View Related Documents

Abstract

In this paper we present two algorithms for color image segmentation based on Huang's idea of describing the segmentation problem as the one of minimizing a suitable energy function for a Hopfield network. The first algorithm builds three different networks (one for each color feature) and then combine the results. The second builds a unique network according to the number of clusters obtained by histogram analysis. Experimental results, heuristically and quantitatively evaluated, are encouraging.

Fulltext Preview

Image of the first page of the fulltext document