A computational model for perceptual grouping

A computational model for perceptual grouping is described, based on a single-instruction multiple-data (SIMD) machine, embedding a cellular automaton. The author shows that extraction of information and combination of perceptual features into higher-level grouping can be performed by SIMD computations. A description is given of a labeling procedure for the cellular automaton, based on the Huffman-Clowes system, where the labels are the states of the automation and the label combination rules its local transition rules.<
>