Semi-continuous HMMs with explicit state duration for unconstrained Arabic word modeling and recognition

  • Authors:

  • A. Benouareth;A. Ennaji;M. Sellami

  • Affiliations:

  • Laboratoire de Recherche en Informatique, Département d'Informatique, Université Badji Mokhtar, Annaba, BP, 12, 23000 Sidi Amar, Algeria;Laboratoire LITIS, INSA de ROUEN, Université de Rouen, Madrillet 76800, SER, France;Laboratoire de Recherche en Informatique, Département d'Informatique, Université Badji Mokhtar, Annaba, BP, 12, 23000 Sidi Amar, Algeria

  • Venue:
  • Pattern Recognition Letters
  • Year:
  • 2008

Quantified Score

Hi-index 0.10

Visualization

Abstract

In this paper, we describe an off-line unconstrained handwritten Arabic word recognition system based on segmentation-free approach and semi-continuous hidden Markov models (SCHMMs) with explicit state duration. Character durations play a significant part in the recognition of cursive handwriting. The duration information is still mostly disregarded in HMM-based automatic cursive handwriting recognizers due to the fact that HMMs are deficient in modeling character durations properly. We will show experimentally that explicit state duration modeling in the SCHMM framework can significantly improve the discriminating capacity of the SCHMMs to deal with very difficult pattern recognition tasks such as unconstrained handwritten Arabic recognition. In order to carry out the letter and word model training and recognition more efficiently, we propose a new version of the Viterbi algorithm taking into account explicit state duration modeling. Three distributions (Gamma, Gauss and Poisson) for the explicit state duration modeling have been used and a comparison between them has been reported. To perform word recognition, the described system uses an original sliding window approach based on vertical projection histogram analysis of the word and extracts a new pertinent set of statistical and structural features from the word image. Several experiments have been performed using the IFN/ENIT benchmark database and the best recognition performances achieved by our system outperform those reported recently on the same database.