CFP last date
22 April 2024
Reseach Article

A Comparative Study on Efficiency of Classification Techniques with Zone Level Gabor Features towards Handwritten Telugu Character Recognition

by N. Shobha Rani, Vasudev T.
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 148 - Number 1
Year of Publication: 2016
Authors: N. Shobha Rani, Vasudev T.
10.5120/ijca2016910991

N. Shobha Rani, Vasudev T. . A Comparative Study on Efficiency of Classification Techniques with Zone Level Gabor Features towards Handwritten Telugu Character Recognition. International Journal of Computer Applications. 148, 1 ( Aug 2016), 28-38. DOI=10.5120/ijca2016910991

@article{ 10.5120/ijca2016910991,
author = { N. Shobha Rani, Vasudev T. },
title = { A Comparative Study on Efficiency of Classification Techniques with Zone Level Gabor Features towards Handwritten Telugu Character Recognition },
journal = { International Journal of Computer Applications },
issue_date = { Aug 2016 },
volume = { 148 },
number = { 1 },
month = { Aug },
year = { 2016 },
issn = { 0975-8887 },
pages = { 28-38 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume148/number1/25723-2016910991/ },
doi = { 10.5120/ijca2016910991 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T23:52:09.705911+05:30
%A N. Shobha Rani
%A Vasudev T.
%T A Comparative Study on Efficiency of Classification Techniques with Zone Level Gabor Features towards Handwritten Telugu Character Recognition
%J International Journal of Computer Applications
%@ 0975-8887
%V 148
%N 1
%P 28-38
%D 2016
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Achieving high accuracies in recognition of handwritten text is a challenging research problem and never exhausting. The factors that instill challenges in handwritten character recognition include high degree of variability in writing, script type and the type of documents etc. In this paper, we focus on recognition of handwritten Telugu text commonly found in document images. The character set include all the vowels, consonants and single level vowel consonant clusters chosen in accordance with the commonly used terminology employed in composition pre-printed documents such as admission forms. In this paper, an algorithm is devised that performs zone-based feature extraction of the segmented character images. In the proposed work, the Gabor features are extracted from the character image at zone level and its efficiency is evaluated individually on two different zone representations and entire image at various scales and orientations. The classification and recognition performance is analyzed using nearest neighbor classifier, Naïve Bayesian, multi-class SVM and probabilistic neural networks classifiers. The efficiency of the classifiers are also tested with statistical, Histogram of Gradients and Hu moments’ feature extraction methods and the best accuracy of the system is found to be 84.8% for Gabor features with zone representation 2 and with multi-class SVM classifier.

References
  1. L. Heutte, T. Paquet, J.V. Moreau, Y. Leocourtier, C. Olivier, “ A structural/statistical feature based vector for handwritten character recognition”, Pattern Recognition letters, Vol. 19, issue 7, pp. 629-641, 1998.
  2. Seong-Whan Lee, “Direct extraction of topographic features for gray scale character recognition”, IEEE transactions on pattern analysis and machine intelligence, Vol. 17, Issue 7, pp. 724-728, 1995.
  3. Chao kan, Mandyam D. Srinath, “Invariant character recognition with Zernike and orthogonal Fourier-Mellin moments”, Pattern recognition, Vol. 35, Issue 1, pp. 143-154, 2002.
  4. L. Wang, “ Direct gray scale extraction of features for character recognition”, IEEE transactions on pattern analysis and machine intelligence, Vol. 15, Issue 10, pp. 1053-1067, 2002.
  5. Anil K. Jain, Torfinn Taxt, “ Feature extraction methods for character recognition- A Survey”, Pattern Recognition, Vol. 29, Issue 4, pp. 641-662, 1996.
  6. Rajashekararadhya, S.V. Ranjan, P. vanaja, “ Efficient zone-bsed feature extraction algorithm for handwritten numeral recognition of four popular South Indian scripts”, Journal of theoretical and information technology, Vol. 4, Issue 12, pp. 1171-1181, 2008.
  7. John T. Favata, Geetha Srikantan, “A multiple feature/Resolution approach to hand printed digit and character recognition”, International journal of imaging systems and technology, Vol. 7, pp. 304-311, 1996.
  8. George S, Kapogiannopoulos, “Character recognition using a bi-orthogonal discrete wavelet transform”, Proc. SPIE , Wavelet Applications in Signal and Image Processing IV, Vol. 2825, 1996.
  9. Pritpal Singh, Sumit Budhiraja, “ Feature extraction and classification techniques in OCR systems for Handwritten Gurumukhi script-A survey”, International journal of engineering, research and applications, Vol. 1, Issue 4, pp. 1736-1739, 2011.
  10. Sumedha B. Hallale, Geeta D. Salunke, “Twelve directional feature extraction for handwritten English character recognition”, International Journal of Recent Technology and Engineering (IJRTE), Volume-2, Issue-2, pp. 39-42, 2013.
  11. Gita Sinha, Rajneesh Rani and Renu Dhir. “Handwritten Gurmukhi numeral recognition using zone-based hybrid feature extraction techniques”. International Journal of Computer Applications 47(21):24-29, June 2012.
  12. Sandeep Saha, Nabarag Paul, Sayam Kumar Das, sandip Kundu, “Optical Character Recognition using 40-point feature extraction and artificial neural network” International Journal of Advanced Research in Computer Science and Software Engineering”, Volume 3, Issue 4, pp. 495-502, April 2013.
  13. Raju Dara, Urmila Panduga, “Telugu Handwritten Isolated Characters Recognition using Two Dimensional Fast Fourier Transform and Support Vector Machine”, International Journal of Computer Applications, Vol. 116, No. 5,pp. 7-11, 2015.
  14. C. Vikram, C. Shoba Bindu, C. Sasikala, “Handwritten Character Recognition for Telugu Scripts Using Multi Layer Perceptrons (MLP)”, International Journal of Advanced Research in Computer Engineering & Technology (IJARCET), Vol. 2, No. 12, pp. 3105-3110, 2013.
  15. Ram Mohan Rao, B.Ramesh, G.Indrasena Reddy, “Font and Size Identification in Telugu Printed Document”, International Journal of Engineering Research and Development, Vol. 6, No. 11. 2013, PP. 92-110.
  16. K. Vijay Kumar R.Rajeshwara Rao, “Improvement in Efficiency of Recognition of Handwritten Telugu script”, International Journal of Inventive Engineering and Sciences (IJIES), Vol.-2, No. 1, pp. 1-4, 2013.
  17. Samit Kumar Pradhan, “A syntactic PR approach to Telugu handwritten character recognition”, Proceeding of the workshop on Document Analysis and Recognition, pp. 147-153, ACM, 2012.
  18. Dan E. Willard,”New trie data structures which supports very fast search operations”, Journal of computer and system sciences, Vol. 28, issue 3, pp.379-394, 1984.
  19. B.V. Dhandra, R.G. Benne, Mallikarjun Hangarge, “Kannada, Telugu and Devanagari Handwritten Numeral recognition with Probabilistic Neural Network: A Script Independent Approach”, International
  20. Panyam Narahari Sastry, Ramakrishnan Krishnan, Bhagavatula Venkata Sanker Ram, “Classification and identification of telugu handwritten characters extracted from palm leaves using decision tree approach”, ARPN Journal of Engineering and Applied Sciences ,Vol. 5, No. 3, pp. 22-32, 2010.
  21. Andrés, Javier de., “Statistical techniques vs. SEES algorithm: an application to a small business environment”, 2001.
  22. Venkat Rasagna, K. J. Jinesh, C. V. Jawahar, “On Multifont Character Classification in Telugu”, International Institute of Information Technology, Hyderabad, INDIA.
  23. Nusaibath C, Ameera Mol P M, “Off-line Handwritten Malayalam Character Recognition Using Gabor Filters”, International Journal of Computer Trends and Technology (IJCTT), Vol. 4 No. 8, pp. 2476-2479, 2013.
  24. Xuewen Wang , Xiaoqing Ding, Changsong Liu, “Gabor filters-based feature extraction for character recognition”, Pattern Recognition, Vol. 38, No. 3, pp. 369–379, 2005.
  25. C. L. Liu ; Central Res. Lab., Hitachi Ltd., Kokubunji, Japan ; M. Koga ; H. Fujisawa, “Gabor feature extraction for character recognition: comparison with gradient feature”, International conference on Document Analysis and Recognition, Vol. 1, pp. 121 – 125, 2005.
  26. Xuewen Wang, Xiaoqing Ding, Changsong Liu, “Optimized Gabor filter based feature extraction for character recognition”, International Conference on Pattern Recognition, IEEE, Vol. 4, pp. 223-226, 2002.
  27. Jin Chen, Huaigu Cao, Rohit Prasad, Anurag Bhardwaj, Prem Natarajan, “Gabor Features for Offline Arabic Handwriting Recognition”, Workshop on Document Analysis and Systems, 2010.
  28. Liu, C., Wechsler, H., “Independent component analysis of Gabor features for face recognition”, IEEE transactions on Neural Networks, Vol. 14, issue 4, pp.919-928, 2003.
  29. Chacko, B.P., Krishnan, V.V., Raju, G., Anto, P.B., “Handwritten character recognition using wavelet energy and extreme learning machine”, International Journal of Machine Learning and Cybernetics, Vol. 3, issue 2, pp.149-161, 2012.
  30. Cash, G.L., Hatamian, M., “Optical character recognition by the method of moments”, Computer Vision, Graphics, and Image Processing, Vol. 39, issue 3, pp.291-310, 1987.
  31. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P., “Gradient-based learning applied to document recognition”, Proceedings of the IEEE, Vol. 86, issue 11, pp.2278-2324, 1998.
  32. Tan, Hin-Leong., “Hybrid feature-based and template matching optical character recognition system”, U.S. Patent No. 5,077,805, 31 Dec. 1991.
  33. P.B. Pati, S. Sabari Raju, N. Pati, A. G. Ramakrishnan, “Gabor filters for document analysis in Indian bilingual documents”, International Conference on Intelligent Sensing and Information Processing, pp. 123-126, 2004.
  34. Jonathan Alon, Vassilis Athitsos, and Stan Sclaroff, “Online and Offline Character Recognition Using Alignment to Prototypes”, International Conference on Document Analysis and Recognition (ICDAR), 2005.
  35. Chih-Wei Hsu, Chih-Jen Lin,” A Comparison of Methods for Multi-class Support Vector Machines”, IEEE Transactions on Neural Networks, Vol.13(2), pp. 415-425, 2002.
  36. Sabine Barrat, Salvatore Tabbone, Patrick Nourrissier ,”A Bayesian classifier for symbol recognition”, Workshop on Graphics Recognition - GREC, 2007.
  37. Richard D. Romero, David S. Touretzky, Robert H. Thibadeau, “Optical Chinese character recognition using probabilistic neural networks”, Pattern Recognition, Vol. 30, Issue 8, pp. 1279-1292, 1997 .
  38. Vincent Labatut, Hocine Cherifi, “Accuracy measures for comparision of classifiers”, International conference on information technology, arXiv:1207.3790, 2011.
  39. Newell, Andrew J., Lewis D. Griffin, “Multiscale histogram of oriented gradient descriptors for robust character recognition”, In 2011 International Conference on Document Analysis and Recognition, pp. 1085-1089, IEEE, 2011.
  40. Davis, James W., Aaron F. Bobick, “The representation and recognition of human movement using temporal templates”, In Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on, pp. 928-934, IEEE, 1997.
Index Terms

Computer Science
Information Sciences

Keywords

Handwritten Telugu text Character recognition Gabor feature Multi-class SVM Naïve Bayesian classifier nearest neighbor.