Abstract
A new scheme for the optimization of codebook sizes for HMMs and the generation of HMM ensembles is proposed in this paper. In a discrete HMM, the vector quantization procedure and the generated codebook are associated with performance degradation. By using a selected clustering validity index, we show that the optimization of HMM codebook size can be selected without training HMM classifiers. Moreover, the proposed scheme yields multiple optimized HMM classifiers, and each individual HMM is based on a different codebook size. By using these to construct an ensemble of HMM classifiers, this scheme can compensate for the degradation of a discrete HMM.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Arica, N., Vural, F.T.Y.: A shape descriptor based on circular Hidden Markov Model. In: 15th Intl. Conf. on Pattern Recognition (ICPR00) (2000)
Bandyopadhyay, S., Maulik, U.: Non-parametric Genetic Clustering: Comparison of Validity Indices. IEEE Transactions on Systems, Man and Cybernetics Part-C 31(1), 120–125 (2001)
Bengio, Y.: Markovian Models for Sequential Data. Neural Computing Surveys 2, 129–162 (1999)
Britto Jr., A.: A Two-Stage HMM-Based Method for Recognizing Handwritten Numeral Strings. Ph.D. Thesis, Pontifical Catholic University of Paraná (2001)
Britto, A.S., et al.: Recognition of Handwritten Numeral Strings Using a Two-Stage Hmm-Based Method. International Journal on Document Analysis and Recognition (IJDAR) 5(2-3), 102–117 (2003)
Dietterich, T.G.: Machine Learning for Sequential Data: A Review. In: Caelli, T.M., et al. (eds.) SPR 2002 and SSPR 2002. LNCS, vol. 2396, pp. 15–30. Springer, Heidelberg (2002)
Eppstein, D.: Fast hierarchical clustering and other applications of dynamic closest pairs. In: Proceedings of the Ninth ACM-SIAM Symposium on Discrete Algorithms, pp. 619–628 (1998)
Guenter, S., Bunke, H.: Off-line cursive handwriting recognition using multiple classifier systems - on the influence of vocabulary, ensemble, and training set size. Optics and Lasers in Engineering 43, 437–454 (2005)
Guenter, S., Bunke, H.: Ensembles of classifiers derived from multiple prototypes and their application to handwriting recognition. In: Roli, F., Kittler, J., Windeatt, T. (eds.) MCS 2004. LNCS, vol. 3077, pp. 314–323. Springer, Heidelberg (2004)
Guenter, S., Bunke, H.: Off-line Cursive Handwriting Recognition - On the Influence of Training Set and Vocabulary Size in Multiple Classifier Systems. In: Proceedings of the 11th Conference of the International Graphonomics Society (2003)
Guenter, S., Bunke, H.: A new combination scheme for HMM-based classifiers and its application to handwriting recognition. In: Proc. 16th Int. Conference on Pattern Recognition, vol. II, pp. 332–337 (2002)
Bunke, H., Günter, S.: Generating Classifier Ensembles from Multiple Prototypes and Its Application to Handwriting Recognition. In: Roli, F., Kittler, J. (eds.) MCS 2002. LNCS, vol. 2364, pp. 179–188. Springer, Heidelberg (2002)
Guenter, S., Bunke, H.: Creation of classifier ensembles for handwritten word recognition using feature selection algorithms. In: Proc. 8th Int. Workshop on Frontiers in Handwriting Recognition, pp. 183–188 (2002)
Guenter, S., Bunke, H.: Ensembles of Classifiers for Handwritten Word Recognition. International Journal of Document Analysis and Recognition 5(4), 224–232 (2003)
Guenter, S., Bunke, H.: New Boosting Algorithms for Classification Problems with Large Number of Classes Applied to a Handwritten Word Recognition Task. In: Windeatt, T., Roli, F. (eds.) MCS 2003. LNCS, vol. 2709, pp. 326–335. Springer, Heidelberg (2003)
Bunke, H., Günter, S.: Fast Feature Selection in an HMM-Based Multiple Classifier System for Handwriting Recognition. In: Michaelis, B., Krell, G. (eds.) DAGM 2003. LNCS, vol. 2781, pp. 289–296. Springer, Heidelberg (2003)
Guenter, S., Bunke, H.: Optimization of weights in a multiple classifier handwritten word recognition system using a genetic algorithm. Electronic Letters of Computer Vision and Image Analysis 3(1), 25–44 (2004)
Halkidi, M., Batistakis, Y., Vazirgiannis, M.: On Clustering Validation Techniques. Journal of Intelligent Information Systems 17(2-3) (2001)
Halkidi, M., Batistakis, Y., Vazirgiannis, M.: Clustering Validity Checking Methods: Part II. SIGMOD Record 31(3), 19–27 (2002)
Huang, X., Acero, A., Hon, H.: Spoken Language Processing - a guide to theory, algorithm, and system development. Prentice Hall PTR, Englewood Cliffs (2001)
Kargupta, H., Johnson, E.L.: Collective, Hierarchical Clustering from Distributed, Heterogeneous Data. In: Zaki, M.J., Ho, C.-T. (eds.) KDD 1999. LNCS (LNAI), vol. 1759, pp. 221–244. Springer, Heidelberg (2000)
Kittler, J., et al.: On Combining Classifiers. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(3), 226–239 (1998)
Ko, A., Sabourin, R., Britto, J.A.: Combining Diversity and Classification Accuracy for Ensemble Selection in Random Subspaces. In: IEEE World Congress on Computational Intelligence (WCCI 2006) - International Joint Conference on Neural Networks (IJCNN 2006) (2006)
Ko, A., Sabourin, R., Britto, J.A.: Evolving Ensemble of Classifiers in Random Subspace. In: Genetic and Evolutionary Computation Conference (GECCO 2006) (2006)
Kuncheva, L.I., Skurichina, M., Duin, R.P.W.: An Experimental Study on Diversity for Bagging and Boosting with Linear Classifiers. International Journal of Information Fusion 3(2), 245–258 (2002)
Maulik, U., Bandyopadhyay, S.: Performance Evaluation of Some Clustering Algorithms and Validity Indices. IEEE Trans. Pattern Anal. Mach. Intell 24(12), 1650–1654 (2002)
Pakhira, M.K., Bandyopadhyay, S., Maulik, U.: Validity index for crisp and fuzzy clusters. Pattern Recognition 37(3), 487–501 (2004)
Pekalska, E., Skurichina, M., Duin, R.P.W.: Combining Dissimilarity-Based One-Class Classifiers. In: Roli, F., Kittler, J., Windeatt, T. (eds.) MCS 2004. LNCS, vol. 3077, pp. 122–133. Springer, Heidelberg (2004)
Rabiner, L.R.: A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Proceedings of the IEEE 77(2), 257–286 (1989)
Rabiner, L.R., Juang, B.H.: Fundamentals of Speech Recognition. Prentice-Hall, Englewood Cliffs (1993)
Ruta, D., Gabrys, B.: Classifier Selection for Majority Voting. International Journal of Information Fusion, 63–81 (2005)
Seo, J., Shneiderman, B.: Interactively Exploring Hierarchical Clustering Results. IEEE Computer 35(7), 80–86 (2002)
Shipp, C.A., Kuncheva, L.I.: Relationships between combination methods and measures of diversity in combining classifiers. International Journal of Information Fusion 3(2), 135–148 (2002)
Smyth, P., Heckerman, D., Jordan, M.I.: Probabilistic independence networks for hidden Markov probability models. Neural Computation 9, 227–269 (1997)
Wang, X.: Durationally constrained training of HMM without explicit state durational. Proceedings of the Institute of Phonetic Sciences 18, 111–130 (1994)
Xie, X.L., Beni, G.: A validity measure for fuzzy clustering. IEEE Transactions of Pattern Analysis and Machine Intelligence, 841–847 (1991)
Xu, L., Krzyzak, A., Suen, C.Y.: Methods of combining multiple classifiers and their applications to handwriting recognition. IEEE Transactions on Systems, Man and Cybernetics 22(3), 418–435 (1992)
Xu, L., Krzyzak, A., Suen, C.Y.: Methods of combining multiple classifiers and their applications to handwriting recognition. IEEE Transactions on Systems, Man and Cybernetics 22(3), 418–435 (1992)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Ko, A.HR., Sabourin, R., de Souza Britto, A. (2007). A New HMM-Based Ensemble Generation Method for Numeral Recognition. In: Haindl, M., Kittler, J., Roli, F. (eds) Multiple Classifier Systems. MCS 2007. Lecture Notes in Computer Science, vol 4472. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-72523-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-540-72523-7_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-72481-0
Online ISBN: 978-3-540-72523-7
eBook Packages: Computer ScienceComputer Science (R0)