Investigation of normalization techniques and their impact on a recognition rate in handwritten numeral recognition

• Autorzy: Chmielnicki W. , Stąpor K.
• Języki publikacji: EN

Abstrakty

EN

This paper presents several normalization techniques used in handwritten numeral recognition and their impact on recognition rates. Experiments with five different feature vectors based on geometric invariants, Zernike moments and gradient features are conducted. The recognition rates obtained using combination of these methods with gradient features and the SVM-rbf classifier are comparable to the best state-of-art techniques.

Słowa kluczowe

EN

handwritten numeral recognition; normalization techniques; SVM classifier; feature vectors; OCR; geometric invariants; Zernike moments; gradient features

• Wydawca: Wydawnictwo Uniwersytetu Jagiellońskiego
• Czasopismo: Schedae Informaticae
• Rocznik: 2010
• Tom: Vol. 19
• Strony: 53--77
• Opis fizyczny: Bibliogr. 66 poz., rys.

Twórcy

autor

Chmielnicki W.

autor

Stąpor K.

• Faculty of Physics, Astronomy and Applied Computer Science, Jagiellonian University, Reymonta 4, 30-059 Kraków,

Bibliografia

• [1] Xu D., Li H.; Geometric moment invariants, Pattern Recognition 41, 2008, pp. 240-249.
• [2] Liu Ch.L., Nakashima K., Sako H., Fujisava H.; Handwritten digit recognition: investigation of normalization and feature extraction techniques, Pattern Recognition 37, 2004, pp. 265-279.
• [3] Chang C.-C, Lin C.-J.; LIBSVM: a library for support vector machines, software available at: http://www.csie.ntu.edu.tw/~cjlin/libsvm, 2001.
• [4] Lauer F., Suen Ch.Y., Bloch G.; A trainable feature extractor for handwritten digit recognition, Pattern Recognition 40, 2007, pp. 1816-1824.
• [5] Zhang W., Tang Y.Y., Xue Y.; Handwritten Character Recognition Using Combined Gradient and Wavelet Feature, International Conference on Computational Intelligence and Security, Vol. 1, 2006, pp. 662-667.
• [6] Stąpor K.; Automatic object classification, Publishing House EXIT, 2005.
• [7] Tong X.J., Zeng S., Zhou K., Jiang Q.; Hand-written numeral recognition based on Zernike moment, Proceedings of the 2008 ICWAPR, pp. 368-372.
• [8] Teow L.-N., Loe K.-F.; Robust vision-based features and classification schemes for offline handwritten digit recognition, Pattern Recognition 35(11), 2002, pp. 2355-2364.
• [9] Liu H., Ding X.; Handwritten Character Recognition Using Gradient Feature and Quadratic Classifier with Multiple Discrimination Schemes, Proceedings of the Eighth ICDAR, 2005, pp. 19-25.
• [10] Shi M., Fujisava Y., Wakabayashi T., Kimura F.; Handwritten Numeral Recognition using gradient and curvature of gray scale image, Pattern Recognition 35(10), 2002, pp. 2051-2059.
• [11] Cristianini N., Scholkopf B.; Support vector machines and Kernel methods: the new generation of learning machines, AI Magazine 13(3), 2002, pp. 3-41.
• [12] Liu Ch.L., Nakashima K., Sako H., Fujisava H.; Handwritten digit recognition: benchmarking of state-of-the-art techniques, Pattern Recognition 36, 2003, pp. 2271-2285.
• [13] Shi M., Fujisawa Y., Wakabayashi T., Kimura F.; Handwritten numeral recognition using gradient and curvature of gray scale image, Pattern Recognition 35, 2002, pp. 2051-2059.
• [14] Scholkopf B., Smola A.J.; Learning with Kernels. Support Vector Machines, Regularization, Optimization, and Beyond, The MIT Press, 2001.
• [15] Cheriet M., Kharma N., Liu Ch.-L., Suen Ch.-Y.; Character Recognition Systems: A guide for students and practioners, Wiley-Interscience, 2007.
• [16] Suen Ch.Y., Nadal Ch., Legault R., Mai T.A., Lam L.; Computer Recognition of unconstrained handwritten numeral, Proceedings of the IEEE, 80, 1992, pp. 1162-1180.
• [17] Srikantan G., Lam S.W., SriHari S.N.; Gradient-based contour encoding for character recognition, Pattern Recognition 29, 1996, pp. 1147-1160.
• [18] Arica N., Yarmna-Vural F.T.; Optical Character Recognition for Cursive Handwriting, IEEE Transactions on Pattern Analysis and Machine Intelligence 23, 2002, pp. 801-813.
• [19] Liu C.-L., Nakashima K., Sako H., Fujisawa H.; Aspect Ratio adaptive normalization for handwritten character recognition, in: Advances in Multimodal Interfaces - ICMI 2000, T. Tan Y. Shi, W. Gao (eds.), Lecture Notes in Computer Science 1948, 2000, pp. 418-425.
• [20] Kimura et al.; Evaluation an synthesis of feature vectors for handwritten numeral recognition, IEICE Trans. Inform. Systems E79-D(5), 1996, pp. 436-442.
• [21] Heutte L., Paquet T., Moreau J.V., Lecourtier Y., Olivier C; A structural/ statistical feature based vector for handwritten character recognition, Pattern Recognition Letters 19(7), 1998, pp. 629-641
• [22] Jain A.K., Duin R.P.W., Mao J.; Statistical Pattern Recognition: a review, IEEE Transactions on Pattern Analysis and Machine Intelligence 22(1), 2000, pp. 4-37.
• [23] Burges C.J.C.; A tutorial on support vector machines for pattern recognition, Knowledge Discovery Data Mining 2(2), 1998, pp. 1-43.
• [24] Kimura F., Takashina K., Tsuruoka S., Miyake Y.; Modified quadratic discriminant functions and the application to Chinese character recognition, IEEE Trans. Pattern Anal. Mach. Intell. 9(1), 1987, pp. 149-153.
• [25] Vapnik V.; The Nature of Statistical Learning Theory, Springer, New York 1995.
• [26] Kimura F., Shridhar M.; Handwritten numeral recognition based on multiple algorithms, Pattern Recognition 24(10), 1991, pp. 969-981.
• [27] Liu C.-L., Sako H., Fujisawa H.; Performance evaluation of pattern classifiers for handwritten character recognition, International Journal on Document Analysis Recognition 4(3), 2002, pp. 191-204.
• [28] Lee D.-S., Srihari S.-N.; Handprinted digit recognition: a comparison of algorithms, Proceedings of the Third International Workshop on Frontiers of Handwriting Recognition, Buffalo, New York, 1993, pp. 153-164.
• [29] LeCun Y. et al.; Comparison of learning algorithms for handwritten digit recognition, in: Proceedings of the International Conference on Artificial Neural Networks, F. Fogelman-Soulie, P. Gallinari (eds.), Nanterre, France 1995, pp. 53-60.
• [30] Suen C.-Y., Liu K., Strathy N.W.; Sorting and recognizing cheques and financial documents, in: Document Analysis Systems: Theory and Practice, S.-W. Lee, Y. Nakano (eds.), Springer, Berlin 1999, pp. 173-187.
• [31] Liu C.-L., Nakagawa M.; Handwritten numeral recognition using neural networks: improving the accuracy by discriminative training, Proceedings of the Fifth International Conference on Document Analysis and Recognition, 1999, pp. 257-260.
• [32] Naggy G., Tuong N.; Normalization techniques for handprinted numerals, Communications of the ACM 13(8), 1970, pp. 475-481.
• [33] Franke J.; Isolated handprinted digit recognition, in: Handbook of Character Recognition and Document Image Analysis, H. Bunke, P.S.P. Wang (eds.), World Scientific, Singapore 1997, pp. 103-121.
• [34] Gader P.D., Khabou M.A.; Automatic feature generation for handwritten digit recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence 18(12), 1996, pp. 1256-1261.
• [35] Cai J.-H., Liu Z.-Q.; Integration of structural and statistical information for unconstrained handwritten numeral recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence 21(3), 1999, pp. 263-270.
• [36] Oh I.-S., Lee J.-S., Suen C.Y.; Analysis of class separation and combination of class-dependent features for handwriting recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence 21(10), 1999, pp. 1089-1094.
• [37] Mayraz G., Hinton G.E.; Recognizing handwritten digits using hierarchical products of experts, IEEE Transactions on Pattern Analysis and Machine Intelligence 24(2), 2002, pp. 189-197.
• [38] Dong J.X., Krzyzak A., Suen C.Y.; A multi-net learning framework for pattern recognition, Proceedings of the Sixth International Conference on Document Analysis and Recognition, Seattle 2001, pp. 328-332.
• [39] Belongie S., Malik J., Puzicha J.; Shape matching and object recognition using shape contexts, IEEE Transactions on Pattern Analysis and Machine Intelligence 24(4), 2002, pp. 509-522.
• [40] Gonzalez R.C., Woods R.E.; Digital Image Processing, 2nd edition, Addison Wesley, 2001.
• [41] Hull J.J.; Document image skew detection: Survey and annotated bibliography, in: Document Analysis Systems II, J.J. Hull and S.L. Taylor (eds.), World Scientific, Singapore, 1998, pp. 40-64.
• [42] Yamaguchi T., Nakano Y., Maruyama M., Miyao H., Hannoi T.; Digit classification on signboard for telephone number recognition, Proceedings of the 7th International Conference for Document Analysis and Recognition, Edinburgh, Scotland 2003, pp. 359-363.
• [43] Zhang T.Y., Suen C.Y.; A fast parallel algorithm for thinning digital patterns, Communication of the ACM 27(3), 1984, pp. 236-239.
• [44] Favata J.T., Srikantan G., Srihari S.N.; Handprinted character/digit recognition using a multiple feature/resolution philosophy, Proceedings of the Fourth International Workshop on Frontiers of Handwriting Recognition, Taipei 1994, pp. 57-66.
• [45] de Oliveira Jr. J.J., Veloso L.R., de Carvalho J.M.; Interpolation/decimation scheme applied to size normalization of characters images, Proceedings of the 15th International Conference Pattern Recognition, Vol. 2, Barcelona, Spain 2000, pp. 577-580.
• [46] Ramteke R.J., Mehrotra S.C.; Feature Extraction Based on Moment Invariants for Handwriting, IEEE Conference on Recognition Cybernetics and Intelligent Systems, Issue 7-9, 2006, pp. 1-6.
• [47] Cheng D., Yan H.; Recognition of handwritten digits based on contour information, Pattern Recognition 31(3), 1998, pp. 235-255.
• [48] Tong X.J., Zeng S., Zhou K., Zhao K., Jiang Q.; Hand-written numeral recognition based on Zernike moment, Proceedings of the 2008 International Conference on Wavelet Analysis and Pattern Recognition, Vol. 1, 2008, pp. 368-372.
• [49] Teague M.R.; Image analysis via the general theory of moments, Journal of the Optical Society of America 70(8), 1980, pp. 920-930.
• [50] Trier O.D., Jain A.K., Taxt T.; Feature extraction. Methods for character recognition - a survey, Pattern Recognition 29, 1996, pp. 641-662.
• [51] Kawamura A. et al.; On-line recognition of freely handwritten Japanese characters using directional feature densities, Proceedings of the 11th International Conference on Pattern Recognition, Vol. 2, The Hague 1992, pp. 183-186.
• [52] Mori S., Suen C.Y., Yamamoto K.; Historical review of OCR research and development, Proceedings of IEEE 80(7), 1992, pp. 1029-1053.
• [53] Khotanzad A., Hong Y.H.; Invariant image recognition by Zernike moments, IEEE Transactions on Pattern Analysis and Machine Intelligence 12(5), 1990, pp. 489-490.
• [54] Burges C.J.C.; A tutorial on support vector machines for pattern recognition. Knowledge Discovery Data Mining 2(2), 1998, pp. 1-43.
• [55] Gudessen A.; Quantitative Analysis of preprocessing techniques for the recognition of handprinted characters, Pattern Recognition 8, 1976, pp. 219-227.
• [56] Cristianini N., Shawe-Taylor J.; An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods, Cambridge University Press, 2000.
• [57] Labusch K, Barth E., Martinetz T.; Simple Method for High-Performance Digit Recognition Based on Sparse Coding, IEEE Transaction on Neural Networks 19(11), 2008, pp. 1985-1989.
• [58] Fan R.E., Chen P.H., Lin C.J.; Working Set Selection Using Second Order Information for Training Support Vector Machines, Journal of Machine Learning Research 6, 2005, pp. 1889-1918.
• [59] Keerthi S.S., Lin C.J.; Asymptotic behaviors of support vector machines with Gaussian kernel, Neural Computation 15(7), 2003, pp. 1667-1689.
• [60] Kernel machines web site, http://www.kernel-machines.orgA
• [61] The MNIST database of handwritten digits, http://yann.lecun.com/exdb/mnistA
• [62] Hsu C.W., Chang C.C., Lin C.J.; A practical guide to support vector classification, http ://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide. pdf.
• [63] Mukundan R., RamaKrishnan K.R.; Fast Computation of Legendre and Zernike Moments, Pattern Recognition 28(9), 1995, pp. 1433-1442.
• [64] Casey R.G.; Moment normalization of handprinted character, IBM Journal of Research and Development 14, 1970, pp. 548-557.
• [65] Lee S.-W.; Multilayer cluster neural network for totally unconstrained handwritten numeral recognition, Neural Networks 8(5), 1995, pp. 783-792.
• [66] Abuhaiba I.S.I., Holt M.J.J., Datta S.; Recognition of off-line handwriting, Computer Vision and Image Understanding 71, 1998, pp. 19-38.