Abstract
Hidden Markov Models (HMM) have now became the prevalent paradigm in automatic speech recognition. Only recently, several researchers in off-line handwriting recognition have tried to transpose the HMM technology to their field after realizing that word images could be assimilated to sequences of observations. HMM’s form a family of tools for modelling sequential processes in a statistical and generative manner. Their reputation is due to the results attained in speech recognition which derive mostly from the existence of automatic training techniques and the advantages of the probabilistic framework. This article first reviews the basic concepts of HMM’s. The second part is devoted to illustrative applications in the field of off- line handwriting recognition. We describe four different applications of HMM’s in various contexts and review some of the other approaches.
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
Rabiner, L.R., Juang, B.H.: An introduction to hidden Markov models, IEEE ASSP Magazine 3(1) (1986).
Poritz, A.B.: hidden Markov models: a guided tour, Proc. of the IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP’88), 7-13 (1988).
Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition, Proc. of the IEEE 77(2) 257–286 (1989).
Church, K.W.: A stochastic parts program and noun phrase parser for unrestricted text, Proc. of the Second Conf. on Applied Natural Language Processing, 136-143 (1988).
Derouault, M., Mérialdo, B.: Natural language modelling for phoneme-to-text transcription, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 8, 742–749 (1986).
Kuhn, R., De Mori, R.: A cache-based natural-language model for speech recognition, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. PAMI-12(6), 570–583 (1990).
Gilloux, M.: Automatic learning of word transducers from examples, Proc. of the 5th Conf. of the European Chapter of the Association for Compulation Linguistics (EACL’91), 107-112 (1991).
Vstovsky, G.V., Vstovskaya, A.V.: A class of hidden Markov models for images processing, Pattern Recognition Letters 14, 391–396 (1993).
Bellegarda, E.J., Bellegarda, J.R., Nahamoo, D., Nathan, K.S: On-line handwriting recognition based upon continuous parameter mixture densities, Proc. of the Third International Workshop on Frontiers in Handwriting Recognition (IWFHR-3), 225-234 (1993).
Bercu, S., Lorette, G.: On-line handwritten word recognition: an approach based on hidden Markov models, Proc. of the Third International Workshop on Frontiers in Handwriting Recognition (IWFHR-3), 385-390 (1993).
Bahl, L. R., F. Jelinek, and R. L. Mercer: A maximum likelihood approach to speech recognition, IEEE Trans. on Pattern Analysis and Machine Intelligence 5(2), 179–190 (1983).
Baum, L. E.: An inequality and associated maximization technique in statistical estimation of probabilistic functions of Markov processes, Inequalities 3, 1–8 (1972).
Kirkpatrick, S., Gelatt, C.D., Vecchi, M.P.: Optimization by simulated annealing, Science 220, 671-680 (1983).
Jouvet, D., Monné, J., Dubois, D.: A new network-based speaker independent connected-word speech recognition system, Proc. of the Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP86), 1109-1112 (1986).
Forney, G.D.: The Viterbi Algorithm, Proc. of the IEEE 61(3) (1973).
Bengio, Y., De Mori, R., Flammia, G., Kompe, R.: Global optimization of a neural network-hidden Markov model hybrid, IEEE Trans. on Neural Networks 3(2), 252–259 (1992).
Mérialdo, B.,: Phonetic recognition using hidden Markov models and maximum mutual information training, Proc. of the Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP’88), 111-114 (1988).
Bourlard, H. Wellekens, C.J.: Links between Markov models and multilayer pcrceptrons, IEEE Trans. on Pattern Analysis and Machine Intelligence 12(12), 1167–1178 (1990).
Bahl, L.R., Brown, P.F., de Souza, P.V., Mercer, R.L.: A new algorithm for the estimation of hidden Markov model parameters, Proc. of the Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP’88), 493-496 (1988).
Vapnik, V.N.: Estimation of dependencies based on empirical data, Springer-Verlag (1982).
Lang, K.J., Waibel, A.H., Hinton, G.E.: A Time delay Neural network architecture for isolated word recognition, Neural networks 3(1), 23–44 (1990).
Lee, K.F. Hon, H., Hwang, M., Mahajan, S., Reddy, R.: The SPHINX speech recognition system, Proc. of the IEEE Int. Conf. ASSP, 445-448 (1989).
Picone, J.: Continuous speech recognition using hidden Markov models, IEEE ASSP Magazine, 26-41 (1990).
Waibel, A., Lee, K.-F. (eds): Readings in speech recognition, Morgan Kaufmann (1990).
Levinson, E.S, Rabiner, L.R., Sondhi, M.M.: An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition, The Bell System Technical Journal 62(4), 1035–1074 (1983).
Schwartz, R., Austin, S.: A comparison of several approximate algorithms for finding multiple (N-best) sentence hypotheses, Proc. of the Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP’91), 701-704 (1991).
Chen, M.-Y. et al.: Off-line handwritten word recognition using hidden Markov model, Proc. of the 5th USPS Advanced Technology Conf., 563-577 (1992).
Tao, C.: A generalization of discrete hidden Markov model and of Viterbi algorithm. Pattern Recognition 25(11), 1381–1387 (1992).
Lari, K., Young, S.J.: The estimation of stochastic context-free grammars using the Insidc-Outside algorithm, Computer Speech and Language 4, 35–36, 1990.
Levinson, S. E., Continuously variable duration hidden Markov models for automatic speech recognition, Computer Speech and Language 1, 29–45 (1986).
Brugnara, F., et al.: A family of parallel hidden Markov models, Proc. of the Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP’92), 377-380 (1992).
Kundu, A., Bahl, P.: Recognition of handwritten script: a hidden Markov model based approach, Proc. of the Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP’88), 928-931 (1988).
Kundu, A., He Y., Bahl, P.: Recognition of handwritten word: first and second order hidden Markov model based approach. Pattern Recognition 22(3), 283–297 (1989).
Gillies, A. M.: Cursive word recognition using hidden Markov models, Proc. of the 5th USPS Advanced Technology Conf., 557-562 (1992).
Gilloux, M., Leroux, M.: Recognition of cursive script amounts on postal cheques, Proc. of the 5th USPS Advanced Technology Conf., 545-556 (1992).
Chen, M.-Y., Kundu, A., Srihari, S.N.: Unconstrained handwritten word recognition using continuous density variable duration hidden Markov model, Proc. of the IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP’93) (1993).
Park, H.S., Lee, S.-W.: Off-line recognition of large-set handwritten Hangul (Korean script) with hidden Markov models, Proc. of the Third International Workshop on Frontiers in Handwriting Recognition (IWFHR-3), 51-61 (1993).
Caesar, T., et al.: Recognition of handwritten word images by statistical methods, Proc. of the Third International Workshop on Frontiers in Handwriting Recognition (IWFHR-3), 409-416 (1993).
Chen, M.-Y., Kundu, A.: An alternative to variable duration HMM in handwritten word recognition, Proc. of the Third International Workshop on Frontiers in Handwriting Recognition (IWFHR-3), 82-91 (1993).
Gilloux, M., Bertille, J.-M., Leroux, M.: Recognition of handwritten words in a limited dynamic vocabulary, Proc. of the Third International Workshop on Frontiers in Handwriting Recognition (IWFHR-3), 417-422 (1993).
Ha, J.-Y., et al.: Unconstrained handwritten word recognition with interconnected hidden Markov models, Proc of the Third International Workshop on Frontiers in Handwriting Recognition (IWFHR-3), 455-460 (1993).
Bertille, J.-M., El Yacoubi, M.: Global cursive postal code recognition using hidden Markov models, Proc. of the 1st European Conf. on Postal Technologies (JetPoste’93), 129-138 (1993).
Leroux, M., Salomé, J.-C., Badard, J.: Recognition of cursive script words in a small lexicon, Proc. of the 1st International Conf. on Document Analysis and Recognition (ICDAR’91), 774-782 (1991).
Geman, S., Geman, D.: Stochastic relaxation, Gibbs distributions, and the bayesian restoration of images, IEEE Trans. on Pattern Analysis and Machine Intelligence 6, 721–741 (1984).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gilloux, M. (1994). Hidden Markov Models in Handwriting Recognition. In: Impedovo, S. (eds) Fundamentals in Handwriting Recognition. NATO ASI Series, vol 124. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-78646-4_15
Download citation
DOI: https://doi.org/10.1007/978-3-642-78646-4_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-78648-8
Online ISBN: 978-3-642-78646-4
eBook Packages: Springer Book Archive