Bengali printed character recognition using a feature based chain code method

Authors

  • Ankita Sikdar Department of Computer Science and Engineering, West Bengal University of Technology, Kolkata, West Bengal
  • Sreeparna Banerjee Department of Computer Science and Engineering, West Bengal University of Technology, Kolkata, West Bengal
  • Payal Roy Department of Computer Science and Engineering, West Bengal University of Technology, Kolkata, West Bengal
  • Somdeep Mukherjee Department of Computer Science and Engineering, West Bengal University of Technology, Kolkata, West Bengal
  • Moumita Das Department of Computer Science and Engineering, West Bengal University of Technology, Kolkata, West Bengal

DOI:

https://doi.org/10.14738/aivp.23.189

Keywords:

Bengali character recognition, feature identification, chain code technique

Abstract

 Bengali, one of the official languages of the Indian subcontinent, is composed of 50 alphabets, of which 11 are vowels and 39 consonants. In addition, Bengali words are formed from compound characters and modifiers. Compound characters are formed by combining parts of single characters and modifiers are parts of vowels and consonants which make sense only when adjacent to or attached with a letter. In this paper, features of Bengali characters are studied using a hierarchical structure. The first few layers deal with features that broadly classify the characters into small size groups. The lower level features are more specific to each character within a group. Higher level features can be identified based on pixel density and arrangement, while the lower level features have been identified using a chain code technique. The algorithm progresses successively through each group in the hierarchy until it finds a match with the input character.

References

. Mohammed Jasim Uddin, Mohammed Towhidul Islam and Md. Abdus Sattar, Recognition of Printed Bangla Characters Using Graph Theory, National Conference on Computer and Information System-NCCIS, Dec 9-10, 1997, Dhaka, Bangladesh

. Chaudhuri, B. B., Pal, U.: A Complete Printed Bangla OCR System. Pattern Recognition, Vol. 31. (1998) 531-549

. Ujjwal Bhattacharya, Malayappan Shridhar, and Swapan K.Parui. On recognition of handwritten bangla characters. In ICVGIP, pages 817- 828, 2006.

. J.U. Mahmud, M.F. Raihan and C.M. Rahman, “A Complete OCR System for continuous Bengali Character”,TENCON 2003, Conference on Convergent Technologies for Asia-Pacific Region, 15-17 Oct. 2003

. Dewi Nasien, Habibollah Haron, Siti Sophiayati Yuhaniz, “The Heuristic Extraction Algorithms for Freeman Chain Code of Handwritten Character”, International Journal of Experimental Algorithms-IJEA, Vol. 1, Issue 1, pages 1-20.

. Trier, O. D., Jain, A. K. and Taxt, T.: Feature Extraction Methods for Character Recognition - A Survey. Pattern Recognition, Vol. 29 (1996) 641 - 662

. Otsu, N.: A Threshold Selection Method from Grey-Level Histograms. IEEE Trans.Systems, Man, and Cybernetics, Vol. 9 (1979) 377-393

. Freeman, H.: Computer processing of Line-drawing Images ACM Computing Surveys, Vol. 6 (1974) 57-97

. Sikdar A., Roy P., Mukherjee S., Das M. and Banerjee S., A Feature Based Chain Code Method for Identifying Printed Bengali Characters, (2012) Proceedings, SIPM 2012, 89-96.

Downloads

Published

2014-06-30

How to Cite

Sikdar, A., Banerjee, S., Roy, P., Mukherjee, S., & Das, M. (2014). Bengali printed character recognition using a feature based chain code method. European Journal of Applied Sciences, 2(3), 01–09. https://doi.org/10.14738/aivp.23.189