A multifractal analysis approach for SAR image segmentation

In this paper we propose a multifractal-based approach to the extraction of textural features from SAR images. We first estimate the Holder exponents from the continuous wavelet transform of the image, and then we compute the singularity spectrum using affine iterated function systems (IFS). Each fractal component consisting of pixels having the same Holder exponent can be an attractor of an IFS. Finally, to highlight the edges, we use the K-means algorithm. The spectrum at each point is used as input for the K-means classifier. The theory and the algorithms for this segmentation approach are presented. Experimental results show that the approach is beneficial for SAR image segmentation, demonstrating better segmentation than those obtained by other techniques.