Abstract

The multi-font and multi-lingual handwritten numerals recognition has been a demanding requirement in this decade. This research work proposes multi-lingual handwritten numerals recognition using partial derivatives for classifying handwritten numerals of five major Indian languages. The objective of the proposed work aims at designing and developing a recognition algorithm for multilingual handwritten numerals. This objective is achieved through data collection and preprocessing which involves creation of handwritten numeral databases, data collection, round off mean aspect ratio value based representation and identification of features using partial derivatives. The features derived from partial derivatives are stored in a five dimensional column vector which yielded a recognition rate of 94.80, 95.89, 96.44, 95.81 and 92.03%, respectively for Kannada, Gurumukhi, Sindhi, Malayalam and Tamil Handwritten Numerals respectively.

Keywords:

Binary numeral image, feature identification, multi-lingual handwritten numeral recognition, representation, single linkage clustering and distance metric,

References

1. Al-Omari, F., 2001. Handwritten Indian numeral recognition system using template matching approaches. Proceeding of the ACS/IEEE International Conference on Computer Systems and Applications. Beirut, pp: 83-88.
   CrossRef    
2. Baheti, M.J. and K.V. Kale, 2013. Recognition of Gujarati numerals using hybrid approach and neural networks. Proceeding of International Conference on Recent Trends in Engineering and Technology (ICRTET, 2013), 5: 12-17.
   
3. Bhattacharya, U. and B.B. Chaudhuri, 2009. Handwritten numeral databases of Indian scripts and multistage recognition of mixed numerals. IEEE T. Pattern Anal., 31(3): 444-455.
   CrossRef    PMid:19147874    
4. Chen, M.W. and M.H. Ng, 1999. Recognition of Unconstrained Handwritten Numerals Using Crossing Features. Proceeding of the 15th International Symposium on Signal Processing and Its Applications (ISSPA '99), 1: 283-288.
   CrossRef    
5. Elnagar, A., F. Al-Kharousi and S. Harous, 1997. Recognition of handwritten Hindi numerals using structural descriptors. Proceeding of the IEEE International Conference on Systems, Man and Cybernetics, Computational Cybernetics and Simulation. Orlando, FL, 2: 983-988.
   CrossRef    
6. Hossain, M.Z., M.A. Amin and Y. Hong, 2011. Rapid feature extraction for Bangla handwritten digit recognition. Proceeding of the International Conference on Machine Learning and Cybernatics (ICMLC, 2011). Guilin, 4: 1832-1837.
   CrossRef    
7. Impedovo, S., M.G. Lucchese and G. Pirlo, 2006. Optimal zoning design by genetic algorithms. IEEE T. Syst. Man Cyb., 36(5): 833-846.
   CrossRef    
8. Kartar, S.S., D. Renu and R. Rajneesh, 2011. Handwritten Gurmukhi numeral recognition using different feature sets. Int. J. Comput. Appl., 29(2): 20-24.
   
9. Majhi, B., J. Satpathy and M. Rout, 2011. Efficient Recognition of Odiya Numerals using Low complexity neural classifier. Proceeding of the International Conference on Energy, Automation and Signal (ICEAS, 2011), pp: 140-143.
   CrossRef    
10. Mamatha, H.R., K.S. Murthy, A.V. Veeksha, P.S. Vokuda and M. Lakshmi, 2011. Recognition of handwritten kannada numerals using directional features and K-means. Proceeding of the International Conference on Computational Intelligence and Communication Network (CICN, 2011). Gwalior, pp: 644-647.
    
11. Medhi, K. and S.K. Kalita, 2014. Recognition of assamese handwritten numerals using mathematical morphology. Proceeding of the IEEE International Advance Computing Conference (IACC, 2014). Gurgaon, pp: 1076-1080.
    CrossRef    
12. Mowlaei, A., K. Faez and A.T. Haghighat, 2002. Feature extraction with wavelet transform for recognition of isolated handwritten Farsi/Arabic characters and numerals. Proceeding of the 14th International Conference on Digital Signal Processing (DSP, 2002), 2: 923-926.
    
13. Mozaffari, S., K. Faez and M. Ziaratban, 2005. Structural decomposition and statistical description of Farsi/Arabic handwritten numeric characters. Proceeding of the 8th International Conference on Document Analysis and Recognition, 1: 237-241.
    CrossRef    
14. Pirlo, G. and D. Impedovo, 2012. Voronoi-based zoning design by multi-objective genetic optimization. Proceeding of the 10th IAPR International Workshop on Document Analysis Systems (DAS). Gold Cost, QLD, pp: 220-224.
    CrossRef    
15. Plamondon, R. and S.N. Srihari, 2000. Online and off-line handwriting recognition: A comprehensive survey. IEEE T. Pattern Anal., 22(1): 63-84.
    CrossRef    
16. Purkait, P. and B. Chanda, 2010. Off-line recognition of hand-written Bengali numerals using morphological features. Proceeding of the 12th International Conference on Frontiers in Handwriting Recognition. Kolkata, India, pp: 363-368.
    CrossRef    
17. Rajashekararadhya, S.V. and P.V. Ranjan, 2009. Support vector machine based handwritten numeral recognition of Kannada script. Proceeding of the IEEE International Advance Computing Conference, pp: 381-386.
    CrossRef    
18. Reddy, G.S., P. Sharma, S.R.M. Prasanna, C. Mahanta and L.N. Sharma, 2012. Combined online and offline assamese handwritten numeral recognizer. Proceeding of the National Conference on Communications (NCC, 2012). Kharagpur, pp: 1-5.
    CrossRef    
19. Roy, A., N. Mazumder, N. Das, R. Sarkar, S. Basu and M. Nasipuri, 2012. A new quad tree based feature set for recognition of handwritten Bangla numerals. Proceeding of the IEEE International Conference on Engineering Education: Innovative Practices Future Trends (AICERA, 2012). Kottayam, pp: 1-6.
    CrossRef    
20. Sabaei, M. and K. Faez, 1997. Unsupervised classification of handwritten Farsi numerals using evolution strategies. Proceeding of IEEE Region 10 Annual Conference. Speech and Image Technologies for Computing and Telecommunications (TENCON '97). Brisbane, Qld., Australia, 1: 403-406.
    CrossRef    
21. Sanossian, H., 1998. Feature extraction technique for Hindi numerals. Proceedings of the IEEE Signal Processing Society Workshop Neural Networks for Signal Processing VIII. Cambridge, pp: 524-530.
    CrossRef    
22. Sung-Bae, C., 1996. Recognition of unconstrained handwritten numerals by doubly self-organizing neural network. Proceeding of the 13th International Conference on Pattern Recognition, 4: 426-430.
    CrossRef    
23. Tappert, C.C., C.Y. Suen and T. Wakahara, 1990. The state of the art in online handwriting recognition. IEEE T. Pattern Anal., 12(8): 787-808.
    CrossRef    
24. Zhang, P., L. Chen and A.C. Kot, 2000. A floating feature detector for handwritten numeral recognition. Proceeding of the 15th International Conference on Pattern Recognition. Barcelona, 2: 553-556.
    CrossRef    
25. Zhang, P., T.D. Bui and C.Y. Suen, 2004. Extraction of hybrid complex wavelet features for the verification of handwritten numerals. Proceeding of 9th International Workshop on Frontiers in Handwritten Recognition, pp: 347-352.
    CrossRef    

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.