A Gabor filter-based method for recognizing handwritten numerals

被引：117

作者：

Hamamoto, Y ^{[1
]}

Uchimura, S

Watanabe, M

Yasuda, T

Mitani, Y

Tomita, S

机构：

[1] Yamaguchi Univ, Fac Engn, Ube, Yamaguchi 755, Japan

[2] Oshima Natl Coll Maritime Technol, Oshima 74221, Japan

来源：

PATTERN RECOGNITION | 1998年 / 31卷 / 04期

关键词：

numeral character recognition; Gabor filter; feature extraction;

D O I：

10.1016/S0031-3203(97)00057-5

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We study a Gabor-filter-based method for handwritten numeral character recognition. The Gabor filter is based on a multi-channel filtering theory for processing visual information in the early stages of the human visual systems. The performance of the Gabor-filter-based method is demonstrated on the ETL-1 database. Experimental results show that the artificial neural-network classifier achieved the error rate of 2.34% for a test set of 7000 characters. Therefore, the Gabor-filter-based method should be considered in recognition of handwritten numeric characters. (C) 1998 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

引用

页码：395 / 400

页数：6

共 19 条

[1] TWO-DIMENSIONAL SPECTRAL-ANALYSIS OF CORTICAL RECEPTIVE-FIELD PROFILES [J].

DAUGMAN, JG .

VISION RESEARCH, 1980, 20 (10) :847-856

[2] UNCERTAINTY RELATION FOR RESOLUTION IN SPACE, SPATIAL-FREQUENCY, AND ORIENTATION OPTIMIZED BY TWO-DIMENSIONAL VISUAL CORTICAL FILTERS [J].

DAUGMAN, JG .

JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 1985, 2 (07) :1160-1169

[3]

Fukunaga K., 1990, INTRO STAT PATTERN R

[4]

Gabor D., 1946, Journal of the Institution of Electrical Engineers-Part III: Radio and Communication Engineering, V93, P429, DOI DOI 10.1049/JI-3-2.1946.0074

[5]

GARRIS MD, 1991, P C AN NEUR NETW APP, P160

[6]

Hamamoto Y., 1995, Proceedings of the Third International Conference on Document Analysis and Recognition, P819, DOI 10.1109/ICDAR.1995.602027

[7]

HAMAMOTO Y, 1996, IEICE T J, V79, P202

[8] UNSUPERVISED TEXTURE SEGMENTATION USING GABOR FILTERS [J].