We present a novel information theoretic approach to image segmentation. We cast the
segmentation problem as the maximization of the mutual information between the region
labels and the image pixel intensities, subject to a constraint on the total length of the region
boundaries. We assume that the probability densities associated with the image pixel
intensities within each region are completely unknown a priori, and we formulate the
problem based on nonparametric density estimates. Due to the nonparametric structure, our …

In this paper, we present a novel information theoretic approach to image segmentatioa Wfe
cast lhe segmentation problem as the maximization of (he mutual information between the
region labels and the image pixel intensities, subject to a constraint on the total length of the
region boundaries. Wfe assume thatthe probability densities associated with the image pixel
intensities within each region are completely unknown a priori, and we formulate the
problem based on nonparametric density estimates. Due to the nonparametric structure, our …