Texture classification by center-symmetric auto-correlation, using Kullback discrimination of distributions

Abstract We propose a new method of texture analysis and classification based on a local center-symmetric covariance analysis, using Kullback (log-likelihood) discrimination of sample and prototype distributions. Features of our analysis are generalized, invariant, local measures of texture having center-symmetric patterns, which is characteristic of many natural and artificial textures. We introduce two local center-symmetric auto-correlations, with linear and rank-order versions (SAC and SRAC), together with a related covariance measure (SCOV) and variance ratio (SVR). All of these are rotation-invariant, and three are locally greyscale invariant, robust measures. In classification experiments, we compare their discriminant information to that of Laws' well-known convolutions, which have specific center-symmetric masks. We find that our new covariance measures, which can be regarded as generalizations of Laws' measures, perform better than Laws' approach despite their measure of texture pattern and grey-scale.

[1]  Josef Kittler,et al.  On local linear transform and Gabor filter representation of texture , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis,.

[2]  Li WangDong-Chen He,et al.  Texture classification using texture spectrum , 1990, Pattern Recognit..

[3]  Michael Spann,et al.  Texture feature performance for image segmentation , 1990, Pattern Recognit..

[4]  Solomon Kullback,et al.  Information Theory and Statistics , 1970, The Mathematical Gazette.

[5]  F. Ade,et al.  Characterization of textures by ‘Eigenfilters’ , 1983 .

[6]  Linda G. Shapiro,et al.  Computer and Robot Vision , 1991 .

[7]  M. Unser.  Local linear transforms for texture measurements , 1986 .

[8]  Luc Van Gool,et al.  Texture analysis Anno 1983 , 1985, Comput. Vis. Graph. Image Process..

[9]  Solomon Kullback,et al.  Information Theory and Statistics , 1960 .

[10]  Luc Van Gool,et al.  Texture inspection with self-adaptive convolution filters , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[11]  M. Kendall,et al.  An Introduction to the Theory of Statistics. , 1911 .

[12]  Azriel Rosenfeld,et al.  Experiments with texture classification using averages of local pattern matches , 1981, IEEE Transactions on Systems, Man, and Cybernetics.

[13]  A. R. Rao,et al.  A Taxonomy for Texture Description and Identification , 1990, Springer Series in Perception Engineering.

[14]  K. Laws.  Textured Image Segmentation , 1980 .

[15]  Larry S. Davis,et al.  Texture classification by local rank correlation , 1985, Comput. Vis. Graph. Image Process..

[16]  C. Neubauer,et al.  Segmentation of defects in textile fabric , 1992, [1992] Proceedings. 11th IAPR International Conference on Pattern Recognition.

[17]  K. K. Benke,et al.  Convolution operators as a basis for objective correlates of texture perception , 1988, IEEE Trans. Syst. Man Cybern..

[18]  Matti Pietikäinen,et al.  Performance evaluation of texture measures with classification based on Kullback discrimination of distributions , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[19]  Phil Brodatz,et al.  Textures: A Photographic Album for Artists and Designers , 1966 .

[20]  Bradley Pryor Kjell,et al.  Determining composition of grain mixtures using texture energy operators , 1992, Other Conferences.

[21]  Jane You,et al.  A multi-scale texture classifier based on multi-resolution 'tuned' mask , 1992, Pattern Recognit. Lett..