Lattice Associative Memories for Segmenting Color Images in Different Color Spaces

This paper describes a technique for segmenting color images in different color spaces based on lattice auto-associative memories. Basically, the min- or max auto-associative memories can be used to determine tetrahedra enclosing different subsets of image pixels. The column vectors of either memory, additively scaled, correspond to the most saturated color pixels that are the vertices of a specified tetrahedron, and any other color pixel can be considered a linear mixture of these points. The non-negative least square method is used to linearly unmix color pixels and provides the fundamental step in the unsupervised segmentation of a given input color image. We give illustrative examples to demonstrate the effectiveness of our method as well as the color separation results in four different color spaces.