An HMM-based approach for off-line unconstrained handwritten word modeling and recognition

1 January 1999

journal article
research article
Published by Institute of Electrical and Electronics Engineers (IEEE)

Vol. 21 (8) , 752-760
https://doi.org/10.1109/34.784288

Abstract

This paper describes a hidden Markov model-based approach designed to recognize off-line unconstrained handwritten words for large vocabularies. After preprocessing, a word image is segmented into letters or pseudoletters and represented by two feature sequences of equal length, each consisting of an alternating sequence of shape-symbols and segmentation-symbols, which are both explicitly modeled. The word model is made up of the concatenation of appropriate letter models consisting of elementary HMMs and an HMM-based interpolation technique is used to optimally combine the two feature sets. Two rejection mechanisms are considered depending on whether or not the word image is guaranteed to belong to the lexicon. Experiments carried out on real-life data show that the proposed approach can be successfully used for handwritten word recognition.

Keywords

This publication has 20 references indexed in Scilit:

Script recognition using hidden Markov models
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2005
Improvements of a lexicon directed algorithm for recognition of unconstrained handwritten words
Published by Institute of Electrical and Electronics Engineers (IEEE) ,2002
Modeling and recognition of cursive words with hidden Markov models
Pattern Recognition, 1995
Off-line cursive handwriting recognition using hidden markov models
Pattern Recognition, 1995
Strategies for cursive script recognition using hidden Markov models
Machine Vision and Applications, 1995
RECOGNITION OF UNCONSTRAINED HANDWRITTEN ENGLISH WORDS WITH CHARACTER AND LIGATURE MODELING
International Journal of Pattern Recognition and Artificial Intelligence, 1995
Variable duration hidden Markov model and morphological segmentation for handwritten word recognition
IEEE Transactions on Image Processing, 1995
Off-line handwritten word recognition using a hidden Markov model type stochastic network
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1994
Continuous speech recognition using hidden Markov models
IEEE ASSP Magazine, 1990
Off-line cursive script word recognition
Published by Institute of Electrical and Electronics Engineers (IEEE) ,1989