Abstract
In this study we evaluate different HMM topologies in terms of recognition of handwritten numeral strings by considering the framework of the Level Building Algorithm (LBA). By including an end-state in a left-to-right HMM structure we observe a significant improvement in the string recognition performance since it provides a better definition of the segmentation cuts by the LBA. In addition, this end-state allows us the use of a two-step training mechanism with the objective of integrating handwriting-specific knowledge into the numeral models to obtain a more accurate representation of numeral strings. The contextual information regarding the interaction between adjacent numerals in strings (spaces, overlapping and touching) is modeled in a pause model built into the numeral HMMs. This has shown to be a promising approach even though it is really dependent on the training database.
This is a preview of subscription content, log in via an institution to check access.
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. and Juang B. H., Fundamentals of Speech Recognition. Prentice Hall, New Jersey, 1993
Cho W., Lee S. W., and Kim, J. H. Modeling and Recognition of Cursive Words with Hidden Markov Models, Pattern Recognition 1995; 28:1941–1953
Dolfing J. G. A. Handwriting recognition and verification: A hidden Markov approach. PhD. thesis, Eindhoven University of Technology, Netherlands, 1998
Britto A. S., Sabourin R., Lethelier E., Bortolozzi F., Suen C. Y. Improvement in handwritten numeral string recognition by slant normalization and contextual information. In: Proceedings of the 7th International Workshop on Frontiers of Handwriting Recognition (7th IWFHR), Netherlands, 2000, pp 323–332
Sabourin R., 1990. Une Approache de Type Compréhension de Scène Appliquée au Probleme de la Vérification Automatique de L’Identité par L’Image de la Signature Manuscrite. Thése de Doctorat, École Polytechnique, Université de Montréal, 1990
Mohamed M. and Gader P. Handwritten word recognition using segmentation-free hidden Markov modeling and segmentation-based dynamic programming techniques. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1996;18 548–554
Linde Y., Buzo A., and Gray R. M. An algorithm for Vector Quantizer Design. IEEE Transactions on Communications, 1980; COM-28: 84–95
Elms A. J., Procter S. and Illingworth J. The Advantage of using an HMM-bases Approach for Faxed Word Recognition. International Journal on Document Analysis and Recognition (IJDAR). 1998; 18–36
Procter S., Illingworth J. and Elms A. J., The recognition of handwritten digit strings of unknown length using hidden Markov models, In: Proceedings of the Fourteenth International Conference on Pattern Recognition, 1998, pp 1515–1517
Rabiner L. and Levinson L. A speak-independent, syntax-directed, connected word recognition system based on hidden Markov models and Level Building. Transactions on Acoustics, Speech, and Signal Processing, 1985;Vol. ASSP-33, N°. 3.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
de S. Britto, A., Sabourin, R., Bortolozzi, F., Suen, C.Y. (2001). An Enhanced HMM Topology in an LBA Framework for the Recognition of Handwritten Numeral Strings. In: Singh, S., Murshed, N., Kropatsch, W. (eds) Advances in Pattern Recognition — ICAPR 2001. ICAPR 2001. Lecture Notes in Computer Science, vol 2013. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44732-6_11
Download citation
DOI: https://doi.org/10.1007/3-540-44732-6_11
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41767-5
Online ISBN: 978-3-540-44732-0
eBook Packages: Springer Book Archive