On Developing High Accuracy OCR Systems for Telugu and Other Indian Scripts

Authors:
Chakravarthy Bhagvati;Tanuku Ravi;S. Mahesh Kumar;Atul Negi
Affiliations:
Dept. of Computer and Information Sciences, University of Hyderabad, Hyderabad, India;Dept. of Computer and Information Sciences, University of Hyderabad, Hyderabad, India;Dept. of Computer and Information Sciences, University of Hyderabad, Hyderabad, India;Dept. of Computer and Information Sciences, University of Hyderabad, Hyderabad, India
Venue:
LEC '02 Proceedings of the Language Engineering Conference (LEC'02)
Year:
2002

Citing 0
Cited 3

Characterization of printed Malayalam characters based on dominant singular values and marginal frequency

Proceedings of the International Conference on Advances in Computing, Communication and Control
Gujarati handwritten numeral optical character reorganization through neural network

Pattern Recognition
On performance analysis of end-to-end OCR systems of Indic scripts

Proceeding of the workshop on Document Analysis and Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we list a number of factors that are impo-tantin achieving high recognition accuracy in OCR systemsfor Telugu and other Indian scripts. While it is relativelyeasy to obtain 85% - 93% accuracy, it becomes increasinglydifficult to improve the performance further. We di-cusshow the factors presented in this paper helped achievean accuracy of nearly 97% with our OCR system for Teluguscript. It is expected that these factors are specific not onlyto Telugu but also work for other Indian scripts in generaland south Indian scripts in particular.