Offline Handwritten Character Recognition is a very challenging field to work upon, as the handwriting of an individual differs very much from another individual, even the handwriting of an individual may differ on different times. Studies have shown that recognition efficiency of characters depends on the ways the features are extracted and formulated as the feature vector. A lot of techniques have been proposed by the various research scholars for feature extraction. In this paper, a combinational approach of feature extraction is proposed as combinational feature vectors (Gradient features, Zernike complex moment features, and Wave based features) may contribute to improved recognition rate. For training and testing purpose, samples of Hindi numerals from 0 to 9 are taken. A feature vector of directional gradient histogram (DGH), a feature vector of Zernike complex moments (ZCM) and a feature vector of Wave features (WF) are feed to the Back-propagation based Neural Network classifiers for training and recognition rate of approx. 79.7%, 92.7% and 73% are attained respectively. By combining the feature vectors DGH, CZM, and WF, a higher recognition rate of 96.4% is obtained for isolated Hindi Numerals.

Character Recognition, Gradient features, Zernike Moments, Wave features, Backpropagation Neural Network

[1] M.B. Mendapara and M.M. Goswami, “Stroke Identification in Gujarati Text using Directional Feature”, International Conference on Green Computing Communication and Electrical Engineering, IEEE 2014.
[2] Anitha Mary, M.O. Chacko and P.M. Dhanya, “A Comparative Study of Different Feature Extraction Techniques for Offline Malayalam Character Recognition”, International Conference on Computational Intelligence in Data Mining, Springer, Vol. 2, pp.9-18, 2014.
[3] Ravindra S. Hegadi and Parshuram M. Kamble, “Recognition of Marathi Handwritten Numerals Using Multi-layer Feed-Forward Neural Network”, World Congress on Computing and Communication Technologies, IEEE, pp. 21-24, 2014.
[4] Hetal R. Thaker and Dr C. K. Kumbharana, “Analysis of structural features and classification of Gujarati consonants for offline character recognition”, International Journal of Scientific and Research Publications, Vol. 4, Issue 8, pp. 1-5, August 2014.
[5] Muhammad Arif Mohamad, Dewi Nasien, Haswadi Hassan, Habibollah Haron, “A Review on Feature Extraction and Feature Selection for Handwritten Character Recognition”, International Journal of Advanced Computer Science and Applications, Vol. 6, No. 2, 2015.
[6] U. Pal, T. Wakabayashi, F. Kimura, “Comparative Study of Devnagari Handwritten Character Recognition using Different Feature and Classifiers”, IEEE, 10th International Conference on Document Analysis and Recognition, pp. 1111-1115, 2009.
[7] Sandhya Arora, Debotosh Bhattacharjee, Mita Nasipuri, Dipak Kumar Basu, Mahantapas Kundu, “Multiple Classifier Combination for Offline Handwritten Devanagari Character Recognition”, arxiv.org/pdf/1006.5913, pp. 01-06, June 2010.
[8] Xianjing Wang and Atul Sajjanhar, “Using a Circular grid for Offline Handwritten Character Recognition”, 4th International Congress on Image and Signal Processing, pp. 945-949, 2011.
[9] Ashutosh Aggarwal, Karamjeet Singh and Kamalpreet Singh, “Use of Gradient Technique for extracting features from Handwritten Gurumukhi Characters and Numerals”, International Conference of Information and Communication Technologies, Elsevier, pp. 1716-1723, 2014.
[10] Karbhari V. Kale, Prapti D. Deshmukh, Shriniwas V. Chavan, Majharoddin M. Kazi, Yogesh S. Rode, “Zernike Moment Feature Extraction for Handwritten Devanagari (Marathi) Compound Character Recognition”, International Journal of Advanced Research in Artificial Intelligence, Vol. 3, No.1, pp. 68-76, 2014.
[11] Kulkarni Sadanand A., Borde Prashant L., Manza Ramesh R., Yannawar Pravin L. “Offline MODI Character Recognition Using Complex Moments”, Second International Symposium on Computer Vision and the Internet (VisionNet’15), Procedia Computer Science -58 516–523, pp.516-523, 2015.
[12] Dayashankar Singh, Dr J.P. Saini and Prof. D.S. Chauhan, “Hindi Character Recognition Using RBF Neural Network and Directional Group Feature Extraction Technique”, International Conference on Cognitive Computing and Information Processing, IEEE 2015.
[13] Dayashankar Singh, Maitreyee Dutta and Sarvpal H. Singh, “Neural Network based Handwritten Hindi Character Recognition System”, 2nd Bangalore Annual Computer Conference, Article No. 15, ISBN 978-1-60558-476-8.
[14] Ajay Indian, Karamjit Bhatia, “Offline Handwritten Hindi ‘SWARs’ Recognition Using A Novel Wave Based Feature Extraction Method”, International Journal of Computer Science Issues, Volume 14, Issue 4, ISSN: 1694-0814, pp.08-14, July 2017.
[15] K. Radha Revathi1, A.N.L Kumar, Andey Krishnaji, “Neuro Recognizer: Neural Network Based Hand-Written Character Recognition”, International Journal of Computer Sciences and Engineering, E-ISSN: 2347-2693, Volume-3, Issue-9, pp.28-33, Sep.2015.
[16] Siddhartha Banerjee, Bibek Ranjan Ghosh, Arka Kundu, “Handwritten Character Recognition from Bank Cheque”, International Journal of Computer Sciences and Engineering, E-ISSN: 2347-2693, Vol.-4(1), pp.99-104, Feb 2016.
[17] Shen-Wei Lee and Hsien-Chu Wu, “Effective Multiple-features Extraction for Off-line SVM-Based Handwritten Numeral Recognition”, International Conference on Information Security and Intelligence Control, IEEE, pp. 194-197, 2012.
[18] G Raju, Bindu S Moni and Madhu S. Nair, "A Novel Handwritten Character Recognition System using Gradient-based Features and Run Length Count", Indian Academy of Sciences, Vol. 39, Issue 6, pp. 1333–1355, December 2014.
[19] L. Heutte, J. V. Moreau, T. Paquet, Y. Lecourtier, and C. Olivier, “Combining Structural and Statistical Features for the Recognition of Handwritten Characters,” Proceedings of 13th International Conference on Pattern Recognition, Vienna, Austria, Vol. 2, pp. 210-214, 1996.
[20] S. Arora, D. Bhattacharjee, M. Nasipuri, D. K. Basu and M. Kundu, "Combining multiple feature extraction techniques for handwritten Devanagari character recognition," IEEE Region 10 Colloquium and 3rd International Conference on Industrial and Information Systems, Dec. 2008.
[21] Y. Kimura, A. Suzuki, K. Odaka, “Feature Selection for Character Recognition using Genetic Algorithm,” IEEE Fourth International Conference on Innovative Computing, Information and Control (ICICIC), Kaohsiung , pp. 401-404, Dec. 2009.