Texture Analysis Using Modified Discrete Radon Transform

In this paper, we address the problem of the rotationinvariant texture analysis. For this purpose, we first present a modified version of the discrete Radon transform whose performance, including accuracy and processing time, is significantly better than the conventional transform in direction estimation and categorization of textural images. We then utilize this transform with a rotated version of Gabor filters to propose a new scheme for texture classification. Experimental results on a set of images from the Brodatz album indicate that the proposed scheme outperforms previous works. key words: rotation-invariant texture analysis, discrete Radon transform, Gabor filters, direction estimation