A Bilingual Machine-Interface OCR for Printed Kannada and English Text Employing Wavelet Features

Author

Kunte, R. Sanjeev ; Samuel, R. D Sudhaker

Author_Institution

J S S Res. Found., Mysore

fYear

2007

fDate

17-20 Dec. 2007

Firstpage

202

Lastpage

207

Abstract

An Optical Character Recognition (OCR) system is one of the important research areas in the field of Human- machine interface. This paper presents a bilingual OCR system for printed Kannada and English text. Gabor filter based features are used for separating the Kannada and English words from the bilingual document. Wavelets that have been progressively used in pattern recognition are used in the system to extract the features for classifying both the Kannada and English characters. Multilayer feed forward Neural classifiers known for their good generalization and approximation property have been effectively used in the system for the classification. An overall recognition rate of 90.5% is obtained at character level.

Keywords

Gabor filters; feature extraction; human computer interaction; multilayers; natural language processing; optical character recognition; pattern classification; recurrent neural nets; text analysis; wavelet transforms; English text; Gabor filter; bilingual OCR system; bilingual document; bilingual machine-interface OCR; feature extraction; human- machine interface; multilayer feed forward neural classifiers; optical character recognition system; pattern recognition; printed Kannada; wavelet features; Character recognition; Databases; Feature extraction; Gabor filters; Information technology; Natural languages; Optical character recognition software; Optical filters; Pattern analysis; Pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Technology, (ICIT 2007). 10th International Conference on

Conference_Location

Orissa

Print_ISBN

0-7695-3068-0

Type

conf

DOI

10.1109/ICIT.2007.12

Filename

4418296