Radial basis function and subspace approach for printed Kannada text recognition

Author

Vijaykumar, B. ; Ramakrishnan, A.G.

Author_Institution

Dept. of Electr. Eng., Indian Inst. of Sci., Bangalore, India

Volume

5

fYear

2004

fDate

17-21 May 2004

Abstract

Neural network based radial basis function networks (RBFN) and subspace projection approach have been employed to recognize printed Kannada characters. RBFNs are trained with wavelet features using K-means and subspace method is applied on normalized image. Use of structural features for disambiguating confused characters improved the recognition accuracy by 3% in case of subspace and by 1.6% using RBFN. Compared to subspace, a maximum recognition rate of 99.1% is achieved with RBFN using Haar wavelets and structural features.

Keywords

Haar transforms; character recognition; radial basis function networks; Haar wavelets; K-means method; RBFN training; confused characters disambiguation; maximum recognition rate; neural network based RBFN; normalized image; printed Kannada character recognition; radial basis function networks; recognition accuracy; structural features; subspace projection method; text recognition; Character recognition; Discrete wavelet transforms; Feature extraction; Filters; Multiresolution analysis; Neural networks; Optical character recognition software; Radial basis function networks; Shape; Text recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2004. Proceedings. (ICASSP '04). IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-8484-9

Type

conf

DOI

10.1109/ICASSP.2004.1327112

Filename

1327112