In Proceedings of ICCV. 1457--1464 . Kai Wang, Boris Babenko, and Serge Belongie. 2011. End-to-end scene text recognition. In Proceedings of ICCV. 1457--1464.
- Peng Wang Lu Yang Hui Li Yuyan Deng Chunhua Shen and Yanning Zhang. 2019. A simple and robust convolutional-attention network for irregular text recognition. CoRR abs/1904.01375. Peng Wang Lu Yang Hui Li Yuyan Deng Chunhua Shen and Yanning Zhang. 2019. A simple and robust convolutional-attention network for irregular text recognition. CoRR abs/1904.01375. · arXiv
- Tao Wang , David J. Wu , Adam Coates , and Andrew Y . Ng . 2012 . End-to-end text recognition with convolutional neural networks. In Proceedings of ICPR. 3304--3308. Tao Wang, David J. Wu, Adam Coates, and Andrew Y. Ng. 2012. End-to-end text recognition with convolutional neural networks. In Proceedings of ICPR. 3304--3308.
- Xinyu Wang , Yuliang Liu , Chunhua Shen , Chun Chet Ng , Canjie Luo, Lianwen Jin, Chee Seng Chan, Anton van den Hengel, and Liangwei Wang. 2020 . On the general value of evidence, and bilingual scene-text visual question answering. In Proceedings of CVPR. Xinyu Wang, Yuliang Liu, Chunhua Shen, Chun Chet Ng, Canjie Luo, Lianwen Jin, Chee Seng Chan, Anton van den Hengel, and Liangwei Wang. 2020. On the general value of evidence, and bilingual scene-text visual question answering. In Proceedings of CVPR.
- Fred L. Bookstein Principal Warps . 1989 . Thin-plate splines and the decompositions of deformations . IEEE Trans. Pattern Anal. Mach. Intell. 11 , 6 (1989). Fred L. Bookstein Principal Warps. 1989. Thin-plate splines and the decompositions of deformations. IEEE Trans. Pattern Anal. Mach. Intell. 11, 6 (1989).
- Linjie Xing , Zhi Tian , Weilin Huang , and Matthew R . Scott . 2019 . Convolutional character networks. In Proceedings of ICCV. 9125--9135. Linjie Xing, Zhi Tian, Weilin Huang, and Matthew R. Scott. 2019. Convolutional character networks. In Proceedings of ICCV. 9125--9135.
- Xiao Yang , Dafang He , Zihan Zhou , Daniel Kifer , and C. Lee Giles . 2017. Learning to read irregular text with attention mechanisms . In Proceedings of IJCAI. 3280--3286 . Xiao Yang, Dafang He, Zihan Zhou, Daniel Kifer, and C. Lee Giles. 2017. Learning to read irregular text with attention mechanisms. In Proceedings of IJCAI. 3280--3286.
- Cong Yao , Xiang Bai , Wenyu Liu , Yi Ma , and Zhuowen Tu . 2012 . Detecting texts of arbitrary orientations in natural images . In Proceedings of CVPR. 1083--1090 . Cong Yao, Xiang Bai, Wenyu Liu, Yi Ma, and Zhuowen Tu. 2012. Detecting texts of arbitrary orientations in natural images. In Proceedings of CVPR. 1083--1090.
- Qixiang Ye , Wen Gao , Weiqiang Wang , and Wei Zeng . 2003 . A robust text detection algorithm in images and video frames . In Proceedings of ICASSP. IEEE, 802--806 . Qixiang Ye, Wen Gao, Weiqiang Wang, and Wei Zeng. 2003. A robust text detection algorithm in images and video frames. In Proceedings of ICASSP. IEEE, 802--806.
- Fei Yin , Yi-Chao Wu , Xu-Yao Zhang , and Cheng-Lin Liu . 2017 . Scene text recognition with sliding convolutional character models . In Proceedings of ICCV. Fei Yin, Yi-Chao Wu, Xu-Yao Zhang, and Cheng-Lin Liu. 2017. Scene text recognition with sliding convolutional character models. In Proceedings of ICCV.
- Tai-Ling Yuan Zhe Zhu Kun Xu Cheng-Jun Li and Shi-Min Hu. 2018. Chinese text in the wild. CoRR abs/1803.00085. Tai-Ling Yuan Zhe Zhu Kun Xu Cheng-Jun Li and Shi-Min Hu. 2018. Chinese text in the wild. CoRR abs/1803.00085. · arXiv
- Sheng Zhang , Yuliang Liu , Lianwen Jin , and Canjie Luo . 2018 . Feature enhancement network: A refined scene text detector . In Proceedings of AAAI. 2612--2619 . Sheng Zhang, Yuliang Liu, Lianwen Jin, and Canjie Luo. 2018. Feature enhancement network: A refined scene text detector. In Proceedings of AAAI. 2612--2619.
- Yu Zhou , Shuang Liu , Yongzheng Zhang , Yipeng Wang , and Weiyao Lin . 2014 . Perspective scene text recognition with feature compression and ranking . In Proceedings of ACCV. 181--195 . Yu Zhou, Shuang Liu, Yongzheng Zhang, Yipeng Wang, and Weiyao Lin. 2014. Perspective scene text recognition with feature compression and ranking. In Proceedings of ACCV. 181--195.
Cited by
Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances
Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., & Alshurafa, N. (2022) · Sensors · doi:10.3390/s22041476 · Cited by 625
Scene Text Recognition with Permuted Autoregressive Sequence Models
Bautista, D., & Atienza, R. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19815-1_11 · Cited by 267
DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting
Ye, M., Zhang, J., Zhao, S., Liu, J., Liu, T., Du, B., & Tao, D. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01854 · Cited by 142
A Comprehensive Review on Vision-Based Violence Detection in Surveillance Videos
Ullah, F. U. M., Obaidat, M. S., Ullah, A., Muhammad, K., Hijji, M., & Baik, S. W. (2022) · ACM Computing Surveys · doi:10.1145/3561971 · Cited by 133
Conditional Text Image Generation with Diffusion Models
Zhu, Y., Li, Z., Wang, T., He, M., & Yao, C. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01368 · Cited by 164
Self-citation
Metadata
- Authors
- Chen, X., Jin, L., Zhu, Y., Luo, C., & Wang, T.
- Affiliations
- South China University of Technology (CN)
- Venue
- ACM Computing Surveys
- Published
- 2021-03-05
- Volume
- 54
- Issue
- 2
- Pages
- 1-35
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W3134064484
- Semantic Scholar
- 2cb9407082a8627408961b572ad5a74d50e3c811
- Cited by
- 205
- References
- 170
- Citations by year
- 2026: 27 · 2025: 39 · 2024: 38 · 2023: 50 · 2022: 31 · 2021: 20
- FWCI
- 12.51
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- ACM Computing Surveys (publishedVersion)
- Funders
- Guangdong Intellectual Property Office Project (2018-10-1)
- National Natural Science Foundation of China (61936003)
- Natural Science Foundation of Guangdong Province (2017A030312006)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Handwritten Text Recognition Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Vehicle License Plate Recognition
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- scene text recognition, natural scene text, text detection, text localization, text recognition, benchmark dataset
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.