This Article 
 Bibliographic References 
 Add to: 
Maximization of Mutual Information for Offline Thai Handwriting Recognition
August 2006 (vol. 28 no. 8)
pp. 1347-1351
This paper aims to improve the performance of an HMM-based offline Thai handwriting recognition system through discriminative training and the use of fine-tuned feature extraction methods. The discriminative training is implemented by maximizing the mutual information between the data and their classes. The feature extraction is based on our proposed block-based PCA and composite images, shown to be better at discriminating Thai confusable characters. We demonstrate significant improvements in recognition accuracies compared to the classifiers that are not discriminatively optimized.

[1] H. Nishimura, M. Kobayashi, M. Maruyama, and Y. Nakano, “Off-Line Character Recognition Using HMM by Multiple Directional Feature Extraction and Voting with Bagging Algorithm,” Proc. Fifth Int'l Conf. Document Analysis and Recognition, vol. 1, pp. 49-52, 1999.
[2] V.H. Quan, H. Kiem, P.N. Trung, L.T. Tin, N.D.H. Ha, and A.H. Nguyen, “A System for Recognizing Vietnamese Document Images Based on HMM and Linguistics,” Proc. Sixth Int'l Conf. Document Analysis and Recognition, pp. 627-630, 2001.
[3] P.C. Woodland and D. Povey, “Large Scale Discriminative Training of Hidden Markov Models for Speech Recognition,” Computer Speech and Language, vol. 16, no. 1, pp. 25-48, 2002.
[4] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-Based Learning Applied to Document Recognition,” Proc. IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
[5] S. Airphaiboon and S. Kondo, “Recognition of Handprinted Thai Characters Using Loop Structures,” IEICE Trans. Information and Systems, vol. E79-D, no. 9, pp. 1296-1303, 1996.
[6] P. Phokharatkul and C. Kimpan, “Handwritten Thai Character Recognition Using Fourier Descriptors and Genetic Neural Networks,” Proc. Fourth Symp. Natural Language Processing, pp. 108-123, 2000.
[7] J.L. Mitrpanont and S. Kiwprasopsak, “The Development of the Feature Extraction Algorithms for Thai Handwritten Character Recognition System,” Lecture Notes in Computer Science, vol. 2358, pp. 536-546, June 2002.
[8] L. Rabiner, “A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition,” Proc. IEEE, vol. 77, no. 2, pp. 257-286, 1989.
[9] D. Povey, “Discriminative Training for Large Vocabulary Speech Recognition,” PhD thesis, Univ. of Cambridge, U.K., July 2004.
[10] A. Biem, “Minimum Classification Error Training of Hidden Markov Models for Handwriting Recognition,” Proc. IEEE Int'l Conf. Acoustics, Speech, and Signal Processing, pp. 1529-1532, 2001.
[11] R. Schluter, “Investigations on Discriminative Training Criteria,” PhD thesis, RWTH Aachen, Germany, Sept. 2000.
[12] R. Nopsuwanchai, “Discriminative Training Methods and Their Applications to Handwriting Recognition,” PhD thesis, Univ. of Cambridge, U.K., Aug. 2004.
[13] S. Young, G. Evermann, T. Hain, D. Kershaw, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. Woodland, The HTK Book (for HTK Version 3.2). Cambridge, U.K.: Cambridge Univ. Eng. Dept., 2002.
[14] R. Nopsuwanchai and D. Povey, “Discriminative Training for HMM-Based Offline Handwritten Character Recognition,” Proc. Seventh Int'l Conf. Document Analysis and Recognition, vol. 1, pp. 114-118, 2003.
[15] J. Geist, R.A. Wilkinson, S. Janet, P.J. Grother, B. Hammond, N.W. Larsen, R.M. Klear, C.J.C. Burges, R. Creecy, J.J. Hull, T.P. Vogl, and C.L. Wilson, “The Second Census Optical Character Recognition Systems Conf.,” technical report, Nat'l Inst. of Standards and Technology, Maryland, June 1994.

Index Terms:
Character recognition, Hidden Markov Model, discriminative training, PCA, feature extraction, Thai handwriting recognition.
Roongroj Nopsuwanchai, Alain Biem, William F. Clocksin, "Maximization of Mutual Information for Offline Thai Handwriting Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 8, pp. 1347-1351, Aug. 2006, doi:10.1109/TPAMI.2006.167
Usage of this product signifies your acceptance of the Terms of Use.