Computer architectures for image analysis

Abstract

The author reviews a number of parallel-processing projects which use processing power, memory and input/output of image data for image analysis. The systems covered include ILLIAC, CLIP, MPP, the cytocomputer, SNAP, and PAPIA and II. Issues in parallelism reviewed include types of parallelism, types of operation, complexity of processing elements, and the different paradigms of human vision and their application and implementation.<>