Abstract
In this article, we propose an original hybrid CRF-HMM system for handwriting recognition. The main idea is to benefit from both the CRF discriminative ability and the HMM modeling ability. The CRF stage is devoted to the discrimination of low level frame representations, while the HMM performs a lexicon-driven word recognition. Low level frame representations are defined using \(n\)-gram codebooks and HOG descriptors. The system is trained and tested on the public handwritten word database RIMES.
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
Bengio, Y., LeCun, Y., LeRec, Y.: Ann/hmm hybrid for on-line handwriting recognition. Neural Computation 7(6), 1289–1303 (1995)
Gauvain, J., Lee, C.-H.: Maximum a posteriori estimation for multivariate gaussian mixture observations of markov chains. In: Speech and Audio Processing, pp. 291–298 (April 1994)
Graves, A., Liwicki, M., Fernandez, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A novel connectionist system for unconstrained handwriting recognition. PAMI, 855–868 (May 2009)
Graves, A., Fernández, S., Liwicki, M., Bunke, H., Schmidhuber, J.: Unconstrained online handwriting recognition with recurrent neural networks. In: NIPS (December 2007)
Grosicki, E., El Abed, H.: Icdar 2009 handwriting recognition competition. In: ICDAR (2009)
Gunawardana, A., Mahajan, M., Acero, A., Platt, J.C.: Hidden conditionnal random fields for phone classification. In: InterSpeech (2005)
Lafferty, J., McCallum, A., Pereira, F.C.N.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: ICML (June 2001)
Mohamed, A.-R., Dong, Y., Deng, L.: Investigation of full-sequence training of deep belief networks for speech recognition. In: InterSpeech (2010)
Morency, L.-P., Quattoni, A., Darrell, T.: Latten-dynamic discriminative models for continuous gesture recognition. In: CVPR (2007)
Nefian, A.V., Hayes III, M.H.: Maximum likelihood training of the embedded hmm for face detection and recognition. Image Processing 1, 33–36 (2000)
Quattoni, A., Collins, M., Darrel, T.: Conditional random fields for object recognition. In: NIPS (December 2005)
Rabiner, L.R.: A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE 77(2) (February 1989)
Rodriguez, J.A., Perronin, F.: Local gradient histogram features for word spotting in unconstrained handwritten documents. In: ICFHR (2008)
Shetty, S., Srinivasan, H.: Handwritten word recognition using conditional random fields. In: ICDAR, pp. 1098–1102 (September 2007)
Stephenson, T.A., Bourlard, H., Bengio, S., Morris, A.C.: Automatic speech recognition using dynamic bayesian networks with both acoustic and articulatory variables. In: ICSLP, vol. 2, pp. 951–954 (October 2000)
Sutton, C., McCallum, A.: Introduction to conditional random fields for relational learning. In: Introduction to Statistical Relational Learning, pp. 94–126 (2006)
Vinel, A., Do, T.M.T., Artieres, T.: Joint optimization of hidden conditional random fields and non linear feature extraction. In: ICDAR, pp. 513–517 (September 2011)
Zweig, G., Nguyen, P.: A segmental crf approach to large vocabulary continuous speech recognition. In: Automatic Speech Recognition & Understanding, pp. 152–157 (December 2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Bideault, G., Mioulet, L., Chatelain, C., Paquet, T. (2014). A Hybrid CRF/HMM Approach for Handwriting Recognition. In: Campilho, A., Kamel, M. (eds) Image Analysis and Recognition. ICIAR 2014. Lecture Notes in Computer Science(), vol 8814. Springer, Cham. https://doi.org/10.1007/978-3-319-11758-4_44
Download citation
DOI: https://doi.org/10.1007/978-3-319-11758-4_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11757-7
Online ISBN: 978-3-319-11758-4
eBook Packages: Computer ScienceComputer Science (R0)