Multilevel Classifiers in Recognition of Handwritten Kannada Numerals

Authors: Dinesh Acharya U., N. V. Subba Reddy, Krishnamoorthi Makkithaya

Abstract:

The recognition of handwritten numeral is an important area of research for its applications in post office, banks and other organizations. This paper presents automatic recognition of handwritten Kannada numerals based on structural features. Five different types of features, namely, profile based 10-segment string, water reservoir; vertical and horizontal strokes, end points and average boundary length from the minimal bounding box are used in the recognition of numeral. The effect of each feature and their combination in the numeral classification is analyzed using nearest neighbor classifiers. It is common to combine multiple categories of features into a single feature vector for the classification. Instead, separate classifiers can be used to classify based on each visual feature individually and the final classification can be obtained based on the combination of separate base classification results. One popular approach is to combine the classifier results into a feature vector and leaving the decision to next level classifier. This method is extended to extract a better information, possibility distribution, from the base classifiers in resolving the conflicts among the classification results. Here, we use fuzzy k Nearest Neighbor (fuzzy k-NN) as base classifier for individual feature sets, the results of which together forms the feature vector for the final k Nearest Neighbor (k-NN) classifier. Testing is done, using different features, individually and in combination, on a database containing 1600 samples of different numerals and the results are compared with the results of different existing methods.

Keywords: Fuzzy k Nearest Neighbor, Multiple Classifiers, Numeral Recognition, Structural features.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1055964

References:

[1] U. Pal,B B Chaudhuri, "Indain script character recognition: a survey", pattern Recognition 37, pp 1887-1899, 2004.
[2] Liu C. L., Nakashimga, K. Sako, H. Fujisasa, "Handwritten Digit Recognition: Benchmarking of the state-of-the-art techniques", Pattern Recognition 36, 2003, pp 2271-2285.
[3] Anil K Jain and Torfinn Taxt, "Feature Extraction Methods for Character Recognition: A Survey", Pattern Recognition, Vol 29, No, 4, 1996, pp 641- 662.
[4] Tuan A Mai and Ching Y Suen "A Generalized Knowledge based System for the Recognition of Unconstrained HandWritten Numerals", IEEE Trans. on Systems, Man and Cybernetics, vol. 20, no. 4, July / August 1990.
[5] Govindan V K, Shivaprasad A P, "Character Recognition - a review", Pattern Recognition 23,pp 671-683. 1990.
[6] Plamondon R, Srihari S N., " Online and Offline Handwriting Recognition: Comprehensive Survey", IEEE Trans. Pattern Anal. Machine Intell. PAMI 22,pp 63-84, 2000.
[7] U. Pal and P. P. Roy, "Multi-oriented and curved text lines extraction from Indian documents", IEEE Trans. on Systems, Man and Cybernetics - Part B, vol.34, pp.1676-1684, 2004.
[8] Leena lepistö, Iivari Kunttu,Jorma Autio and Ari Visa," Combining Classifiers in Rock Image Classification - Supervised and Unsupervised Approach", ICIAP 2005.
[9] J. M. Keller, M. R. Gray, and J. A. Givens, Jr., "A Fuzzy K-Nearest Neighbor Algorithm", IEEE Transactions on Systems, Man, and Cybernetics, Vol. 15, No. 4, pp. 580-585.
[10] R.O. Duda, P.E.Hart, and D.G. Stork, Pattern Classifica-tion, 2nd ed., John Wiley & Sons, New York, 2001.
[11] Dinesh Acharya U, N V Subba Reddy, Krishnamoorthy," Isolated Kannada Numeral Recognition using Structural Features and K-Means Cluster", Proc. of IISN 2007, pp. 125-129.
[12] G.G.Rajaput and Mallikarjun Hangarge, "Recognition of Isolated Handwritten Kannada Numeral Recognition Using Image Fusion Method-, PREMI07, LNCS 4815, pp 153-160.
[13] V N Manjunath Ardhya, G Hemanth Kumar and S Noushath, "Robust Unconstrained Handwritten Digit Recognition Using Radon Transform", IEEE-ICSN 2007, pp. 626-629.
[14] Rajashekaradhya S V and P Vanaja Ranjan, "Isolated Handwritten Kannada Digit Recognition: A Novel Approach", ICCR08, pp.134-140.
[15] Ganapatsingh G Rajput, "Unconstrained Kannada Handwritten Numeral Recognition based upon Image Reduction and KNN classifier", ICCR08, pp.11-16.
[16] N. Sharma, U. Pal, and F. Kimura, "Recognition of Handwritten Kannada Numerals", Proc, of IEEE-ICIT 2006.
[17] L. Lepistö, I. Kunttu, J. Autio, and A. Visa, "Classifica-tion of Nonhomogenous Textures by Combining Classi-fiers", Proceedings of IEEE ICIP, Vol. 1, 2003, pp. 981-984.
[18] J. Kittler, M. Hatef, R.P.W. Duin, and J. Matas, "On Combining Classifiers", IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 20, No. 3, March 1998, pp. 226-239.
[19] L. Xu, A. Krzyzak, and C. Y. Suen, "Methods for Com-bining Multiple Classifiers and their Applications to Handwriting Recognition", IEEE Trans. on Systems, Man, and Cybernetics, Vol. 22, No. 3, 1992, pp. 418- 435.
[20] A. K. Jain, S. Prabhakar, and S. Chen, "Combining Multi-ple Matchers for a High Security Fingerprint Verification System", Pattern Recognition Letters, Vol. 20, No. 11-13, Nov. 1999, pp. 1371-1379.
[21] L. Lam, C.Y. Suen, "Application of majority voting to pattern recognition: An analysis of the behavior and performance", IEEE Transactions on Systems, Man, and Cy-bernetics, vol. 27, No. 5, 1997, pp. 553-567.
[22] T. Vasudev, G Hemanthkumar,D S Guru and P Nagabhushan, "Extension of 7-segment display concept for Handwritten Numeral Recognition", Proc. of NCDAR, 200.1.
[23] P Nagabhushan and N V Subba Reddy, "A new approach to Handwritten Numeral Recognition", Austrian Pattern Recognition Society, 1996.
[24] U. Pal, B. B. Chowdhary, "Automatic Recognition of Unconstrained Offline Bangla Handwritten Numerals", LNCS, Vol.1948, Springer, 2000, pp 371- 378.
[25] U Bhattacharya T. K. Das, A. Datta, S. K. Parui, and B. B. Caudhri, "Recognition of Handprinted Bangla using Neural Network Models", LNAI 2275, 2002, pp 228-235.
[26] P. M. Patil, T. T. Sotakke, "Scale and Translation Invariant Handwritten Devanagaari Numeral Character Recognition using General Fuzzy Neural Networks", Pattern Recognition 40, 2007, pp 2110-2117.
[27] Zohn Yen, Reza Langari, "Fuzzy Logic Intelligence, Control, and Information", Pearson Education, 2003.