Massively parallel approach to pattern recognition

Author

Wang, Wu ; Iyengar, S. Sitharama ; Chen, Jianhua

Author_Institution

Dept. of Comput. Sci., Louisiana State Univ., Baton Rouge, LA, USA

fYear

1990

fDate

21-23 Mar 1990

Firstpage

61

Lastpage

67

Abstract

Template matching is concerned with measuring the similarity between patterns of two objects. A massively parallel approach to pattern recognition with a large template set is proposed. A class of image recognition problem inherently needs large template sets, for example, the recognition of Chinese characters, which needs thousands of templates. The proposed algorithm is based on the SIMD-SM-R machine or the SIMD machine with broadcasting abilities, which is the most popular parallel machine to date, and uses a multiresolution method to search for the matching template. The approach uses the pyramid data structure for the multiresolution representation of templates and the input image pattern. For a given image it scans the template pyramid searching for the match. Implementation of the proposed scheme is described

Keywords

computerised pattern recognition; parallel processing; Chinese characters; SIMD machine; SIMD-SM-R machine; broadcasting abilities; image recognition problem; massively parallel approach; multiresolution method; pattern recognition; pyramid data structure; template matching; Broadcasting; Character recognition; Computer science; Data structures; Image recognition; Image resolution; Parallel machines; Pattern matching; Pattern recognition; Writing;

fLanguage

English

Publisher

ieee

Conference_Titel

Computers and Communications, 1990. Conference Proceedings., Ninth Annual International Phoenix Conference on

Conference_Location

Scottsdale, AZ

Print_ISBN

0-8186-2030-7

Type

conf

DOI

10.1109/PCCC.1990.101601

Filename

101601