Multilinguistic handwritten character recognition by Bayesian decision-based neural networks

Author

Fu, Hsin-Chia ; Xu, Yeong Yuh

Author_Institution

Dept. of Comput. Sci. & Inf. Eng., Nat. Chung-Hsing Univ., Taichung, Taiwan

Volume

46

Issue

10

fYear

1998

fDate

10/1/1998 12:00:00 AM

Firstpage

2781

Lastpage

2789

Abstract

In this paper, we present a Bayesian decision-based neural network (BDNN) for multilinguistic handwritten character recognition. The proposed self-growing probabilistic decision-based neural network (SPDNN) adopts a hierarchical network structure with nonlinear basis functions and a competitive credit-assignment scheme. Our prototype system demonstrates a successful utilization of SPDNN to the handwriting of Chinese and alphanumeric character recognition on both public databases (CCL/HCCR1 for Chinese and CEDAR for the alphanumerics) and in-house database (NCTU/NNL). Regarding the performance, experiments on three different databases all demonstrated high recognition (86-94%) accuracy as well as low rejection/acceptance (6.7%) rates. As for the processing speed, the whole recognition process (including image preprocessing, feature extraction, and recognition) consumes approximately 0.27 s/character on a Pentium-100 based personal computer, without using a hardware accelerator or coprocessor

Keywords

Bayes methods; feature extraction; handwriting recognition; learning (artificial intelligence); neural nets; optical character recognition; Bayesian decision-based neural network; CCL/HCCR1 public database; CEDAR public database; Chinese; NCTU/NNL in-house database; Pentium-100 based personal computer; alphanumeric character recognition; competitive credit-assignment scheme; feature extraction; hierarchical network structure; high recognition accuracy; image preprocessing; low rejection/acceptance rates; multilinguistic handwritten character recognition; nonlinear basis functions; self-growing probabilistic decision-based neural network; Bayesian methods; Character recognition; Feature extraction; Hardware; Image databases; Image recognition; Microcomputers; Neural networks; Prototypes; Spatial databases;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/78.720379

Filename

720379