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

Volume

ii

fYear

1990

fDate

16-21 Jun 1990

Firstpage

343

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;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1990. Proceedings., 10th International Conference on

Conference_Location

Atlantic City, NJ

Print_ISBN

0-8186-2062-5

Type

conf

DOI

10.1109/ICPR.1990.119380

Filename

119380