Hand-written digit recognition by one variable stochastic simulated annealing

Author

Lee, Sunghun ; Chiwha Song ; Lee, Won Don

Author_Institution

Korea Mobile Telecommun. Co., Daejeon, South Korea

Volume

2

fYear

1993

fDate

25-29 Oct. 1993

Firstpage

1586

Abstract

This paper presents the experimental results of hand-written digit recognition. This neural approach is based on the graph matching, a form of elastic matching, and one-variable stochastic simulated annealing (OVSSA) which is a mean-field annealing algorithm to find a global minimum of a real valued function. Experimental results show that this method is insensitive to displacement, scale changes and rotation, and promising to hand-written character recognition.

Keywords

neural nets; optical character recognition; simulated annealing; displacement insensitivity; elastic matching; global minimum; graph matching; hand-written digit recognition; handwritten character recognition; mean-field annealing algorithm; neural approach; one-variable stochastic simulated annealing; real-valued function; rotation insensitivity; scale insensitivity; Character recognition; Computational modeling; Computer science; Computer simulation; Educational institutions; Mobile computing; Pattern matching; Pattern recognition; Simulated annealing; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on

Print_ISBN

0-7803-1421-2

Type

conf

DOI

10.1109/IJCNN.1993.716906

Filename

716906