Printed PAW Recognition Based on Planar Hidden Markov Models

Najoua Ben Amara (1) , Abdel Belaïd (2)

1 ENIM - École Nationale d’Ingénieurs de Monastir
2 READ - READ

In this paper, we present an approach for connected Arabic printed text recognition using statistical models based on Planar Hidden Markov Models (PHMM), without prior segmentation. The performance is enhanced by the use of robust features and an efficient superstate duration distribution. The approach has been tested on a vocabulary of 11 kinds of Pieces of Arabic Word (PAW) of three characters each. The experiments have shown promising results and directions for further improvements. The recognition accuracy has proved to be of 100% even with poorly and degraded texts.

Mots clés: hidden Markov models; image segmentation; optical character recognition; probability

Domaines: Bibliothèque électronique [cs.DL]

Najoua Ben Amara, Abdel Belaïd. Printed PAW Recognition Based on Planar Hidden Markov Models. 13th International Conference on Pattern Recognition - ICPR'96, Aug 1996, Vienna, Austria. pp.220-224, ⟨10.1109/ICPR.1996.546821⟩. ⟨inria-00534080⟩