Parallel Vision Computing on a Network of Workstation Clusters

the advanced technology of computer network has made Vision computing involves the execution of a large number of operations on large sets of structured data. In this paper we demonstrate that such vision tasks can be implemented in parallel on a network of workstation clusters for fast processing. We introduce some techniques used in distributed systems and adopt a divide-and-conquer policy to schedule the complex vision tasks for parallelism. The visionrelated algorithms for mask convolution, feature extraction, discrete Fourier transform and image matching are implemented in parallel using PVM(paralle1 virtual machine). In addition, a hierarchical object recognition system is described to conclude that a general distributed system can be applied to parallel vision computing at a low cost.