A Statistical Approach to Texture Classification from Single Images
International Journal of Computer VisionPublished 2 November 2004
Manik Varma, Andrew Zisserman
Citations124
SJR quartileQ1
SJR score3.14
SNIP5.15
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A method of reliably measuring relative orientation co-occurrence statistics in a rotationally invariant manner is presented, and whether incorporating such information can enhance the classifier’s performance is discussed.
Abstract
We investigate texture classification from single images obtained under unknown viewpoint and illumination. A statistical approach is developed where textures are modelled by the joint probability distribution of filter responses. This distribution is represented by the frequency histogram of filter response cluster centres (textons). Recognition proceeds from single, uncalibrated images and the novelty here is that rotationally invariant filters are used and the filter response space is low dimensional. Classification performance is compared with the filter banks and methods of Leung and Malik [IJCV, 2001], Schmid [CVPR, 2001] and Cula and Dana [IJCV, 2004] and it is demonstrated that superior performance is achieved here. Classification results are presented for all 61 materials in the Columbia-Utrecht texture database. We also discuss the effects of various parameters on our classification algorithm--such as the choice of filter bank and rotational invariance, the size of the texton dictionary as well as the number of training images used. Finally, we present a method of reliably measuring relative orientation co-occurrence statistics in a rotationally invariant manner, and discuss whether incorporating such information can enhance the classifier's performance.
Keywords
Computer ScienceEngineering
Cambridge University Press eBooksAn Introduction to Support Vector Machines and Other Kernel-based Learning Methods
13,883 Citations2000Nello Cristianini, John Shawe‐Taylor
The MIT Press eBooksLearning with Kernels
9,548 Citations2001Bernhard Schölkopf, Alexander J. Smola
Learning with Kernels provides an introduction to SVMs and related kernel methods that provide all of the concepts necessary to enable a reader equipped with some basic mathematical knowledge to enter the world of machine learning using theoretically well-founded yet easy-to-use kernel algorithms.
Applied Physics Letters10.1162/15324430152748236
1,869 Citations2000
It is demonstrated that by exploiting a probabilistic Bayesian learning framework, the 'relevance vector machine' (RVM) can derive accurate prediction models which typically utilise dramatically fewer basis functions than a comparable SVM while offering a number of additional advantages.
International Journal of Computer VisionRepresenting and Recognizing the Visual Appearance of Materials using Three-dimensional Textons
1,494 Citations2001Thomas Leung, Jitendra Malik
A unified model to construct a vocabulary of prototype tiny surface patches with associated local geometric and photometric properties, represented as a set of linear Gaussian derivative filter outputs, under different lighting and viewing conditions is provided.
ACM Transactions on GraphicsReflectance and texture of real-world surfaces
1,326 Citations1999Kristin Dana, Bram van Ginneken +2 more
A new texture representation called the BTF (bidirectional texture function) which captures the variation in texture with illumination and viewing direction is discussed, and a BTF database with image textures from over 60 different samples, each observed with over 200 different combinations of viewing and illumination directions is presented.
International Journal of Computer VisionContour and Texture Analysis for Image Segmentation
1,091 Citations2001Jitendra Malik, Serge Belongie +2 more
This paper provides an algorithm for partitioning grayscale images into disjoint regions of coherent brightness and texture, and introduces a gating operator based on the texturedness of the neighborhood at a pixel to facilitate cue combination.
IEEE Transactions on Information TheoryThe reduced nearest neighbor rule (Corresp.)
560 Citations1972Geoffrey W. Gates
A further modification to Cover and Hart's nearest neighbor decision rule, the reduced nearest neighbor rule, is introduced and experimental results demonstrate its accuracy and efficiency.
Constructing models for content-based image retrieval
363 Citations2005C. Schmid
A new method for constructing models from a set of positive and negative sample images; the method requires no manual extraction of significant objects or features and allows to efficiently capture "texture-like" visual structure.
Lecture notes in computer scienceClassifying Images of Materials: Achieving Viewpoint and Illumination Independence
340 Citations2002Manik Varma, Andrew Zisserman
This paper presents a novel method of classifying a single image without requiring any a priori knowledge about the viewing or illumination conditions under which it was photographed, and argues that using rotationally invariant filters while clustering in such a low dimensional space improves classification performance.
Lecture notes in computer scienceOn the Significance of Real-World Conditions for Material Classification
339 Citations2004E. Hayman, Barbara Caputo +2 more
A first contribution of this paper is to further advance the state-of-the-art by applying Support Vector Machines to this problem and record the best results to date on the CUReT database.
IEEE Transactions on Pattern Analysis and Machine IntelligenceSupport vector machines for texture classification
338 Citations2002Kwang In Kim, Keechul Jung +2 more
Experimental results demonstrate the effectiveness of SVMs in texture classification, and it is shown that SVMs can incorporate conventional texture feature extraction methods within their own architecture, while also providing solutions to problems inherent in these methods.
Lecture notes in computer scienceIs machine colour constancy good enough?
253 Citations1998Brian Funt, Kobus Barnard +1 more
The goal was to show how well the various methods would do on an obvious machine colour vision task, namely, object recognition, and results showed the correlation between colour constancy performance and object recognition performance, and as one might expect, the better the colour constancies the best the recognition rate.
Viewpoint invariant texture matching and wide baseline stereo
192 Citations2002F. Schaffalitzky, Andrew Zisserman
A texture region descriptor is described and demonstrated which is invariant to affine geometric and photometric transformations, and insensitive to the shape of the texture region, resulting in richer and more stable descriptors than those computed at a point.
International Journal of Computer Vision3D Texture Recognition Using Bidirectional Feature Histograms
166 Citations2004Oana G. Cula, Kristin Dana
A 3D texture recognition method is designed which employs the BFH as the surface model, and classifies surfaces based on a single novel texture image of unknown imaging parameters, and a computational method for quantitatively evaluating the relative significance of texture images within the BTF is developed.
A sparse texture representation using affine-invariant regions
151 Citations2003Svetlana Lazebnik, C. Schmid +1 more
The proposed texture representation is evaluated in retrieval and classification tasks using the entire Brodatz database and a collection of photographs of textured surfaces taken from different viewpoints.
Affine-invariant local descriptors and neighborhood statistics for texture recognition
106 Citations2003Lazebnik, Schmid +1 more
A framework for texture recognition based on local affine-invariant descriptors and their spatial layout is presented and initial probabilities computed from the generative model are refined using a relaxation step that incorporates co-occurrence statistics.
Statistical cues for domain specific image segmentation with performance analysis
78 Citations2002S. Konishi, Alan Yuille
Performance analysis on the Sowerby dataset shows that the learnt models achieve high accuracy in classifying individual pixels into those classes for which the filter responses are approximately spatially homogeneous.
Lecture notes in computer scienceShape-adapted smoothing in estimation of 3-D depth cues from affine distortions of local 2-D brightness structure
72 Citations1994Tony Lindeberg, Jonas Gårding
By extending the linear scale-space concept into an affine scale- space representation and performing affine shape adaption of the smoothing kernels, the accuracy of surface orientation estimates derived from texture and disparity cues can be improved by typically one order of magnitude.
Correlation model for 3D texture
70 Citations1999Kristin Dana, Shree K. Nayar
This work presents a correlation model for a particular class of 3D textures that characterizes the spatial relationship among neighboring pixels in an image of3D texture and the change of this spatial relationship with viewing direction.
Image and Vision ComputingUnifying statistical texture classification frameworks
67 Citations2004Manik Varma, Andrew Zisserman
There is a correspondence between the two common representations of filter outputs—textons and binned histograms and it is shown that two classification methodologies, nearest neighbour matching and Bayesian classification, are equivalent for particular choices of the distance measure.
Histogram model for 3D textures
65 Citations2002Kristin Dana, Shree K. Nayar
This work presents a concise analytical model for the bidirectional histogram of Lambertian, isotropic, randomly rough surfaces, which are common in real-world scenes and demonstrates the usefulness of the model by employing it in a novel 3D texture synthesis procedure.
IEEE Transactions on Pattern Analysis and Machine IntelligenceThe analysis and recognition of real-world textures in three dimensions
54 Citations2000Pei-Hsiu Suen, Glenn Healey
It is shown, using a set of 12,505 images from 61 material samples, that the information captured by the multiband correlation model allows surfaces to be recognized over a wide range of conditions and that the use of color information provides significant advantages for three-dimensional texture recognition.
Lecture notes in computer scienceSteerable-scalable kernels for edge detection and junction analysis
44 Citations1992Pietro Perona
Lecture notes in computer scienceThe Effect of Illuminant Rotation on Texture Filters: Lissajous’s Ellipses
34 Citations2002Mike J. Chantler, Marius Schmidt +2 more
New theory and experimental results are presented that show that changes in illumination tilt angle cause texture clusters to describe Lissajous's ellipses in feature space as illuminant tilt varies, which has significant implications for illuminants tilt invariant texture classification.
Estimating Lighting Direction and Classifying Textures
9 Citations2002Mike J. Chantler, G. McGunnigle +2 more
A classifier is proposed that is robust to lighting direction—even when the direction is unknown, and was able to accurately estimate both the azimuth and the zenith of the light source for most textures and gave a 98% classification rate.