The DOI matches its Crossref record; 44 of the 45 references it cites were found in a registry or an index.
Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Peng et al. (2019) [89] Structured Light Laser line grid projector images, IHED deep learning model Box volume measurement Measure volumes ranging from 100 mm to 1800 mm with an accuracy of ±5.0 mm”
From Use and Potential of AI in Assisting Surveyors in Building Retrofit and Demolition—A Scoping Review (2025) · cites this paper as [89]
Citations
Cites
(1967) · Cited by 23,719
Stochastic relaxation, gibbs distributions, and the bayesian restoration of images.
Geman, S., & Geman, D. (1984) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.1984.4767596 · Cited by 17,949
Press, W. H., Teukolsky, S. A., Vetterling, W. T., & Flannery, B. P. (1994) · Cited by 15,411
Turk, M., & Pentland, A. (1991) · Journal of Cognitive Neuroscience · doi:10.1162/jocn.1991.3.1.71 · Cited by 13,733
(1973) · CERN Document Server (European Organization for Nuclear Research) · Cited by 12,895
Markov Chain Monte Carlo in Practice
Gilks, W. R., Richardson, S. T., & Spiegelhalter, D. J. (1995) · Chapman & Hall/CRC eBooks · doi:10.1201/b14835 · Cited by 7,927
Vector Quantization and Signal Compression
Gersho, A., & Gray, R. M. (1992) · Springer eBooks · doi:10.1007/978-1-4615-3626-0 · Cited by 7,055
Pattern Recognition and Neural Networks
Ripley, B. D. (1996) · Cambridge University Press eBooks · doi:10.1017/cbo9780511812651 · Cited by 6,500
The Laplacian pyramid as a compact image code
Burt, P., & Adelson, E. (1983) · IEEE Transactions on Communications · doi:10.1109/tcom.1983.1095851 · Cited by 6,077
Multirate Systems and Filter Banks
Vaidyanathan, P. P. (1992) · CaltechAUTHORS (California Institute of Technology) · Cited by 5,457
Flagged first, then by citations
1 of the 45 references couldn’t be matched to a known paper.
Research works printed but not linked: 2
- Dana, K. and Nayar, S. 1999a. 3D textured surface modelling. In Proceedings Workshop on the Integration of Appearance and Geometric Methods in Object Recognition, pp. 46-56.
- Yuan, J. and Rao, S. 1993. Spectral estimation for random fields with applications to Markov modeling and texture classification. In Markov Random Fields: Theory and Application, R. Chellappa and A. Jain (Eds.). Academic Press.
Cited by
Sorted by citations
The multimodal brain tumor image segmentation benchmark (BRATS)
Menze, B. H., Jakab, A., Bauer, S., Kalpathy-Cramer, J., Farahani, K., Kirby, J., Burren, Y., Porz, N., Slotboom, J., Wiest, R., et al. (2015) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2014.2377694 · Cited by 6,781
“To characterize the tumor surface variation, we employ our novel texture features such as fractal PTPSA [107], and mBm [108] as well as classical textons [109] as the second set of features.”
MethodVisual categorization with bags of keypoints
Csurka, G. (2004) · Cited by 4,379
A Bayesian Hierarchical Model for Learning Natural Scene Categories
Fei-Fei, L., & Perona, P. (2005) · 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.2005.16 · Cited by 3,665
“One way to think about our model is as a generalization of the the “texton models” [5, 16] for textures, which require samples of “pure” texture to be trained.”
BackgroundMethodInfluentialLaptev, I. (2005) · International Journal of Computer Vision · doi:10.1007/s11263-005-1838-7 · Cited by 2,672
Describing Textures in the Wild
Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., & Vedaldi, A. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.461 · Cited by 2,438
“The most common coding method is to vector quantize the descriptors using an algorithm such as K -means [19], resulting in the so-called bag-of-visual-words (BoVW) representation [8].”
BackgroundMethodInfluentialYOLACT: Real-Time Instance Segmentation
Bolya, D., Zhou, C., Xiao, F., & Lee, Y. J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00925 · Cited by 2,536
“sets (13.5 fps on 5502 px images; see Table2c). Prototypes Learning prototypes (aka vocabulary or codebook) has been extensively explored in computer vision. Classical representations include textons [21] and visual words [37], with advances made via sparsity and locality priors [42,41,44]. Others have designed protot…”
MethodInfluentialZhang, J., Marszałek, M., Lazebnik, S., & Schmid, C. (2006) · International Journal of Computer Vision · doi:10.1007/s11263-006-9794-4 · Cited by 1,962
Understanding deep image representations by inverting them
Mahendran, A., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7299155 · Cited by 1,827
“Most image understanding and computer vision methods build on image representations such as textons [17], histogram of oriented gradients (SIFT [20] and HOG [4]), bag of visual words [3][27], sparse [37] and local coding [34], super vector coding [40], VLAD [10], Fisher Vectors [23], and, lately, deep neural networks,…”
BackgroundEvaluating Color Descriptors for Object and Scene Recognition
van de Sande, K. E. A., Gevers, T., & Snoek, C. G. M. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.154 · Cited by 1,837
“The bag-of-words model is also known as “textons” [30], “object parts” [31], and “codebooks” [32], [33].”
Invariant Scattering Convolution Networks
Bruna, J., & Mallat, S. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2012.230 · Cited by 1,633
“For texture analysis, many researchers [21], [31] have been using averaged wavelet coefficient amplitudes jx ? j ?”
MethodContext Encoding for Semantic Segmentation
Zhang, H., Dana, K., Shi, J., Zhang, Z., Wang, X., Tyagi, A., & Agrawal, A. (2018) · 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.2018.00747 · Cited by 1,528
“For a given input image, hand-engineered features are densely extracted using SIFT [37] or filter bank responses [30,46].”
MethodSemantic object classes in video: A high-definition ground truth database
Brostow, G., Fauqueur, J., & Cipolla, R. (2008) · Pattern Recognition Letters · doi:10.1016/j.patrec.2008.04.005 · Cited by 1,426
“Rather than pixel intensities directly, the image features being classified are grouped as 200 texton (Leung and Malik, 2001) clusters.”
BackgroundA large-scale hierarchical multi-view RGB-D object dataset
Lai, K., Bo, L., Ren, X., & Fox, D. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980382 · Cited by 1,353
“Additionally, we extract texton histograms [20] features, which capture texture information using oriented gaussian filter responses.”
MethodLaptev, & Lindeberg, T. (2003) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2003.1238378 · Cited by 1,321
“Similar approach has proven to be successful in the spatial domain for the task of image representation [21] indexing [25] and recognition [10, 31, 16].”
BackgroundSalient Object Detection: A Discriminative Regional Feature Integration Approach
Jiang, H., Wang, J., Yuan, Z., Wu, Y., Zheng, N., & Li, S. (2013) · 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.2013.271 · Cited by 1,177
Shotton, J., Winn, J. M., Rother, C., & Criminisi, A. (2006) · Lecture notes in computer science · doi:10.1007/11744023_1 · Cited by 1,154
“For this we utilize textons [17] which have been proven effective in categorizing materials [18] as well as generic object classes [4].”
MethodRegion Covariance: A Fast Descriptor for Detection and Classification
Tuzel, O., Porikli, F., & Meer, P. (2006) · Lecture notes in computer science · doi:10.1007/11744047_45 · Cited by 1,146
“Besides tracking, histograms were also used for texture representation [8, 9], matching [10] and other problems in the field of computer vision.”
MethodA Statistical Approach to Texture Classification from Single Images
Varma, M., & Zisserman, A. (2005) · International Journal of Computer Vision · doi:10.1007/s11263-005-4635-4 · Cited by 1,144
“Leung and Malik (2001) were amongst the first to seriously tackle the problem of classifying textures under varying viewpoint and illumination.”
BackgroundMethodResultInfluentialSVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition
Zhang, H., Berg, A. C., Maire, M., & Malik, J. (2006) · 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.2006.301 · Cited by 1,138
“In our previous work on Caltech-101 (Berg, Berg and Malik [3]), we sought to find shape correspondence in a deformable template paradigm.”
BackgroundMethodInfluentialSelf-citationA sparse texture representation using local affine regions
Lazebnik, S., Schmid, C., & Ponce, J. (2005) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2005.151 · Cited by 1,138
Cremers, D., Rousson, M., & Rachid Deriche, B. (2006) · International Journal of Computer Vision · doi:10.1007/s11263-006-8711-1 · Cited by 1,003
“More sophisticated features are conceivable as well (Leung and Malik, 2001).”
BackgroundSampling Strategies for Bag-of-Features Image Classification
Nowak, E., Jurie, F., & Triggs, B. (2006) · Lecture Notes in Computer Science · doi:10.1007/11744085_38 · Cited by 927
“Patches are selected using keypoints [4, 1, 2, 5, 6, 7, 8, 9, 10, 11] or densely [3, 13, 15].”
InfluentialGao, Y., Beijbom, O., Zhang, N., & Darrell, T. (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.2016.41 · Cited by 919
“Leung and Malik used vector quantization in the Bag of Visual Words (BoVW) framework [20] initially used for texture classification, but later adopted for other visual tasks.”
BackgroundMethodBosch, A., Zisserman, A., & Muñoz, X. (2006) · Lecture notes in computer science · doi:10.1007/11744085_40 · Cited by 771
“[2, 8, 18], have been used.”
Review of MRI-based brain tumor image segmentation using deep learning methods
Işın, A., Direkoğlu, C., & Şah, M. (2016) · Procedia Computer Science · doi:10.1016/j.procs.2016.09.407 · Cited by 766
“Features like, asymmetry-related features 19 , discrete wavelet transforms 20 (DWT), textons 21 , multifractal Brownian motion features 22 , first order statistical features 19 , raw intensities, local image textures, intensity gradients and edge based features 12 are some examples.”
BackgroundDiscriminative learned dictionaries for local image analysis
Mairal, J., Bach, F., Ponce, J., Sapiro, G., & Zisserman, A. (2008) · 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.2008.4587652 · Cited by 735
Creating efficient codebooks for visual recognition
Jurie, F., & Triggs, B. (2005) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2005.66 · Cited by 713
“[18] use Gabor texture features for texture classification.”
InfluentialScene Classification Using a Hybrid Generative/Discriminative Approach
Bosch, A., Zisserman, A., & Muñoz, X. (2008) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.70716 · Cited by 682
“Previously, both sparse [7], [17], [28] and dense descriptors, for example, [8], [19], [31] have been used.”
BackgroundRecovering Surface Layout from an Image
Hoiem, D., Efros, A. A., & Hebert, M. (2007) · International Journal of Computer Vision · doi:10.1007/s11263-006-0031-y · Cited by 678
“To represent texture, we apply a subset of the filter bank designed by Leung and Malik (2001).”
MethodInfluentialDeep filter banks for texture recognition and segmentation
Cimpoi, M., Maji, S., & Vedaldi, 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.2015.7299007 · Cited by 670
“Hence, a significant amount of effort in the computer vision community has gone into recognizing texture via tasks such as texture perception [1, 2, 12, 13] and description [7, 11], material recognition [26, 36, 37], segmentation [20, 29], and even synthesis [9, 43].”
BackgroundA Statistical Approach to Material Classification Using Image Patch Exemplars
Varma, M., & Zisserman, A. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.182 · Cited by 617
“In this section, we describe the Columbia-Utrecht (CUReT) database [10] and its level of difficulty for single image classification.”
BackgroundMethodResultInfluentialPothole detection in asphalt pavement images
Koch, C., & Brilakis, I. (2011) · Advanced Engineering Informatics · doi:10.1016/j.aei.2011.01.002 · Cited by 590
Kernel Codebooks for Scene Categorization
van Gemert, J. C., Geusebroek, J., Veenman, C. J., & Smeulders, A. W. M. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-88690-7_52 · Cited by 606
“The codebook approach is inspired by a word-document representation as used in text retrieval, first applied on images in texture recognition [1].”
BackgroundMethodTexture Feature Extraction Methods: A Survey
Humeau‐Heurtier, A. (2019) · IEEE Access · doi:10.1109/access.2018.2890743 · Cited by 524
“In 2001, Leung and Malik [231] built a small, finite vocabulary of micro-structures.”
BackgroundUnsupervised Discovery of Mid-Level Discriminative Patches
Singh, S., Gupta, A., & Efros, A. A. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-33709-3_6 · Cited by 517
“At a slightly higher level, combining such patches together, typically by clustering and histogramming, allows one to represent texture information (e.g., textons [9], dense bag-of-words [2], etc).”
BackgroundMaterial recognition in the wild with the Materials in Context Database
Bell, S., Upchurch, P., Snavely, N., & Bala, K. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298970 · Cited by 516
“This led to research on the task of instance-level texture or material classification [15, 30], and an appreciation of the challenges of building features that are invariant to pose and illumination.”
BackgroundVisualizing Deep Convolutional Neural Networks Using Natural Pre-images
Mahendran, A., & Vedaldi, A. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-016-0911-8 · Cited by 500
“Notable examples of representations include textons [22], histogram of oriented gradients (SIFT [25] and HOG [5]), bag of visual words [4][36], sparse [46] and local coding [43], super vector coding [51], VLAD [15], Fisher Vectors [31], and, lately,”
BackgroundFast Discriminative Visual Codebooks using Randomized Clustering Forests
Moosmann, F., Triggs, B., & Jurie, F. (2007) · Advances in Neural Information Processing Systems 19 · doi:10.7551/mitpress/7503.003.0128 · Cited by 467
“The usual way to handle the resulting set of descriptor vectors is to vector quantize them to produce socalled textons [ 12 ] or visual words [5, 22].”
BackgroundTwo Systems for the Detection of Melanomas in Dermoscopy Images Using Texture and Color Features
Barata, C., Ruela, M., Francisco, M., Mendonça, T., & Marques, J. S. (2013) · IEEE Systems Journal · doi:10.1109/jsyst.2013.2271540 · Cited by 456
“, image retrieval and object-class recognition in large databases [53], [54].”
BackgroundFace recognition with learning-based descriptor
Cao, Z., Yin, Q., Tang, X., & Sun, J. Z. (2010) · 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.2010.5539992 · Cited by 438
“Many recent researches also apply learning approaches in face recognition, such as subspace learning [25, 26], metric learning [9], high-level trait learning [13], discriminant model learning [20, 30, 31], but few of these works focus on the issue of local feature encoding [14, 24] and the study of descriptor compactn…”
BackgroundTexture classification: are filter banks necessary?
Varma, M., & Zisserman, A. (2003) · 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.2003.1211534 · Cited by 428
“These filter response distributions were learnt from training images and represented by clusters [2, 11, 15, 17], or histograms [9, 10, 19].”
BackgroundMethodInfluentialUnsupervised Feature Learning for Aerial Scene Classification
Cheriyadat, A. (2013) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2013.2241444 · Cited by 418
“Following [21], for each scale we set the Gaussian width correspondingly to {1, √ 2, 2, 2 √ 2}.”
MethodInfluentialAutomatic Attribute Discovery and Characterization from Noisy Web Data
Berg, T. L., Berg, A. C., & Shih, J. J. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15549-9_48 · Cited by 418
“Finally, for the texture descriptor we first convolve the image with a set of 16 oriented bar and spot filters [25], then accumulate absolute response to each of the filters in a texture histogram.”
MethodMean shift based clustering in high dimensions: a texture classification example
Georgescu, Shimshoni, I., & Meer (2003) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2003.1238382 · Cited by 413
“– LM: A combination of 48 anisotropic and isotropic filters were used by Leung and Malik [12] and Cula and Dana [3].”
BackgroundMethodInfluentialEfficient Visual Search of Videos Cast as Text Retrieval
Sivic, J., & Zisserman, A. (2009) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2008.111 · Cited by 499
“Here, document vectors are treated as normalized histograms (probability distributions) over terms [13], [ 15 ], [27], [43], [44], i.e., relative word frequencies (7) are used (vectors are normalized to sum to one).”
MethodA theory of eye movements during target acquisition.
Zelinsky, G. J. (2008) · Psychological Review · doi:10.1037/a0013118 · Cited by 407
“, 1993 ; Leung & Malik , 2001 ; Malik & Perona , 1990 ; Olshausen & Field , 1996 ; Rohaly , Ahumada , & Watson , 1997 ; see Landy & Movshon , 1991 , for a review ) , and their inclusion in a search model would lend a measure of biological plausibility to the approach .”
YOLACT++ Better Real-Time Instance Segmentation
Bolya, D., Zhou, C., Xiao, F., & Lee, Y. J. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.3014297 · Cited by 544
“Classical representations include textons [41] and visual words [42], with advances made via sparsity and locality”
BackgroundAmbient Sound Provides Supervision for Visual Learning
Owens, A., Wu, J., McDermott, J. H., Freeman, W. T., & Torralba, A. B. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46448-0_48 · Cited by 391
From BoW to CNN: Two Decades of Texture Representation for Texture Classification
Liu, L., Chen, J., Fieguth, P., Zhao, G., Chellappa, R., & Pietikäinen, M. (2018) · International Journal of Computer Vision · doi:10.1007/s11263-018-1125-z · Cited by 400
“Subsequently, texton theory fell into disfavor as a model of texture discrimination until the influential work by Leung and Malik [114] who revisited textons and gave an operational definition of a texton as a cluster center in filter response space.”
BackgroundMethodInfluentialGu, C., Lim, J. J., Arbeláez, P., & Malik, J. (2009) · 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.2009.5206727 · Cited by 366
Self-citationOn the Significance of Real-World Conditions for Material Classification
Hayman, E., Barbara Caputo, B., Fritz, M., & Eklundh, J. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-24673-2_21 · Cited by 349
“Filter banks are indeed very popular [21, 16, 9, 31, 24], and there is evidence that biological systems process visual stimuli using filters resembling those in Fig.”
BackgroundMethodInfluentialLemaître, G., Martí, R., Freixenet, J., Vilanova, J. C., WALKER, P. M., & Mériaudeau, F. (2015) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2015.02.009 · Cited by 363
Extended local binary patterns for texture classification
Liu, L., Zhao, L., Long, Y., Kuang, G., & Fieguth, P. (2012) · Image and Vision Computing · doi:10.1016/j.imavis.2012.01.001 · Cited by 343
“Recently, the orderless Bag-of-Words (BoW) [5, 2, 3, 8] approach, representing texture images statistically as histograms over a discrete texton dictionary, has proven extremely popular and successful in texture classi fi cation tasks.”
BackgroundMethodClassifying Images of Materials: Achieving Viewpoint and Illumination Independence
Varma, M., & Zisserman, A. (2002) · Lecture notes in computer science · doi:10.1007/3-540-47977-5_17 · Cited by 342
“In the previous section,the number of models was the same as the number of training images (and in effect [ 13 ] used 20 models/images for every texture).”
BackgroundMethodResultInfluentialAutomated annotation of coral reef survey images
Beijbom, O., Edmunds, P. J., Kline, D. I., Mitchell, B. G., & Kriegman, D. J. (2012) · 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.2012.6247798 · Cited by 347
“Varma and Zisserman [31] proposed a method where textures are modeled as histograms of textons [17], and introduce a rotational invariant filter bank, Maximum Response (MR).”
MethodLearning Aerial Image Segmentation From Online Maps
Kaiser, P., Wegner, J. D., Lucchi, A., Jaggi, M., Hofmann, T., & Konrad Schindler, B. (2017) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2017.2719738 · Cited by 351
“As local evidence, conventional classifiers are fed with raw pixel intensities, simple arithmetic combinations such as vegetation indices, and different statistics or filter responses that describe the local image texture [15]–[17].”
BackgroundDeep Filter Banks for Texture Recognition, Description, and Segmentation
Cimpoi, M., Maji, S., Kokkinos, I., & Vedaldi, A. (2016) · International Journal of Computer Vision · doi:10.1007/s11263-015-0872-3 · Cited by 349
Local Learning With Deep and Handcrafted Features for Facial Expression Recognition
Georgescu, M.-I., Ionescu, R. T., & Popescu, M. (2019) · IEEE Access · doi:10.1109/access.2019.2917266 · Cited by 351
“In the training pipeline, we build the feature representation by extracting dense SIFT descriptors [25], [26] from all training images, and by later quantizing the extracted descriptors into visual words using k-means clustering [34].”
MethodBilinear Convolutional Neural Networks for Fine-Grained Visual Recognition
Lin, T., RoyChowdhury, A., & Maji, S. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2723400 · Cited by 408
“Early work [37] represents the texture by computing the statistics of linear filter-bank responses (e.”
BackgroundSteel defect classification with Max-Pooling Convolutional Neural Networks
Masci, J., Meier, U., Ciresan, D., Schmidhuber, J., & Fricout, G. (2012) · The 2012 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2012.6252468 · Cited by 345
“However, in a broader context the problem can be viewed as defect detection in textured material which has received considerable attention in computer vision [7], [8], [9].”
BackgroundThe Pyramid Match Kernel: Efficient Learning with Sets of Features
Grauman, K. L., & Darrell, T. (2007) · doi:10.5555/1248659.1248685 · Cited by 326
Multifractal Texture Estimation for Detection and Segmentation of Brain Tumors
Islam, A., Reza, S. M. S., & Iftekharuddin, K. M. (2013) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2013.2271383 · Cited by 319
“In addition, we extract texton feature [15] for comparison in segmenting brain tumors.”
BackgroundMethodInfluentialI2T: Image Parsing to Text Description
Yao, B., Yang, X., Lin, L., Lee, M. W., & Zhu, S. C. (2010) · Proceedings of the IEEE · doi:10.1109/jproc.2010.2050411 · Cited by 314
“3 illustrates a rough but intuitive idea about two major tasks of the categorical representation: • Task1: Extract low-level visual features such as coherent regions (segmentation) [13]–[15], salient edges [16], [17], filter-bank responses (textons) [18], [19], SIFT descriptors [20], color histograms Fig.”
BackgroundViewpoint Invariant Texture Description Using Fractal Analysis
Xu, Y., Ji, H., & Fermuller, C. M. (2009) · International Journal of Computer Vision · doi:10.1007/s11263-009-0220-6 · Cited by 302
“A number of researchers have proposed to build representation by combining images from many views or illumination directions, which have been registered (Dana and Nayar 1998; Liu et al. 2001; Zalesny and Van Gool 2001; Neubeck et al. 2004; Leung and Malik 2001; Chantler et al. 2005).”
BackgroundContent based image retrieval using motif cooccurrence matrix
Jhanwar, N., Chaudhuri, S., Seetharaman, G. S., & Zavidovique, B. (2004) · Image and Vision Computing · doi:10.1016/j.imavis.2004.03.026 · Cited by 295
“The filter response of the filter bank was learnt from training images and represented by clusters [34,35] or histograms [36,37].”
MethodClass-specific material categorisation
Barbara Caputo, B., Hayman, E., & Mallikarjuna, P. (2005) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2005.54 · Cited by 293
“Certainly very impressive results up to 98% have been reported on the CUReT database [15, 8, 24, 25, 21, 12].”
BackgroundImage retrieval based on multi-texton histogram
Liu, G., Lei Zhang, A., Hou, Y., Li, Z., & Yang, J.-Y. (2010) · Pattern Recognition · doi:10.1016/j.patcog.2010.02.012 · Cited by 291
“This method is invariant to image translation, rotation and scaling because it uses the edges only but ignores correlation between neighboring edges.”
MethodTexture Classification from Random Features
Li, L., & Fieguth, P. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.145 · Cited by 290
“It has been shown that a texton-based approach is an effective local-global representation [18], [21].”
BackgroundDeep TEN: Texture Encoding Network
Zhang, H., Xue, J., & Dana, K. (2017) · 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.2017.309 · Cited by 295
“In classic computer vision approaches for material/texture recognition, hand-engineered features are extracted using interest point detectors such as SIFT [31] or filter bank responses [10,11,26,43].”
MethodRandomized Clustering Forests for Image Classification
Moosmann, F., Nowak, E., & Jurie, F. (2008) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.70822 · Cited by 296
“They allow for summarizing images with a very small amount of local information, so it is very common to find them at the first stage of image categorization algorithms [11], [15], [30], [32].”
BackgroundAnwer, R. M., Khan, F. S., van de Weijer, J., Molinier, M., & Laaksonen, J. T. (2018) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2018.01.023 · Cited by 291
A comprehensive review of current local features for computer vision
Li, J., & Allinson, N. M. (2008) · Neurocomputing · doi:10.1016/j.neucom.2007.11.032 · Cited by 282
“Existing descriptors can be categorized into the following five types: (i) filter-based descriptors [17,25,61], (ii) distribution-based descriptors [9,34,37,42,48], (iii) textons [40,81,82], (iv) derivative-based descriptors [23,36,63], and (v) others [12,79,80].”
BackgroundMethodInfluentialTILT: Transform Invariant Low-Rank Textures
Zhang, Z., Ganesh, A., Liang, X., & Ma, Y. (2012) · International Journal of Computer Vision · doi:10.1007/s11263-012-0515-x · Cited by 295
The effect of viewpoint on perceived visual roughness
Ho, Y.-X., Maloney, L. T., & Landy, M. S. (2007) · Journal of Vision · doi:10.1167/7.1.1 · Cited by 277
“Cula and Dana (2001) and Leung and Malik (2001) were among the first to use linear filters and a machine learning algorithm to train a system to classify a set of textures under a variety of different illumination and viewing conditions.”
BackgroundUsing filter banks in Convolutional Neural Networks for texture classification
Andrearczyk, V., & Whelan, P. F. (2016) · Pattern Recognition Letters · doi:10.1016/j.patrec.2016.08.016 · Cited by 285
“Although there is no generally accepted definition for texture in computer vision, it is established that a texture image or region obeys some statistical properties and exhibits repeated structures [9], [16].”
BackgroundAppearance-space texture synthesis
Lefèbvre, S., & Hoppe, H. (2006) · ACM Transactions on Graphics · doi:10.1145/1141911.1141921 · Cited by 282
SEMANTIC SEGMENTATION OF AERIAL IMAGES WITH AN ENSEMBLE OF CNNS
Marmanis, D., Wegner, J. D., Galliani, S., Konrad Schindler, B., Datcu, M. P., & Stilla, U. (2016) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-annals-iii-3-473-2016 · Cited by 313
“Typical choices of input features are raw pixel intensities, simple arithmetic combinations of the raw values such as vegetation indices, and different statistics or filter responses that describe the local image texture [Leung and Malik, 2001,Schmid, 2001,Shot-ton et al., 2009].”
BackgroundReal-Time Visual SLAM for Autonomous Underwater Hull Inspection Using Visual Saliency
Kim, A., & Eustice, R. M. (2013) · IEEE Transactions on Robotics · doi:10.1109/tro.2012.2235699 · Cited by 263
“Originally developed for text-based applications, the general BoW approach was first adapted and expanded to images in [47], [49], and [50], allowing for aggregate con-”
MethodDimitrov, A., & Golparvar-Fard, M. (2014) · Advanced Engineering Informatics · doi:10.1016/j.aei.2013.11.002 · Cited by 261
“The filter based approach of Leung and Malik [38] was implemented in its original 48-dimensional form (LM) as well as in its 18-dimensional rotationally invariant form (rLM).”
BackgroundMethodInfluentialNatural and unnatural oil slicks in the G ulf of M exico
MacDonald, I. R., Garcia‐Pineda, O., Beet, A., Asl, S. D., Feng, L., Graettinger, G., French-McCay, D., Holmes, J., Hu, C., Huffer, F., et al. (2015) · Journal of Geophysical Research Oceans · doi:10.1002/2015jc011062 · Cited by 246
“This semiautomated routine filters a gray scale image with a 25 3 25 pixel kernel, testing pixel-by-pixel for edge and shape detections based upon the Leung-Malik filter bank [Leung and Malik, 2001].”
MethodUnderstanding image representations by measuring their equivariance and equivalence
Lenc, K., & Vedaldi, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298701 · Cited by 366
Song, H., Liu, Z., Du, H., Sun, G., Meur, O. L., & Ren, T. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2711277 · Cited by 242
“features including the absolute responses and the histograms of 15 LM filters [54], HOG [55] histograms and LBP [56] histograms; geodesic distance (GD) [6].”
BackgroundExploring features in a Bayesian framework for material recognition
Liu, C., Sharan, L., Adelson, E. H., & Rosenholtz, R. E. (2010) · 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.2010.5540207 · Cited by 244
Which is the best way to organize/classify images by content?
Bosch, A., Muñoz, X., & Martí, R. (2006) · Image and Vision Computing · doi:10.1016/j.imavis.2006.07.015 · Cited by 243
“Fan et al. [20] used concept sensitive salient objects as the dominant image components to achieve automatic image annotation at a content level.”
BackgroundEvaluation of color descriptors for object and scene recognition
van de Sande, K. E. A., Gevers, T., & Snoek, C. G. M. (2008) · 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.2008.4587658 · Cited by 235
Synthesis of bidirectional texture functions on arbitrary surfaces
Tong, X., Zhang, J., Liu, L., et al. (2002) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/566570.566634 · Cited by 229
Texture segmentation by multiscale aggregation of filter responses and shape elements
Galun, Sharon, S., Basri, B., & Brandt, �. (2003) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2003.1238418 · Cited by 224
“(An interesting recent variant attempts to identify the “textons” by clustering the filter outputs [8].”
BackgroundDetecting Anatomical Landmarks for Fast Alzheimer’s Disease Diagnosis
Zhang, J., Gao, Y., Gao, Y., Munsell, B. C., & Shen, D. G. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2582386 · Cited by 225
“Instead of using N-ary coding [26] for vector quantization (VQ), we adopt a bag-of-words strategy [27] for VQ to obtain the final histogram features with relatively low feature dimensionality.”
MethodFrom co-saliency to co-segmentation: An efficient and fully unsupervised energy minimization model
Chang, K.-Y., Liu, T.-L., & Lai, S. (2011) · 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.2011.5995415 · Cited by 219
“Since such a histogram is simply composed of the frequencies of the visual words [18], how these words are derived should, in turn, be a key factor.”
BackgroundHan, K. K., & Golparvar-Fard, M. (2015) · Automation in Construction · doi:10.1016/j.autcon.2015.02.007 · Cited by 246
Learning Large-Scale Automatic Image Colorization
Deshpande, A., Rock, J., & Forsyth, D. A. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.72 · Cited by 215
“For this we use LM filter bank responses (scaled between 0 and 1), since they are good at discriminatively identifying the material and texture of swatches [11].”
MethodRigamonti, R., Sironi, A., Lepetit, V., & Fua, P. (2013) · 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.2013.355 · Cited by 220
“Separable filters are desirable because they can be computed very efficiently: Handcrafted filter banks are often made separable [7], and we aim here at the same efficiency with the advantages of learning approaches.”
BackgroundUnsupervised discovery of visual object class hierarchies
Šivic, J., Russell, B. C., Zisserman, A., Freeman, W. T., & Efros, A. A. (2008) · 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.2008.4587622 · Cited by 211
“Similar ‘dense’ representation has been successfully used in the context of supervised object [16] and scene [7, 17] category recognition and texture recognition [18, 30].”
BackgroundInverse shade trees for non-parametric material representation and editing
Lawrence, J., Ben-Artzi, A., DeCoro, C., Matusik, W., Pfister, H., Ramamoorthi, R., & Rusinkiewicz, S. M. (2006) · ACM Transactions on Graphics · doi:10.1145/1141911.1141949 · Cited by 215
Patch-VQ: ‘Patching Up’ the Video Quality Problem
Ying, Z., Mandal, M., Ghadiyaram, D., & Bovik, A. C. (2021) · 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/cvpr46437.2021.01380 · Cited by 206
“• Spatial Gaussian Derivative Filters (3 scales, 2 orientations) from Leung-Malik filter bank [60].”
BackgroundPerson Spotting: Video Shot Retrieval for Face Sets
Šivic, J., Everingham, M., & Zisserman, A. (2005) · Lecture notes in computer science · doi:10.1007/11526346_26 · Cited by 203
“A similar representation (over filter responses) has been used in representing texture [13] and recently has been also applied to face recognition [12].”
Are sparse representations really relevant for image classification?
Rigamonti, R., Brown, M. A., & Lepetit, V. (2011) · 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.2011.5995313 · Cited by 204
“For further investigation of the so lution stability, we performed an experiment where LeungMalik (LM) filters [20], depicted in Fig.”
MethodA comprehensive review of fruit and vegetable classification techniques
Hameed, K., Chai, D., & Rassau, A. (2018) · Image and Vision Computing · doi:10.1016/j.imavis.2018.09.016 · Cited by 210
Using Basic Image Features for Texture Classification
Crosier, M., & Griffin, L. D. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0315-0 · Cited by 194
“…low-dimensional and controls the number of bins in the representation by defining a partition of feature space through unsupervised clustering of feature vectors into textons (Hayman et al. 2004; Varma and Zisserman 2005, 2009; Leung and Malik 2001; Cula and Dana 2001; Varma and Garg 2007).”
BackgroundInfluentialMcIntosh, C., Welch, M. L., McNiven, A., Jaffray, D. A., & Purdie, T. G. (2017) · Physics in Medicine and Biology · doi:10.1088/1361-6560/aa71f8 · Cited by 194
“Features are calculated across a range of scales via convolution with a 3D texture filter bank that is an extension of the Leung–Malik filter bank (Leung and Malik 2001).”
MethodInfluential
Metadata
- Authors
- Leung, T., & Malik, J.
- Affiliations
- University of California, Berkeley (US)
- ORCID
- Malik, Jitendra
- Venue
- International Journal of Computer Vision
- Published
- 2001-06
- Volume
- 43
- Issue
- 1
- Pages
- 29-44
- ISSN
- 0920-5691 (ISSN-L)
- 1573-1405
- OpenAlex
- W1484228140
- Semantic Scholar
- 90d6e7f2202f754d8588f9536e3f5b4a24701f24
- Cited by
- 1,498
- References
- 45
- Citations by year
- 2026: 9 · 2025: 15 · 2024: 18 · 2023: 17 · 2022: 33 · 2021: 30 · 2020: 48 · 2019: 78 · 2018: 74 · 2017: 94 · 2016: 115 · 2015: 116 · 2014: 122 · 2013: 91 · 2012: 81
- FWCI
- 27.29
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- International Journal of Computer Vision (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image Retrieval and Classification Techniques
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Computer Graphics and Visualization Techniques
- Keywords
- material identification, natural textures, surface reflectance, surface normals, appearance modeling, Gaussian derivative filters, texture clustering, surface patches
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
