An Improved Method Based on Gabor Feature for Mathematical Symbol Recognition

Author

Tian, Xue-dong ; Zuo, Li-Na ; Yang, Fang ; Ha, Ming-Hu

Author_Institution

Hebei Univ., Baoding

Volume

3

fYear

2007

fDate

19-22 Aug. 2007

Firstpage

1678

Lastpage

1682

Abstract

An improved method based on Gabor feature for printed mathematical symbol recognition is presented in this paper. Elastic meshing technology is first applied to partition the character and get sampling points. Then, a set of Gabor filters are used to extract different directional features at each sampling point. In order to decrease the processing time, convolution operations are conducted with the real part of Gabor templates. Experimental results show that the proposed method has excellent performance on printed mathematical symbols.

Keywords

Gabor filters; character recognition; document image processing; feature extraction; filtering theory; image classification; image texture; matrix algebra; mesh generation; Gabor feature; Gabor filters; character partitioning; classification; coefficient matrix; elastic meshing technology; printed mathematical symbol recognition; sampling points; texture feature extraction; Character recognition; Convolution; Cybernetics; Feature extraction; Fingerprint recognition; Gabor filters; Machine learning; Optical character recognition software; Sampling methods; Vehicles; Convolution; Elastic meshing; Gabor filter; Mathematical symbol recognition; Sampling point;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2007 International Conference on

Conference_Location

Hong Kong

Print_ISBN

978-1-4244-0973-0

Electronic_ISBN

978-1-4244-0973-0

Type

conf

DOI

10.1109/ICMLC.2007.4370417

Filename

4370417