OCR of Printed Telugu Text with High Recognition Accuracies
Telugu is one of the oldest and popular languages of India spoken by more than 66 million people especially in South India. Development of Optical Character Recognition systems for Telugu text is an area of current research.
OCR of Indian scripts is much more complicated than the OCR of Roman script because of the use of huge number of combinations of characters and modifiers. Basic Symbols are identified as the unit of recognition in Telugu script. Edge Histograms are used for a feature based recognition scheme for these basic symbols. During recognition, it is observed that, in many cases, the recognizer incorrectly outputs a very similar looking symbol. Special logic and algorithms are developed using simple structural features for improving recognition accuracies considerably without too much additional computational effort. It is shown that recognition accuracies of 98.5 % can be achieved on laser quality prints with such a procedure.
KeywordsRecognition Accuracy Near Neighbour Optical Character Recognition Foreground Pixel Zero Crossing
Unable to display preview. Download preview PDF.
- 2.Mori, S., Suen, C.Y., Yamamoto, K.: Historical review of OCR Research and Development. Proc. of the IEEE, 1029–1058 (1992)Google Scholar
- 4.Bansal, V., Sinha, R.M.K.: A survey of OCR in Indian Languages and a Devanagari OCR scheme. In: Proceedings of the STRANS – 2001, IIT, Kanpur (2001)Google Scholar
- 6.Nagabhushan, P., Radhika, A.: Improved region decomposition method for the recognition of non-uniform sized characters. In: Proceedings of the International Conference on Cognitive science, ICCS 1997, New Delhi, vol. 1, pp. 36–42 (1997)Google Scholar
- 7.Anna Durai, S., et al.: Tamil character recognition using multilayer neural network. In: Indian Conference on Pattern Recognition. Image Processing and Computer Vision (ICPIC), pp. 155–160 (1995)Google Scholar
- 8.Bishnu, A., Chaudhuri, B.: Segmentation of Bangla Handwritten text into characters by recursive contour following. In: Proceedings of the Fifth International Conference on Document Analysis and Recognition, ICDAR 1999, pp. 402–405 (1999)Google Scholar
- 9.Pal, U., Chaudhuri, B.: Script line separation from Indian Multi-Script Documents. In: Proceedings of the Fifth International Conference on Document Analysis and Recognition, ICDAR 1999, pp. 406–409 (1999)Google Scholar
- 10.Bansal, V., Sinha, R.: On how to describe shapes of Devanagari Characters and use them for Recognition. In: Proceedings of ICDAR 1999, pp. 410–413 (1999)Google Scholar
- 11.Anatani, S., Agnihotri, L.: Gujarati Character Recognition. In: Proceedings of ICDAR 1999, pp. 418–421 (1999)Google Scholar
- 12.Sundaresan, C., Keerthi, S.: A study of representation for Pen based Handwriting recognition of Tamil Characters. In: Proceedings of ICDAR 1999, pp. 422–425 (1999)Google Scholar
- 14.Negi, A., et al.: An OCR system for Telugu. In: Proceedings of International Conference on Document Analysis and Recognition, ICDAR – 2001, Seattle, USA (2001)Google Scholar
- 15.Vasantha Lakshmi, C., Patvardhan, C., Singh, R.: A novel basic symbol approach for Telugu OCR with neural networks. Journal of the Computer Society of India, 31–39 (March 2003)Google Scholar
- 16.Vasantha Lakshmi, C., Patvardhan, C.: Recognition of basic symbols in Telugu by Neural networks. In: STRANS-2002, IIT Kanpur, March 15–17 (2002)Google Scholar
- 17.Vasantha Lakshmi, C., Patvardhan, C.: An OCR system for Telugu text: A basic symbol approach. Int. Jl. on Pattern Analysis and Applications, 190–204 (July 2004)Google Scholar
- 18.Vasantha Lakshmi, C.: Ph.D. Thesis, Dayalbagh Educational Institute, Agra, India (unpublished, 2003)Google Scholar
- 19.Sonka, M., Hlavac, V., Boyle, R.: Image processing, Analysis, and Machine Vision, 2nd edn. Brooks/Cole Publishing Company (1998)Google Scholar
- 21.LEAP, Indian language software, CDAC, Pune, IndiaGoogle Scholar
- 22.Manjunath, B.S., Salembier, P., Sikora, T. (eds.): Introduction to MPEG-7. John Wiley & Sons, Chichester (2002)Google Scholar