An object recognition system using stochastic knowledge source and VLSI parallel architecture

Author

Mao, W.D. ; Kung, S.Y.

Author_Institution

Dept. of Electr. Eng., Princeton Univ., NJ, USA

Volume

i

fYear

1990

fDate

16-21 Jun 1990

Firstpage

832

Abstract

The authors present a system for 2D shape recognition using hidden Markov model (HMM) knowledge sources. The shape is represented by a sequence of curvature values. A ring hidden Markov model (RHMM), which incorporates a ring structure and local connectivity, is proposed. The approach solves both the context sensitivity problem and the pattern instantiation problem. Simulation results on aircraft indicate that the proposed system can achieve almost 100% recognition accuracy at a very fast learning speed. It is shown that the RHMM system can be efficiently implemented in a systolic array, permitting real-time processing

Keywords

Markov processes; VLSI; knowledge based systems; parallel architectures; pattern recognition; picture processing; 2D shape recognition; VLSI parallel architecture; aircraft; context sensitivity; curvature value sequence; local connectivity; object recognition system; pattern instantiation; ring hidden Markov model; ring structure; stochastic knowledge source; systolic array; Dynamic programming; Hidden Markov models; Object recognition; Parallel architectures; Pattern recognition; Shape; Stochastic processes; Stochastic systems; Target recognition; Very large scale integration;

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.1990.118225

Filename

118225