Cover page and Table of Contents: PDF (size: 523KB)
Full Text (PDF, 523KB), PP.53-59
Views: 0 Downloads: 0
Character recognition, Malayalam, Gradient, Curvature, Principal Component Analysis, SVM, RBF
In this paper, we propose a handwritten character recognition system for Malayalam language. The feature extraction phase consists of gradient and curvature calculation and dimensionality reduction using Principal Component Analysis. Directional information from the arc tangent of gradient is used as gradient feature. Strength of gradient in curvature direction is used as the curvature feature. The proposed system uses a combination of gradient and curvature feature in reduced dimension as the feature vector. For classification, discriminative power of Support Vector Machine (SVM) is evaluated. The results reveal that SVM with Radial Basis Function (RBF) kernel yield the best performance with 96.28% and 97.96% of accuracy in two different datasets. This is the highest accuracy ever reported on these datasets.
Jomy John,Kannan Balakrishnan,Pramod K. V,"A System for Offline Recognition of Handwritten Characters in Malayalam Script", IJIGSP, vol.5, no.4, pp.53-59, 2013. DOI: 10.5815/ijigsp.2013.04.07
Plamondon, R. and S.N. Srihari, Online and off-line handwriting recognition: a comprehensive survey. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2000. 22(1): p. 63-84.
Govindaraju, V. and S. Setlur, Guide to OCR for Indic Scripts: Document Recognition and Retrieval. 2009: Springer Publishing Company, Incorporated. 325.
Ghosh, D., T. Dube, and A.P. Shivaprasad, Script Recognition;A Review. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2010. 32(12): p. 2142-2161.
Shi, M., et al., Handwritten numeral recognition using gradient and curvature of gray scale image. Pattern Recognition, 2002. 35(10): p. 2051-2059.
Jolliffe, I.T., Principal Component Analysis. 2002: Springer.
N, V.V., The Nature of Statistical Learning Theory, 1999, Springer, Information science and statistics: Berlin.
Liu C L, N.K., Sako H, Fujisawa H, Handwritten digit recognition: Benchmarking of state-of-the-art techniques. Pattern Recognition. 36(10): p. 2271-2285.
Bellili A, G.M., Gallinari P, An MLP-SVM combination architecture for offline handwritten digit recogniton:reduction of recogniton errors by support vector machine rejection mechanisms. International Journal of Document Analysis and Recogniton, 2003. 5: p. 244-252.
Shanthi, N. and K. Duraiswamy, A novel SVM-based handwritten Tamil character recognition system. Pattern Analysis and Applications, 2010. 13(2): p. 173-180.
Bhowmik T K, G.P., A. Roy, Parui S. K, SVM-based hierarchical architectures for handwritten Bangla character recognition. International Journal of Document Analysis and Recognition, 2009.
John, J., K.V. Pramod, and K. Balakrishnan, Unconstrained Handwritten Malayalam Character Recognition using Wavelet Transform and Support vector Machine Classifier. Procedia Engineering, 2012. 30(0): p. 598-605.
John, J., K.V. Pramod, and K. Balakrishnan. Offline handwritten Malayalam Character Recognition based on chain code histogram. in Emerging Trends in Electrical and Computer Technology (ICETECT), 2011 International Conference on. 2011.
Joseph, S., et al. Content based image retrieval system for Malayalam handwritten characters. in Electronics Computer Technology (ICECT), 2011 3rd International Conference on. 2011.
Chacko, B.P. and P.B. Anto, A Hybrid Learning Algorithm for Handwriting Recognition in Information Systems for Indian Languages, C. Singh, et al., Editors. 2011, Springer Berlin Heidelberg. p. 232-235.
Chacko, B.P. and A.P. Babu. Online sequential extreme learning machine based handwritten character recognition. in Students' Technology Symposium (TechSym), 2011 IEEE. 2011.
Moni, B.S. and G. Raju, Modified quadratic classifier and directional features for handwritten Malayalam character recognition. Int. J. Comput. Appl, 2011: p. 30-34.