Call for Paper - November 2022 Edition
IJCA solicits original research papers for the November 2022 Edition. Last date of manuscript submission is October 20, 2022. Read More

A Hybrid Model for Recognizing Handwritten Bangla Characters using Support Vector Machine

Print
PDF
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2017
Authors:
Shyla Afroge, Boshir Ahmed
10.5120/ijca2017915312

Shyla Afroge and Boshir Ahmed. A Hybrid Model for Recognizing Handwritten Bangla Characters using Support Vector Machine. International Journal of Computer Applications 174(1):41-46, September 2017. BibTeX

@article{10.5120/ijca2017915312,
	author = {Shyla Afroge and Boshir Ahmed},
	title = {A Hybrid Model for Recognizing Handwritten Bangla Characters using Support Vector Machine},
	journal = {International Journal of Computer Applications},
	issue_date = {September 2017},
	volume = {174},
	number = {1},
	month = {Sep},
	year = {2017},
	issn = {0975-8887},
	pages = {41-46},
	numpages = {6},
	url = {http://www.ijcaonline.org/archives/volume174/number1/28375-2017915312},
	doi = {10.5120/ijca2017915312},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}
}

Abstract

Considering the real time scenario, hand written bangla recognition getting a drastic part to the research community. Though various studies have been performed for Bengali handwritten recognition, but a robust model for Bangla Handwritten classification is still in practice. Therefore a hybrid model is presented in this paper, which intent to classify Bangla handwritten characters. The Proposed model combines Zernike moments, raw binary pixels and histogram of oriented gradients features for recognizing Bangla hand written characters which is feed to the Support Vector Machine classifier. It is observed that, the proposed model outsails existing models with smaller epochs. Proposed model is trained and test with “Bangla Lekha Isolated” dataset which consists of 30000 characters where 24,000 for training dataset and 6,000 for testing .This system shows 46.98% for Zernike Moments, 66.60% for Raw Binary Pixels and 87.62% for Histogram of Oriented Gradients where overall combined features achieve an accuracy of 94.88% in recognizing characters which achieves the best accuracy rate reported till date for this dataset.

References

  1. G. Kumar, P. K. Bhatia, “A Detailed Review of Feature Extraction in Image Processing System,” International Conference on Advanced Computing & Communication Technologies,2014.
  2. Burges, Christopher JC. “A tutorial on support vector machines for pattern recognition.” Data mining and knowledge discovery 2.2 (1998): 121-167.
  3. Mohammed, Nabeel; Momen, Sifat; Abedin, Anowarul; Biswas, Mithun; Islam, Rafiqul; Shom, Gautam; Shopon, Md. (2017), “BanglaLekha-Isolated”, Mendeley Data, v2.
  4. N. Das , B. Das, R. Sarkar, S. Basu, M. Kundu, M. Nasipuri, “Handwritten BanglaBasic and Compound character recognition using MLP and SVM classifier”, JOURNAL OF COMPUTING, VOLUME 2, ISSUE 2, FEBRUARY 2010, ISSN 2151-9617
  5. A.F.R. Rahman, R. Rahman, M.C. Fairhurst, “Recognition of Handwritten Bengali Characters: a Novel Multistage Approach,” Patttern Recognition, vol. 35, p.p. 997 1006, 2002.
  6. T. K. Bhowmik, U.Bhattacharya and S. K. Parui, “Recognition of Bangla Handwritten Characters Using an MLP Classifier Based on Stroke Features,” in Proc. ICONIP, Kolkata, India, p.p. 814-819, 2004.
  7. S.Basu, N.Das, R.Sarkar, M.Kundu, M.Nasipuri, D.K.Basu, “Handwritten Bangla Alphabet Recognition using an MLP Based Classifier,” in Proc. Of the 2nd National Conf. on Computer Processing of Bangla, pp. 285-291, Feb-2005, Dhaka
  8. S. Bhowmik, M.G. Roushan, R. Sarkar, M. Nasipuri, S. Polley, S. Malakar, “Handwritten Bangla Word Recognition using HOG Descriptor” , Fourth International Conference of Emerging Applications of Information Technology, 2014.
  9. G. Nagy,”At the frontiers of OCR”, IEEE 80, pp. 1093–1100 (1992).
  10. X. Tong, A. D. Evans, “A statistical approach to automatic OCR error correction in context”, In: Proceedings of WVLC, pp. 88–10 (1996).
  11. E. Francesconi, M. Gori, S. Marinai, G. Soda, “A serial combination of connectionist-based classifiers for OCR.” International Journal on document analysis and recognition, 3(3), pp. 160-168 (2001).
  12. H. Byun, W. S. Lee, “Applications of support vector machines for pattern recognition: a survey”. In: Proceedings of 1st International Workshop on Pattern Recognition with Support Vector Machines, pp. 213–236 (2002).
  13. H. Hse and A. Richard Newton, “Sketched Symbol Recognition using Zernike Moments” Department of Electrical Engineering and Computer Sciences University of California at Berkeley , CA 94720, U.S.A.
  14. Otsu, Nobuyuki. "A threshold selection method from gray-level histograms." IEEE transactions on systems, man, and cybernetics 9.1 (1979): 62-66
  15. Rownak, Ahnaf Farhan, et al. "An efficient way for segmentation of Bangla characters in printed document using curved scanning." Informatics, Electronics and Vision (ICIEV), 2016 5th International Conference on. IEEE, 2016.
  16. Dalal, Navneet, B. Triggs. "Histograms of oriented gradients for human detection." Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. Vol. 1. IEEE, 2005
  17. Khotanzad, Alireza, and Y. H. Hong. "Invariant image recognition by Zernike moments." IEEE Transactions on pattern analysis and machine intelligence 12.5 (1990): 489-497.
  18. Abu-Mostafa, Yaser S., and D. Psaltis. "Image normalization by complex moments." IEEE Transactions on Pattern Analysis and Machine Intelligence 1 (1985): 46-55.
  19. Hu, Ming-Kuei. "Visual pattern recognition by moment invariants." IRE transactions on information theory 8.2 (1962): 179-187.
  20. F. Zernike, Physica, vol. 1, p. 689, 1934
  21. Cortes, Corinna, and Vladimir Vapnik. "Support-vector networks." Machine learning 20.3 (1995): 273-297.
  22. Das, Nibaran, et al. "Handwritten Bangla basic and compound character recognition using MLP and SVM classifier." arXiv preprint arXiv: 1002. 4040 (2010).

Keywords

Hand written character recognition; Histogram of oriented gradients; Zernike moments; raw binary pixel ;support vector machine; Bangla OCR