OCR for Script Identification of Hindi (Devnagari) Numerals using Error Diffusion Halftoning Algorithm with Neural Classifier
The applications on numbers are across-the-board that there is much scope for study. The chic of writing numbers is diverse and comes in a variety of form, size and fonts. Identification of Indian languages scripts is challenging problems. In Optical Character Recognition [OCR], machine printed or handwritten characters/numerals are recognized. There are plentiful approaches that deal with problem of detection of numerals/character depending on the sort of feature extracted and different way of extracting them. This paper proposes a recognition scheme for handwritten Hindi (devnagiri) numerals; most admired one in Indian subcontinent our work focused on a technique in feature extraction i.e. Local-based approach, a method using 16-segment display concept, which is extracted from halftoned images & Binary images of isolated numerals. These feature vectors are fed to neural classifier model that has been trained to recognize a Hindi numeral. The archetype of system has been tested on varieties of image of numerals. Experimentation result shows that recognition rate of halftoned images is 98 % compared to binary images (95%).
<p>[1] Hussain & Kabuka M.R, ÔÇÿA novel feature recognition Neural network & its application to character recognition-, IEEE TRANS, PAML, Volume 16, 1994, pp-98-106.
[2] Ulicheny, Robert - ÔÇÿDigital Halftoning-, Halliday Lithography, 1987.
[3] Robert W. Floyd and Louis Steinberg, ÔÇÿAn Adaptive Algorithm for Spatial Grayscale-, Proceedings of the Society for Information Display, 1976, 17 (2) pp. 75-77.
[4] Jonas Gomes and Luiz Velho, ÔÇÿImage processing for computer Graphics-, Springer Verlag, New York, Inc, 1997.
[5] T. Vasudev and G. Hemanth Kumar and G. S. Guru and P. Nagabhushan, -Extension of seven-segment display concept for handwritten numeral recognition -A-simple projection approach-, National conference on document analysis and recognition, NCDAR, 2001 ,pp 57-60.
[6] Jacek, M Zurada, ÔÇÿIntroduction to Artificial Neural Network System-, Jaico Publishing house, third edition 1999.
[7] Alessandro Vinciarelli, -A survey on offline cursive word recogniton pattern recognition-, 2002, 35(7), pp1433-1446.
[8] Ahmed, S. M, et.al, ÔÇÿExperiments in character recognition to develop tools For an optical character recogntion system-, IEEE inc.1st National multi topic conf proc.nust ,rawalpindi,pakistan, nov.1995, 61-67.
[9] Alexandre lemieux,christian gagne & marc Parizeau, ÔÇÿGenetically Engineering of Handwriting Representations-, proc. of the international workshop on frontiers in handwriting Recognition (IWFHR),Nigagaraon- lake.August 2002, pp. 6-8.
[10] Bortolozzi, F., Britto Jr,. A Oliveira, L. S and Morita, M., ÔÇÿRecent Advances in handwriting Recognition-, umapada pal et al editors, Documnet Analysis, 2005, pp.1-31.
[11] Gader P. D., Forester B., Ganzberger M., A. Bilies,B Mitchell, M. Whalen, T Youeum ÔÇÿRecognition of handwritten digits using template & model matching. Pattern recognition- , 1991, 5(24):421-431.
[12] Govinda, V.K & Shivaprasad, A P, “Character recognition-a review, Pattern recognition", 1990, 23: pp. 671-683.
[13] Hebert Jean-Francois, Parizeau Marc & Nadia Ghazali, ÔÇÿA new fuzzy geometirc represenation for on-line isolated character recognition- , proc of 14th international conference on Pattern recognition, Brisbane, 1998, pp. 1121-1123.
[14] Mantas, J-An overview of character recognition Methodologies-, Pattern recognition, 1986, 19, pp 425-430.
[15] Suen C.Y., Berthod M., & Mori. S, ÔÇÿAutomatic Recognition of hand printed character-the state of art-, proceeding of IEEE.68, 1980, pp. 469- 487.
[16] Nouboud F., & Plamondon, ÔÇÿOnline Recognition of hand printed chracter: survey and beta tests, pattern recognition-, 1990, 23: pp. 1031- 1044.
[17] Plamondon Rejean, & Sargur N, Srihari, ÔÇÿOn line & off line handwriting recognition- A comprehensive survey IEEE Transactions on PAMI.22, 2000, pp.63-83.</p>
<p>[1] Hussain & Kabuka M.R, ÔÇÿA novel feature recognition Neural network & its application to character recognition-, IEEE TRANS, PAML, Volume 16, 1994, pp-98-106.
[2] Ulicheny, Robert - ÔÇÿDigital Halftoning-, Halliday Lithography, 1987.
[3] Robert W. Floyd and Louis Steinberg, ÔÇÿAn Adaptive Algorithm for Spatial Grayscale-, Proceedings of the Society for Information Display, 1976, 17 (2) pp. 75-77.
[4] Jonas Gomes and Luiz Velho, ÔÇÿImage processing for computer Graphics-, Springer Verlag, New York, Inc, 1997.
[5] T. Vasudev and G. Hemanth Kumar and G. S. Guru and P. Nagabhushan, -Extension of seven-segment display concept for handwritten numeral recognition -A-simple projection approach-, National conference on document analysis and recognition, NCDAR, 2001 ,pp 57-60.
[6] Jacek, M Zurada, ÔÇÿIntroduction to Artificial Neural Network System-, Jaico Publishing house, third edition 1999.
[7] Alessandro Vinciarelli, -A survey on offline cursive word recogniton pattern recognition-, 2002, 35(7), pp1433-1446.
[8] Ahmed, S. M, et.al, ÔÇÿExperiments in character recognition to develop tools For an optical character recogntion system-, IEEE inc.1st National multi topic conf proc.nust ,rawalpindi,pakistan, nov.1995, 61-67.
[9] Alexandre lemieux,christian gagne & marc Parizeau, ÔÇÿGenetically Engineering of Handwriting Representations-, proc. of the international workshop on frontiers in handwriting Recognition (IWFHR),Nigagaraon- lake.August 2002, pp. 6-8.
[10] Bortolozzi, F., Britto Jr,. A Oliveira, L. S and Morita, M., ÔÇÿRecent Advances in handwriting Recognition-, umapada pal et al editors, Documnet Analysis, 2005, pp.1-31.
[11] Gader P. D., Forester B., Ganzberger M., A. Bilies,B Mitchell, M. Whalen, T Youeum ÔÇÿRecognition of handwritten digits using template & model matching. Pattern recognition- , 1991, 5(24):421-431.
[12] Govinda, V.K & Shivaprasad, A P, “Character recognition-a review, Pattern recognition", 1990, 23: pp. 671-683.
[13] Hebert Jean-Francois, Parizeau Marc & Nadia Ghazali, ÔÇÿA new fuzzy geometirc represenation for on-line isolated character recognition- , proc of 14th international conference on Pattern recognition, Brisbane, 1998, pp. 1121-1123.
[14] Mantas, J-An overview of character recognition Methodologies-, Pattern recognition, 1986, 19, pp 425-430.
[15] Suen C.Y., Berthod M., & Mori. S, ÔÇÿAutomatic Recognition of hand printed character-the state of art-, proceeding of IEEE.68, 1980, pp. 469- 487.
[16] Nouboud F., & Plamondon, ÔÇÿOnline Recognition of hand printed chracter: survey and beta tests, pattern recognition-, 1990, 23: pp. 1031- 1044.
[17] Plamondon Rejean, & Sargur N, Srihari, ÔÇÿOn line & off line handwriting recognition- A comprehensive survey IEEE Transactions on PAMI.22, 2000, pp.63-83.</p>
@article{"International Journal of Information, Control and Computer Sciences:62329", author = "Banashree N. P. and Andhe Dharani and R. Vasanta and P. S. Satyanarayana", title = "OCR for Script Identification of Hindi (Devnagari) Numerals using Error Diffusion Halftoning Algorithm with Neural Classifier ", abstract = "The applications on numbers are across-the-board that there is much scope for study. The chic of writing numbers is diverse and comes in a variety of form, size and fonts. Identification of Indian languages scripts is challenging problems. In Optical Character Recognition [OCR], machine printed or handwritten characters/numerals are recognized. There are plentiful approaches that deal with problem of detection of numerals/character depending on the sort of feature extracted and different way of extracting them. This paper proposes a recognition scheme for handwritten Hindi (devnagiri) numerals; most admired one in Indian subcontinent our work focused on a technique in feature extraction i.e. Local-based approach, a method using 16-segment display concept, which is extracted from halftoned images & Binary images of isolated numerals. These feature vectors are fed to neural classifier model that has been trained to recognize a Hindi numeral. The archetype of system has been tested on varieties of image of numerals. Experimentation result shows that recognition rate of halftoned images is 98 % compared to binary images (95%).
", keywords = "OCR, Halftoning, Neural classifier, 16-segmentdisplay concept.", volume = "1", number = "2", pages = "441-5", }
