Multiscale handwritten character recognition using CNN image filters

Author

Saatci, Ertugrul ; Tavsanoglu, Vedat

Author_Institution

Sch. of Eng., South Bank Univ., London, UK

Volume

3

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

2044

Lastpage

2048

Abstract

This paper presents a multi-scale character recognition system consisting of three single-scale recognition systems. The system uses a filter bank of Gabor-type filters implemented by a cellular neural network (CNN). Based on a test set of 26 test characters acting as template and a set consisting of four subsets of 26 unknown handwritten test characters, a maximum 96% and an average 93% correct recognition is provided. This is a considerable improvement over the performance of existing single-scale recognition systems

Keywords

FIR filters; cellular neural nets; handwritten character recognition; image processing equipment; optical character recognition; performance evaluation; scaling phenomena; Gabor-type filters; cellular neural network; correct recognition performance; filter bank; image filters; multi-scale handwritten character recognition system; single-scale recognition systems; test character template; unknown handwritten test characters; Cellular neural networks; Character recognition; Feature extraction; Feedback; Filter bank; Frequency; Gabor filters; Handwriting recognition; Image recognition; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on

Conference_Location

Honolulu, HI

ISSN

1098-7576

Print_ISBN

0-7803-7278-6

Type

conf

DOI

10.1109/IJCNN.2002.1007454

Filename

1007454