In this paper, we review most major filtering approaches to texture feature extraction and perform a comparative study. Filtering approaches included are Laws masks (1980), ring/wedge filters, dyadic Gabor filter banks, wavelet transforms, wavelet packets and wavelet frames, quadrature mirror filters, discrete cosine transform, eigenfilters, optimized Gabor filters, linear predictors, and optimized finite impulse response filters. The features are computed as the local energy of the filter responses. The effect of the filtering is highlighted, keeping the local energy function and the classification algorithm identical for most approaches. For reference, comparisons with two classical nonfiltering approaches, co-occurrence (statistical) and autoregressive (model based) features, are given. We present a ranking of the tested approaches based on extensive experiments.

Filtering for texture classification: a comparative study

Image processing and computer vision are currently hot topics with undergraduates and professionals alike. "Feature Extraction and Image Processing" provides an essential guide to the implementation of image processing and computer vision techniques, explaining techniques and fundamentals in a clear and concise manner. Readers can develop working techniques, with usable code provided throughout and working Matlab and Mathcad files on the web. Focusing on feature extraction while also covering issues and techniques such as image acquisition, sampling theory, point operations and low-level feature extraction, the authors have a clear and coherent approach that will appeal to a wide range of students and professionals.The new edition includes: a new coverage of curvature in low-level feature extraction (SIFT and saliency) and features (phase congruency); geometric active contours; morphology; and camera models and an updated coverage of image smoothing (anistropic diffusion); skeletonization; edge detection; curvature; and shape descriptions (moments). It is an essential reading for engineers and students working in this cutting edge field. It is an ideal module text and background reference for courses in image processing and computer vision. It features a companion website that includes worksheets, links to free software, Matlab files, solutions and new demonstrations.

/pdf/feature-extraction-and-image-processing-1kd8gihm96.pdf

Feature Extraction and Image Processing

Texture features that are based on the local power spectrum obtained by a bank of Gabor filters are compared. The features differ in the type of nonlinear post-processing which is applied to the local power spectrum. The following features are considered: Gabor energy, complex moments, and grating cell operator features. The capability of the corresponding operators to produce distinct feature vector clusters for different textures is compared using two methods: the Fisher (1923) criterion and the classification result comparison. Both methods give consistent results. The grating cell operator gives the best discrimination and segmentation results. The texture detection capabilities of the operators and their robustness to nontexture features are also compared. The grating cell operator is the only one that selectively responds only to texture and does not give false response to nontexture features such as object contours.

/pdf/comparison-of-texture-features-based-on-gabor-filters-3gf0iyx8at.pdf

Comparison of texture features based on Gabor filters

Image analysis by bidimensional empirical mode decomposition

Methods for digital-image texture analysis are reviewed based on available literature and research work either carried out or supervised by the authors The review has been prepared on request of Dr Richard Lerski, Chairman of the Management Committee of the COST B11 action "Quantitation of Magnetic Resonance Image Texture"

/pdf/texture-analysis-methods-a-review-3pph5x6k81.pdf

Texture Analysis Methods - A Review

Recent studies have confirmed that the multichannel Gabor decomposition represents an excellent tool for image segmentation and boundary detection. Unfortunately, this approach when used for unsupervised image analysis tasks imposes excessive storage requirements due to the nonorthogonality of the basis functions and is computationally highly demanding. In this correspondence, we propose a novel method for efficient image analysis that uses tuned matched Gabor filters. The algorithmic determination of the parameters of the Gabor filters is based on the analysis of spectral feature contrasts obtained from iterative computation of pyramidal Gabor transforms with progressive dyadic decrease of elementary cell sizes. The method requires no a priori knowledge of the analyzed image so that the analysis is unsupervised. Computer simulations applied to different classes of textures illustrate the matching property of the tuned Gabor filters derived using our determination algorithm. Also, their capability to extract significant image information and thus enable an easy and efficient low-level image analysis will be demonstrated. >

Unsupervised texture segmentation of images using tuned matched Gabor filters

A comparison of texture feature extraction using adaptive gabor filtering, pyramidal and tree structured wavelet transforms

This paper presents an unsupervised texture segmentation algorithm based on feature extraction using multichannel Gabor filtering. It is shown that feature contrast, a criterion derived for Gabor filter parameter selection, is well suited for feature coordinate weighting in order to reduce the feature space dimension. The central idea of the proposed segmentation algorithm is to decompose the actual segmented image into disjunct areas called scrap images and use them after lowpass filtering as additional features for repeated k-means clustering and minimum distance classification. This yields a classification of texture regions with an improved degree of homogeneity while preserving precise texture boundaries.

An unsupervised texture segmentation algorithm with feature space reduction and knowledge feedback

This article describes a novel approach to orientation and scale-invariant detection of textured objects in images. It performs both, a segmentation of multi-object scenes and the identification of rotation angles and scale rates of textures in an image by applying a comparison with reference texture features stored in a database. The main novelty of the proposed method is the transform of rotation and dilation into shifts in the feature space by employing a polar-log Gabor filter bank. Texture segmentation and identification of the rotation angles and scale rates have been carried out using symmetric phase only matched filters. The simulation results illustrated highlight the performance of the presented method in an exemplary manner.

Orientation- and scale-invariant recognition of textures in multi-object scenes

We present a segmentation algorithm for multichannel image analysis. It is based on a novel method that significantly improves the segmentation performance with respect to both homogeneity of the segmented regions and precision of the segmented region boundaries. The algorithm yields excellent results in comparison with other segmentation algorithms that are based on feature space clustering followed by minimum distance classification, as is shown in some segmentation examples. The main idea of the algorithm is the iterative feedback of the knowledge about the analysed image that has been obtained from preceding segmentation results. It needs just a stack of feature images and the indication of the number of required classes for input data. Therefore, it has a broad field of possible applications, especially in multichannel image analysis.

O. Pichler

Papers

Unsupervised texture segmentation of images using tuned matched Gabor filters

A comparison of texture feature extraction using adaptive gabor filtering, pyramidal and tree structured wavelet transforms

An unsupervised texture segmentation algorithm with feature space reduction and knowledge feedback

Orientation- and scale-invariant recognition of textures in multi-object scenes

A multichannel algorithm for image segmentation with iterative feedback