FAST ALGORITHM FOR TEXTURE-DISCRIMINATION BY USE OF A SEPARABLE ORTHONORMAL DECOMPOSITION OF THE COOCCURRENCE MATRIX

We consider the problem of texture analysis with a fast algorithm. For that purpose we propose to use coefficients of the decomposition of c o-occurrence matrices on an orthonormal and separable basis. We apply this method for texture discrimination, and we thus demonstrate with s ome examples its efficiency in terms of rapidity, discrimination perfo rmance, and robustness. We compare this method with classifiers that u se a Fisher linear discrimination on features a priori defined in the co-occurrence matrices. (C) 1997 Optical Society of America.