Accurate recognition of optical handwritten numeral is still an open and demanding problem in present digital world. The basic objective of the present work is to develop a novel method for recognition of off line unconstrained handwritten Odia numeral using curvature feature and functional link artificial neural network (FLANN) based cat swarm optimization (CSO) technique. In this paper preprocessing and feature extraction steps are carried out before the recognition of numerals. For feature extraction curvature based approach is applied. For recognition of handwritten Odia numeral hybrid architecture has been proposed where the classification task is performed by FLANN classifier and cat swarm optimization is used for finding a suitable set of weights for the FLANN classifier. The proposed model is evaluated on database consisting of 4000 number of handwritten Odia numerals. The combined effect of curvature based feature extraction approach and FLANN based cat swarm optimization technique yielded a high accuracy which exhibits the effectiveness of CSO based FLANN optimization model (FLANN-CSO) for recognition of Odia handwritten numerals.

Odia numeral recognition, FLANN, CSO, Preprocessing, Feature extraction, classification

[1] M. Shia, Y. Fujisawab, T. Wakabayashia, F. Kimuraa, “Handwritten numeral recognition using gradient and curvature of gray scale image,” Journal of Pattern Recognition, Vol. 35, pp. 2051 – 2059, 2002
[2] A. Desai, “Gujarati handwritten numeral optical character reorganization through neural network” , The Journal of Pattern Recognition, Vol. 43, pp. 2582–2589, 2010.
[3] S. Mahmoud, “Recognition of writer-independent off-line handwritten arabic (indian) numerals using hidden Markov models,” Journal of Signal Processing, Vol. 88, pp. 844–857, 2008.
[4] Z. Kamranian, S.A. Monadjemi and N. Nematbakhsh, “A novel free format persian/arabic handwritten zip code recognition system,” Journal of Computers and Electrical Engineering, Vol. 39, pp:1970–1979, 2013.
[5] B. Majhi, J. Satpathy and M. Rout, “Efficient recognition of odia numerals using low complexity neural classifier,” In Proceedings of IEEE International Conference on Energy, Automation and Signal , pp. 140-143, 2011.
[6] T.K.Mishra, B. Majhi, S. Panda, “A comparative analysis of image transformations for handwritten Odia numeral recognition,” In Proceedings of IEEE International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2013, pp. 790-793.
[7] Prashant M. Kakde, S. M. Gulhane, “ A comparative analysis pf particle swarm optimization and support vector machines for Devnagri character recognition: An android application”, Procedia Computer Science, Proceedings of International conference on communication, computing and virtualization (ICCCV) 2016, volume 79, 2016, Pages 337-343
[8] Alejandro Baldominos , Yago Saez, Pedro Isasi, Evolutionary convolutional neural networks: An application to handwritten recognition”, Neuro Computing, Volume 283, 29 March 2018, Pages 38-52
[9] Adarsh Trivedi, Siddhant Srivastava, Aproova Mishra, Anupam Shukla, Ritu Tiwari,” Hybrid evolutionary approach for Devanagari handwritten numeral recognition using convolutional neural network”, Procedia Computer Science, Volume 125, 2018, Pages 525-532
[10] Joseph Tarigan, Nadia, Ryanda Diedan, Yaya Suryana, “ Plate recognition using backpropagation neural network and genetic algorithm”, Procedia Computer Science, Volume 116, 2017, Pages 365-372

[11] W-D Weng, C-S Yang and R-C Lin, A channel equalizer using reduced decision feedback Chebyshev functional link artificial neural networks, Information Sciences, Elsevier, vol.177, issue 13, pp.2642-2654, July 2007. (FLANN)
[12] B. Naik, J. Nayak and H. S. Behera, A global-best harmony search based gradient descent learning FLANN (GbHS-GDL-FLANN) for data classification, Egyptian Informatics Journal, Elsevier,21 October 2015(In press). (FLANN)
[13] C.M.Anish and B. Majhi, Hybrid nonlinear adaptive scheme for stock market prediction using feedback FLANN and factor analysis, Journal of the Korean Statistical Society, July 2015 (in press). (FLANN)
[14] R. Majhi, G. Panda and G. Sahoo, Development and performance evaluation of FLANN based model for forecasting of stock markets, Expert Systems with Applications, Elsevier, vol.36, pp. 6800-6808, June 2012. (FLANN)
[15] B. Majhi and P. K. Sa, FLANN-based adaptive threshold selection for detection of impulsive noise in images, AEU- International Journal of Electronics and Communications, Elsevier, vol. 61, issue 7, pp.478-484, July 2007. (FLANN)
[16] J. C. Patra and A. Bos, Modelling of an intelligent pressure sensor using functional link artificial neural networks, ISA transactions, Elsevier, vol.39, issue 1, pp.15-17, February 2000. (FLANN)
[17] S. K. Behera, D. P. Das and B. Subudhi, Functional link artificial neural network applied to active noise control of a mixture of tonal and chaotic noise, Applied soft computing, Elsevier, vol. 23, pp. 51-60, October 2014. (FLANN)
[18] Chu, S.-C., & Tsai,P.-W, Computational intelligence based on the behavior of cats. International journal of innovative computing, Information and control, 3, pp.163-173
[19] G. Panda, P.M.Prahan, B. Majhi, IIR system identification using cat swarm optimization, Expert system with applications, 38(2011), pp.12671-12683
[20] A.D. Parkins, A.K. Nandiembers, “Genetic programming techniques for hand written digit recognition”, Signal Processing, Volume 84, Issue 12, pp: 2345-2365, December 2004.
[21] Moayad Yousif Potrus, Umi Kalthum Ngah, Bestoun S. Ahmed, “An evolutionary harmony search algorithm with dominant point detection for recognition-based segmentation of online Arabic text recognition”, Ain Shams Engineering Journal, Volume 5, Issue 4, pp. 1129-1139, December 2014.
[22] Saurabh Shrivastava, Manu Pratap Singh, “Performance evaluation of feed-forward neural network with soft computing techniques for hand written English alphabets”, Applied Soft Computing, Volume 11, Issue 1, pp: 1156-1182, January 2011.
[23] C. De Stefano, F. Fontanella, C. Marrocco, A. Scotto di Freca, “A GA-based feature selection approach with an application to handwritten character recognition”, Pattern Recognition Letters, Volume 35, Pages 130-141, 1 January 2014
[24] M. Kherallah, F. Bouri, A.M. Alimi, “On-line Arabic handwriting recognition system based on visual encoding and genetic algorithm”, Engineering Applications of Artificial Intelligence, Volume 22, Issue 1, pp: 153-170, February 2009.