Title :
Parallel coordination of image operators based on shared-memory architecture
Author :
Hwang, Shu-Yuen ; Tanimoto, Steven L.
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Chiao-Tung Univ., China
Abstract :
Several types of parallelism that may be exploited in vision algorithms based on a state-space search are identified. A method called the V* algorithm, which generates the successors of a state in parallel, is presented. In machine vision, this part of the search process is very expensive, and thus V* permits substantial speedup. An experimental evaluation of V* which is based on a simulation of a character-recognition algorithm is presented. The simulation runs on a Sequent Balance 21000, using 16 out of 20 processors
Keywords :
computer vision; computerised pattern recognition; parallel algorithms; parallel architectures; search problems; state-space methods; Sequent Balance 21000; character-recognition algorithm; computer vision; image operators; machine vision; parallel coordination; shared-memory architecture; state-space search; Adaptive control; Computational efficiency; Computer architecture; Computer science; Image recognition; Machine vision; Parallel processing; Search problems; Space exploration; State-space methods;
Conference_Titel :
Pattern Recognition, 1990. Proceedings., 10th International Conference on
Conference_Location :
Atlantic City, NJ
Print_ISBN :
0-8186-2062-5
DOI :
10.1109/ICPR.1990.119380
