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
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
Items 601–700 of 1,001
Self-Supervised Learning to Guide Scientifically Relevant Categorization of Martian Terrain Images
Panambur, T., Chakraborty, D., Meyer, M. J., Milliken, R., Learned-Miller, E. G., & Parente, M. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00138 · Cited by 19
“It is usually cast as a texture recognition problem, and traditional approaches used geometric features, particularly curvature, color features, lighting, illumination direction, and photometric properties [5,15,29,61], followed by feature pooling as seen in bag-ofwords models [11,28].”
MethodEvaluation of Yogurt Microstructure Using Confocal Laser Scanning Microscopy and Image Analysis
Skytte, J. L., Ghita, O., Whelan, P. F., Andersen, U., Møller, F. V., Dahl, A. B., & Larsen, R. (2015) · Journal of Food Science · doi:10.1111/1750-3841.12885 · Cited by 18
“Multiple studies in material classification (Leung and Malik 2001; Hayman and others 2004; Varma and Zisserman 2005; Caputo and others 2005) suggest that such image textures are best described using statistical distributions of the so-called textons, which can be considered prototypical image…”
BackgroundMethodInfluentialSpatial and temporal pyramids for grammatical expression recognition of American sign language
Michael, N., Metaxas, D., & Neidle, C. (2009) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/1639642.1639657 · Cited by 18
“The codebook approach, inspired by the word-document representation used in text retrieval, was first applied to im ages in the work of Leung and Malik [11].”
MethodInfluentialFace and Hair Region Labeling Using Semi-Supervised Spectral Clustering-Based Multiple Segmentations
Ahn, I., & Kim, C. (2016) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2016.2551698 · Cited by 18
“For computing texture features, we use the Leung–Malik (LM) filter [25].”
MethodBardinas, J. P., Aldrich, C., & Napier, L. F. A. (2018) · Processes · doi:10.3390/pr6020017 · Cited by 17
“In general, textons are learned in a series of steps in a training stage that includes image filtering, filter response aggregation, and texton definition as cluster centers in the filter response space [16].”
BackgroundComparison of Five 3D Surface Texture Synthesis Methods
Dong, J., & Chantler, M. J. (2003) · Cited by 18
Feature-Based Pothole Detection in Two-Dimensional Images
Ryu, S.-K., Kim, T.-H., & Kim, Y.-R. (2015) · Transportation Research Record Journal of the Transportation Research Board · doi:10.3141/2528-02 · Cited by 18
Towards Unsupervised Discovery of Visual Categories
Fritz, M., & Schiele, B. (2006) · Lecture notes in computer science · doi:10.1007/11861898_24 · Cited by 18
“We use a generic codebook representation which is also the basis of the object scale estimation procedure as presented in Section 3. Generic Codebook Representation Similar to other approaches for recognition [1], material classification [ 10 ] and detection [4], we use an initial clustering procedure to obtain a visu…”
MethodFast texture synthesis on arbitrary meshes
Magda, S., & Kriegman, D. J. (2003) · ACM SIGGRAPH Conference (SIGGRAPH) · doi:10.1145/965400.965510 · Cited by 18
André, B., Vercauteren, T. K., Buchner, A. M., et al. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15745-5_59 · Cited by 17
“…HH-SIFT method presented by Zhang et al. [10] a sparse detector, the standard approach of Haralick features, the texture retrieval Textons method of Leung and Malik [12], and an efficient image classification method presented by Boiman et al. [13], referred as “BruteForce”, that uses no clustering.”
MethodLi, C., Li, J., Gao, D., et al. (2013) · Pattern Recognition · doi:10.1016/j.patcog.2013.05.003 · Cited by 17
“Textons representation methods such as ML-Textons [17] and MR8-Textons [18] can also withstand the changes of rotation and scale, but this method is”
MethodModeling Image Patches with a Generic Dictionary of Mini-epitomes
Papandreou, G., Chen, L.-C., & Yuille, A. (2014) · 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.2014.264 · Cited by 17
“The idea to use a patch-based representation for image classification first appeared in [23] and was further developed by [26], who applied it to homogeneous texture classification and compared it to the filterbank-based texton representation of [18].”
Optimizing Gabor Filter Design for Texture Edge Detection and Classification
Sandler, R., & Lindenbaum, M. (2009) · International Journal of Computer Vision · doi:10.1007/s11263-009-0237-x · Cited by 17
“Yet it is interesting to examine them in the context of the effective and popular texton-based methods ( Leung and Malik 2001; Varma and Zisserman 2002).”
BackgroundEfficient Kernel Sparse Coding Via First-Order Smooth Optimization
Kim, M. (2014) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2013.2294059 · Cited by 17
“They are visually quite similar, and exhibit that the learned bases effectively discover the most salient filter banks for natural images, especially dots and bars of different orientations conforming to those of [20].”
Colour-based texture image classification using the complex wavelet transform
Barilla-Perez, M. E., & Spann, M. (2008) · International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE) · doi:10.1109/iceee.2008.4723449 · Cited by 17
“LM Convolution with Leung and Malik’s filter-bank [15].”
MethodUnsupervised Learning of Categorical Segments in Image Collections
Andreetto, M., Zelnik‐Manor, L., & Perona, P. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2011.268 · Cited by 17
“Using 'bags of visual words' to characterize the appearance of an image, or an image patch, combines an idea coming from the literature on texture, where Leung and Malik [13] proposed vector-quantizing image patches to produce a small dictionary of 'textons', and an idea from the literature on document retrieval, wher…”
Depth-aware saliency detection using discriminative saliency fusion
Song, H., Liu, Z., Du, H., & Sun, G. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7471952 · Cited by 17
“The details of these features are as follows (along with the number of features in the parenthesis): Average color of each channel and histograms in the RGB, HSV and L*a*b* color spaces (12); average depth value and histogram (2); texture features including absolute responses (15 2 ) and their histograms (1 2 ) of 1…”
BackgroundFeature Quality Based Dynamic Feature Selection for Improving Salient Object Detection
Naqvi, S. R., Browne, W. N., & Hollitt, C. (2016) · IEEE Transactions on Image Processing · doi:10.1109/tip.2016.2587359 · Cited by 17
“The backgroundness descriptor of [19] uses 29 features including average values of color, histograms of color, hue, saturation, texton and response of Leung-Malik (LM) filter bank [33] (for further details please refer to [19]), computed region-wise.”
MethodGeodesic Distance Histogram Feature for Video Segmentation
Le, H., Nguyen, V., Yu, C.-P., et al. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-54181-5_18 · Cited by 17
“Appearance can be represented by features based on color [5, 15], texture [16], and soft boundaries [17].”
BackgroundDominant Sets for 'Constrained' Image Segmentation
Zemene, E., Alemu, L. T., & Pelillo, M. (2019) · ARCA (Università Ca' Foscari Venezia) · doi:10.1109/tpami.2018.2858243 · Cited by 17
“The number of dimensions of feature vectors for each oversegment is then 57 (three for each of the RGB, L*a*b*, and HSV color spaces, and 48 for LM Filter Bank).”
MethodReal-time texture detection using the LU-transform
Targhi, A. T., Björkman, M., Hayman, E., et al. (2006) · Cited by 17
Local Binary Pattern histogram based Texton learning for texture classification
He, Y., Sang, N., & Huang, R. (2011) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2011.6116688 · Cited by 17
“Leung and Malik[4] obtained good texture classification results by building 3D textons from filter responses over a stack of texture images under different viewpoints and illuminations.”
BackgroundUnsupervised detection and localization of structural textures using projection profiles
Yalnız, İ. Z., & Aksoy, S. (2010) · Pattern Recognition · doi:10.1016/j.patcog.2010.04.016 · Cited by 17
“For example, Leung and Malik [27] used the eigenvalues of the second moment matrix to identify distinctive scene elements with a large intensity variation, used the sum of squared differences criterion for matching neighboring patches after estimating an affine transform for the match, and propagated the growing proce…”
BackgroundMethodInfluentialMontazer, G. A., Soltanshahi, M. A., & Giveki, D. (2017) · Optical Memory and Neural Networks · doi:10.3103/s1060992x17020060 · Cited by 16
“The BoVW methodology (sometimes also called bag-of-features) was first proposed for text document analysis and further adapted for computer vision applications [27, 28].”
MethodAmano, K., Lou, E., & Edwards, R. (2019) · Journal of Facilities Management · doi:10.1108/jfm-11-2017-0064 · Cited by 15
Multiple disjoint dictionaries for representation of histopathology images
Zhu, S., Li, Y., Kalra, S., et al. (2018) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2018.06.001 · Cited by 17
Ma, F., Gao, F., Wang, J., et al. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.12.009 · Cited by 17
Perceptual Texture Similarity Estimation: An Evaluation of Computational Features
Dong, X., Dong, J., & Chantler, M. J. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2020.2964533 · Cited by 17
“Others include the trace transform [64], co-occurrence matrices [57] and texton-based approaches [72], [122].”
BackgroundMethodInfluentialScale-Space Analysis of Discrete Filtering over Arbitrary Triangulated Surfaces
Wu, C., Deng, J., Chen, F., & Tai, X. (2009) · SIAM Journal on Imaging Sciences · doi:10.1137/080722758 · Cited by 17
“Scale-space representations of images are useful for compression, transmission, segmentation, feature detection, and classification, as well as image matching [21, 28, 29, 36, 38, 44, 45, 52].”
BackgroundMa, X., & Grimson, W. E. L. (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.2008.4587593 · Cited by 17
An efficient representation of complex materials for real-time rendering
Ma, W., Chao, S.-H., Chen, B., et al. (2004) · ACM Symposium on Virtual Reality Software and Technology (VRST) · doi:10.1145/1077534.1077563 · Cited by 17
Channel-Coded Feature Maps for Computer Vision and Machine Learning
Jonsson, E. (2008) · DiVA (Linkoping University) · Cited by 17
Material Classification on Symmetric Positive Definite Manifolds
Faraki, M., Harandi, M. T., & Porikli, F. (2015) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv.2015.105 · Cited by 16
“Two notable examples are Leung and Malik (LM) and Maximum Response filter banks [36, 19].”
BackgroundAttribute Based Affordance Detection from Human-Object Interaction Images
Hassan, M., & Dharmaratne, A. T. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-30285-0_18 · Cited by 16
Material recognition by feature classification using time-of-flight camera
Martino, F., Patruno, C., Mosca, N., & Stella, E. (2016) · Journal of Electronic Imaging · doi:10.1117/1.jei.25.6.061412 · Cited by 16
Online learning for characterizing unknown environments in ground robotic vehicle models
Koppel, A., Fink, J., Warnell, G., et al. (2016) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2016.7759118 · Cited by 16
E-Counterfeit: A Mobile-Server Platform for Document Counterfeit Detection
Berenguel, A., Terrades, O. R., Lladós, J., et al. (2017) · IAPR International Conference on Document Analysis and Recognition (ICDAR) · doi:10.1109/icdar.2017.390 · Cited by 16
“The best-known orderless encoder is the Bag of Visual Words (BoVW), which characterizes the distribution of textons [15].”
MethodReflectance-based surface saliency
Pitard, G., Goïc, G. L., Mansouri, A., et al. (2017) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2017.8296320 · Cited by 16
“Although many reflectance measurements and models are reported in the literature [6], most of them rely on the assessment of either microgeometry or surface roughness to identify undesired local variations for which the light interaction induces changes in human perception [7, 8, 9].”
BackgroundShape based local affine invariant texture characteristics for fabric image retrieval
Li, Y., Zhang, J., Chen, M., Lei, H., Luo, G., & Huang, Y. (2018) · Multimedia Tools and Applications · doi:10.1007/s11042-018-6936-y · Cited by 16
“The third popular methods to texture analysis is filter based ones, which represent a texture via its response to a family of filters [23, 26], i.”
MethodZhong, L., Yang, L., Rong, J., et al. (2020) · IEEE Access · doi:10.1109/access.2020.2990949 · Cited by 16
“A bag of visual words features is generated as follows [57].”
BackgroundRetrieval Evaluation and Distance Learning from Perceived Similarity between Endomicroscopy Videos
André, B., Vercauteren, T. K., Buchner, A. M., et al. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23626-6_37 · Cited by 16
“Whereas “HH-Sift” combines the sparse “Harris-Hessian” detector with the SIFT descriptor, the competitive “Textons” method proposed by Leung and Malik [3] is based on a dense description of local texture features.”
MethodBag of frequent subgraphs approach for image classification
Mejdoub, M., Aoun, N. B., & Amar, C. B. (2015) · Intelligent Data Analysis · doi:10.3233/ida-140697 · Cited by 16
The Eigen-Transform and Applications
Targhi, A. T., Hayman, E., Eklundh, J., et al. (2006) · Lecture notes in computer science · doi:10.1007/11612032_8 · Cited by 16
“Texture analysis has applications in several areas within computer vision such as image segmentation[15, 7], the classification of objects [19] or materials [9, 17, 10].”
Classification of Cervix Lesions Using Filter Bank-Based Texture Mode
Yeshwanth Srinivasan, A., Nutter, B. S., Mitra, S., et al. (2006) · Proceedings - IEEE Symposium on Computer-Based Medical Systems · doi:10.1109/cbms.2006.66 · Cited by 16
“Texture classification using filter banks has been widely applied to classification of images from standard texture databases with greater than 95% accuracy [8, 9, 10].”
BackgroundMethodDetecting, Localizing and Recovering Kinematics of Textured Animals
Ramanan, D., Forsyth, D. A., & Barnard, K. (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.2005.126 · Cited by 16
“Standard approaches use histograms of textons (quantized filter bank outputs) [9, 10, 16, 18].”
MethodTexton-based segmentation of retinal vessels
Adjeroh, D., Kandaswamy, U., & Odom, J. V. (2007) · Journal of the Optical Society of America A · doi:10.1364/josaa.24.001384 · Cited by 16
Kernels on Sample Sets via Nonparametric Divergence EstimatesPreprint
Sutherland, D. J., Xiong, L., Póczos, B., & Schneider, J. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1202.0302 · Cited by 16
“Perhaps the most common method for using these sets of features is to quantize the local descriptors and represent images as histograms of those features [19], the “bag of words” (BOW) method.”
MethodPQ kernel: A rank correlation kernel for visual word histograms
Ionescu, R. T., & Popescu, M. (2014) · Pattern Recognition Letters · doi:10.1016/j.patrec.2014.06.003 · Cited by 15
Multi-fold Gabor filter convolution descriptor for face recognition
Low, C.-Y., Teoh, A. B. J., & Ng, C.-J. (2016) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2016.7472046 · Cited by 15
“Other well-known filters in texture classification include Leung Malik [2], Schmid [3], MR8 [4], etc. Inspired by the PCANet performance and the Gabor filters that model the receptive field profiles of mammalian cortical simple cells [16-17], this paper outlines a new means of simple filter diversification by self-cro…”
BackgroundMethodComputer aided diagnosis of prostate cancer: A texton based approach
Rampun, A., Tiddeman, B., Reyer Zwiggelaar, A., & Malcolm, P. (2016) · Medical Physics · doi:10.1118/1.4962031 · Cited by 15
Sisodia, D. S., Bhandari, S., Reddy, N. K., et al. (2019) · Asset analytics · doi:10.1007/978-981-13-8253-6_10 · Cited by 15
Fractal dimension of maximum response filters applied to texture analysis
Ribas, L. C., Gonçalves, D. N., Oruê, J. P. M., & Gonçalves, W. N. (2015) · Pattern Recognition Letters · doi:10.1016/j.patrec.2015.07.030 · Cited by 15
“Recently, filter banks composed by filters with different characteristics have been proposed, such as the Leung-Malik filter bank [27] which consists of 48 filters (second derivatives of Gaussians, Laplacian of Gaussian and Gaussians) and the Schmid filter bank [28] which consists of 13 rotationally invariant Gabor-li…”
MethodAn Active Patch Model for Real World Texture and Appearance Classification
Mao, J., Zhu, J., & Yuille, A. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-10578-9_10 · Cited by 15
“Traditional filter-bank-based approaches [8,16,39] have been dominant in texture analysis literature in early years.”
BackgroundMethodObject recognition with hierarchical discriminant saliency networks
Han, S., & Vasconcelos, N. M. (2014) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2014.00109 · Cited by 16
Finger Vein Verification with Vein Textons
Dong, L., Yang, G., Yin, Y., et al. (2015) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001415560030 · Cited by 15
Enhanced Reweighted MRFs for Efficient Fashion Image Parsing
Wu, Q., & Boulanger, P. (2016) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/2890104 · Cited by 15
“…tackle the problem from various aspects: elementary regions (e.g., global, regional, and local), features to describe regions such as textons [Leung and Malik 2001], features learned from largescale deep convolutional neural networks [Zheng et al. 2015]), spatial relationship cues such as…”
BackgroundClassification of calcium in intravascular OCT images for the purpose of intervention planning
Shalev, R., Bezerra, H. G., Ray, S., Prabhu, D. S., & Wilson, D. L. (2016) · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · doi:10.1117/12.2216315 · Cited by 15
Video-Based Highway Asset Recognition and 3D Localization
Balali, V., Golparvar‐Fard, M., & de la Garza, J. M. (2013) · ASCE International Conference on Computing in Civil Engineering (i3CE) · doi:10.1061/9780784413029.048 · Cited by 15
“In this step, first using (Leung and Malik 2001) comprehensive radial and linear filter bank, a set of training candidate frames are convolved and the outcomes are clustered using K-means clustering approach.”
MethodSemantically Guided Geo-location and Modeling in Urban Environments
Singh, G., & Košecká, J. (2016) · Advances in computer vision and pattern recognition · doi:10.1007/978-3-319-25781-5_6 · Cited by 15
Texture Characterization Using Shape Co-Occurrence Patterns
Xia, G.-S., Liu, G., Bai, X., & Zhang, L. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2726182 · Cited by 14
“As mentioned previously, an implicit way to implement the texton theory is to use tools for wavelet-like analysis, such as Gabor filter banks, to probe atomic texture elements in texture images and then utilize the resulting filter responses to describe the underlying statistical texture features [2], [3], [9].”
MethodArtificial Intelligence and Robotics
(2020) · Studies in computational intelligence · doi:10.1007/978-3-030-56178-9 · Cited by 15
Hybrid Cross Deep Network for Domain Adaptation and Energy Saving in Visual Internet of Things
Zhang, Z., & Li, D. (2018) · IEEE Internet of Things Journal · doi:10.1109/jiot.2018.2867083 · Cited by 15
“Second, the proposed HCDN is compared with six state-of-the-art methods, including local binary pattern (LBP) [35], bag-of-words model (BoW) [36], completed LBP (CLBP) [37], Long et al.”
MethodAutomatic Localization of Skin Layers in Reflectance Confocal Microscopy
Somoza, E. A., Cula, G. O., Correa, C. M., & Hirsch, J. B. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-11755-3_16 · Cited by 15
Compressed Sensing for Robust Texture Classification
Liu, L., Fieguth, P., & Kuang, G. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-19315-6_30 · Cited by 15
“We choose a texton-based approach, an effective local-global representation [1][2][3][4], trained by adaptively partitioning the feature space into clusters using K -means.”
BackgroundMethodExample‐based Interpolation and Synthesis of Bidirectional Texture Functions
Ruiters, R., Schwartz, C., & Klein, R. (2013) · Computer Graphics Forum · doi:10.1111/cgf.12056 · Cited by 15
Lu, Y., Zhang, H., Kang, T., Choi, I.-H., & Lim, M. (2014) · Neurocomputing · doi:10.1016/j.neucom.2014.02.046 · Cited by 15
“Even though bag-ofwords (BoW) [9] and bag-of-features [10] are effective for resolving this issue, the amount of structure information still falls short.”
BackgroundA novel hybrid approach for automated detection of retinal detachment using ultrasound images
Koh, J. E. W., Raghavendra, U., Gudigar, A., Ooi, C. P., Molinari, F., Mishra, S., Mathavan, S., Raman, R., & Acharya, U. R. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.103704 · Cited by 15
Cula, O. G., Dana, K., Murphy, F., & Rao, B. K. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000046591.79973.6f · Cited by 15
“In the 3D texton method (Leung and Malik, 1999) (Leung and Malik, 2001), a 3D texton is created by using a multiscale filter bank applied to an image set for a particular sample.”
BackgroundMethodInfluentialThe Bottleneck Geodesic: Computing Pixel Affinity
Omer, I., & Werman, M. (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.2006.302 · Cited by 15
“The texture features used are the Leung-Malik filter bank [9] (a total of 48 filters).”
MethodDeep Multi-Resolution Dictionary Learning for Histopathology Image AnalysisPreprint
Hatami, N., Bilal, M., & Rajpoot, N. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.00669 · Cited by 15
“Before the ‘deep learning era’, models such as the histograms of filter bank responses [16], [17], Bag-of-visual-Words (BoW) [18] and Fisher vector [19] have been successfully applied to texture recognition.”
Deep Active Learning for Automatic Mitotic Cell Detection on HEp-2 Specimen Medical Images
Anaam, A., Al–antari, M. A., Hussain, J., Samee, N. M. A., Alabdulhafith, M. I., & Gofuku, A. (2023) · Diagnostics · doi:10.3390/diagnostics13081416 · Cited by 15
“(2020) [37] CNN-based feature (using AlexNet [76]) + BoW [77] + LM filter bank [79] + DCGAN [60] augmentation SVM 0.”
Drbohlav, O., & Leonardis, A. (2009) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2009.08.006 · Cited by 14
Spatiotemporal Sparsity Induced Similarity Measure for Human Action Recognition
Liu, A.-A., & Han, D. Y. (2010) · International Journal of Digital Content Technology and its Applications · doi:10.4156/jdcta.vol4.issue8.16 · Cited by 14
“We performed K-means algorithm [16] over all the vectors.”
MethodTexture Analysis by Accurate Identification of a Generic Markov–Gibbs Model
Gimel’farb, G., & Zhou, D. (2008) · Studies in computational intelligence · doi:10.1007/978-3-540-76831-9_9 · Cited by 14
Combining Feature Context and Spatial Context for Image Pattern Discovery
Wang, H., Yuan, J., & Tan, Y. (2011) · Proceedings · doi:10.1109/icdm.2011.38 · Cited by 14
“1) Texture Image: We test the proposed method on texture image modelling [19], [20], [21].”
MethodTexture classification of MR images of the brain in ALS using M-CoHOG: A multi-center study
Elahi, G. M. M. E., Kalra, S., Zinman, L. H., et al. (2019) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2019.101659 · Cited by 14
Chiu, M., Lee, Y.-H., & Chen, T.-M. (2022) · Journal of Industrial and Production Engineering · doi:10.1080/21681015.2022.2074155 · Cited by 14
“[31], and [32], used different patterns that appeared in different areas of a picture as the basis for determining differences.”
BackgroundWang, M., Wang, E., Liu, X., Wang, Z., & Wang, C. (2022) · Rock Mechanics and Rock Engineering · doi:10.1007/s00603-022-02907-7 · Cited by 14
“…1962, 1981), geometric features of rock image information (color space combination relations, shape edges, etc.) (Gotlieb and Krey-szig 1990; Leung and Malik 2001; Tuceryan and Jain 1998; Varma and Zisserman 2005), and microstructure and mineral composition characteristics of rock slices…”
BackgroundKennel, P., Tramon, M., Barbier, N., et al. (2013) · International Journal of Remote Sensing · doi:10.1080/01431161.2013.858846 · Cited by 14
“Textons have received much attention in computer vision (Leung and Malik 2001; Varma and Zisserman 2005; van der Maaten and Postma 2007).”
BackgroundMethodOn the relevance of sparsity for image classification
Rigamonti, R., Lepetit, V., González, G., Türetken, E., Benmansour, F., Brown, M., & Fua, P. (2014) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2014.03.009 · Cited by 14
“• The Leung-Malik (LM ) filter bank [65].”
Han, K. K., & Golparvar‐Fard, M. (2014) · International Conference on Computing in Civil and Building Engineering (ICCCBE) · doi:10.1061/9780784413616.046 · Cited by 15
“Utilizing Leung and Malik (2001) filter bank with 48 filters (8 derivative filters, 4 low-pass Gaussian filters, and 36 oriented filters at 6 orientations, 3 scales, and 2filters), they model the material appearance by a joint probability distribution of responses from a filter bank and principal…”
MethodModeling Bidirectional Texture Functions with Multivariate Spherical Radial Basis Functions
Tsai, Y.-T., Fang, K.-L., Lin, W.-C., et al. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.211 · Cited by 14
Automatic Annotation of Scientific Video Material based on Visual Concept Detection
Hentschel, C., Blümel, I., & Sack, H. (2013) · International Conference on Knowledge Management and Knowledge Technologies · doi:10.1145/2494188.2494213 · Cited by 14
“Content-based classification of image data has been subject of research for many years and Bag-of-Visual-Words (BoW) image representations have emerged as a successful state of the art when aiming at re-usable visual descriptors capable to represent a wide (potentially unlimited) range of visual concepts ([2, 7, 13]).”
BackgroundNavlakha, S., Ahammad, P., & Myers, E. W. (2013) · BMC Bioinformatics · doi:10.1186/1471-2105-14-294 · Cited by 14
“Texture is an important cue used by humans when manually segmenting and annotating EM images [23], and its use has become popular in many computer vision tasks today [24].”
BackgroundEstimating surface characteristics using physical reflectance models
Ragheb, H., & Hancock, E. R. (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.2003.1211468 · Cited by 14
“Instead, attempts are being made to understand the formation of texture in terms of surface relief distributions [2, 3].”
BackgroundMaterial Recognition in the Wild with the Materials in Context DatabasePreprint
Bell, S., Upchurch, P., Snavely, N., & Bala, K. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.0623 · Cited by 14
“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.”
BackgroundFusing subcategory probabilities for texture classification
Song, Y., Cai, W., Li, Q., Zhang, F., Feng, D. D., & Huang, H. (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.2015.7299070 · Cited by 13
“Some of the main challenges include the wide variety of natural texture patterns and large intra-class variation caused by illumination and geometric changes, and relatively low inter-class distinction [26, 41].”
BackgroundMelendez, J., Puig, D., & García, M. Á. (2010) · Pattern Recognition · doi:10.1016/j.patcog.2010.06.014 · Cited by 13
Context-aware single image super-resolution using locality-constrained group sparse representation
Tsai, C.-Y., Huang, D.-A., Yang, M.-C., Kang, L., & Wang, Y.-C. F. (2012) · Visual Communications and Image Processing · doi:10.1109/vcip.2012.6410851 · Cited by 13
“When using AP, we apply the chi-square (χ(2))-distance [15] to measure the difference between two image segments S and S in terms of their 360-dimensional textual features hn and h j n,”
MethodGhita, O., Ilea, D. E., Fernández, A., & Whelan, P. F. (2012) · Sensor Review · doi:10.1108/02602281211209446 · Cited by 13
“Classification Results for the LM and MR8 Filter Banks While the texture analysis techniques based on filtering the input images with Leung and Malik (LM) (Leung and Malik, 2001) and Maximum Response (MR8) filter banks (Varma and Zisserman, 2004) are standard signal processing approaches that sample the texture charac…”
MethodInfluentialAdvanced textural representation of materials appearance
Haindl, M., & Filip, J. (2011) · SIGGRAPH Asia Courses · doi:10.1145/2077434.2077435 · Cited by 13
Texture Classification Using Three Circular Filters
Kondra, S., & Torre, V. (2008) · Indian Conference on Computer Vision, Graphics and Image Processing · doi:10.1109/icvgip.2008.24 · Cited by 13
“Previous approaches mainly used statistical representations of the responses of bank of filters [1, 2, 7, 8, 9, 13].”
MethodBag of Features Model Using the New Approaches: A Comprehensive Study
Chougrad, H., Zouaki, H., & Alheyane, O. (2016) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2016.070132 · Cited by 14
“The feature extraction phase is done in two steps, first we sample the patches using either interest points [1, 5, 9, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20] or densely with a regular grid [21, 22, 23, 24].”
MethodDense Descriptors for Optical Flow Estimation: A Comparative Study
Baghaie, A., D'Souza, R., & Yu, Z.-Y. (2017) · Journal of Imaging · doi:10.3390/jimaging3010012 · Cited by 13
“The original set consists of 48 filters [37]; the first and second derivatives of the Gaussian at six orientations and three scales, which makes a total of 36 filters.”
BackgroundMethodSaliency Pattern Detection by Ranking Structured Trees
Zhu, L., Ling, H., Wu, J., et al. (2017) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.583 · Cited by 13
“Specifically, the contrastbased features are: 1) all features except the center coordinates, the hue and saturation histograms that are used for measuring inner-region attributes, 2) histogram-based features in the aforementioned four color spaces, 3) texture features, including the LM filter [27], Gabor filter and LB…”
MethodTCvBsISM: Texture Classification via B-Splines-Based Image Statistical Modeling
Liu, J., He, J., Zhang, W., et al. (2018) · IEEE Access · doi:10.1109/access.2018.2864754 · Cited by 13
Graph-Based Semantic Segmentation
Balaska, V. E., Bampis, L., & Gasteratos, A. C. (2018) · Mechanisms and machine science · doi:10.1007/978-3-030-00232-9_60 · Cited by 13
3D surface texture analysis of high‐resolution normal fields for facial skin condition assessment
Seck, A., Dee, H., Smith, W. A. P., & Tiddeman, B. (2019) · Skin Research and Technology · doi:10.1111/srt.12793 · Cited by 12
D4L: Decentralized dynamic discriminative dictionary learning
Koppel, A., Warnell, G., Stump, E., & Ribeiro, A. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7353786 · Cited by 13
“Inspired by the two-dimensional texton features discussed in [37], we generate texture features to classify, z, as the sum of the sparse dictionary representations of subpatches.”
MethodSong, J., Xiao, L., Molaei, M., & Lian, Z. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3112057 · Cited by 14
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
