Printed PAW recognition based on planar hidden Markov models

Author

Ben Amara, Najoua ; Belaid, Addel

Author_Institution

Ecole Nat. de Ingenieurs de Monastir, Tunisia

Volume

2

fYear

1996

fDate

25-29 Aug 1996

Firstpage

220

Abstract

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 poor and degraded texts

Keywords

hidden Markov models; image segmentation; optical character recognition; probability; connected Arabic printed text recognition; efficient superstate duration distribution; pieces of arabic word; planar hidden Markov models; recognition accuracy; statistical models; Hidden Markov models; Image segmentation; Optimized production technology; Peak to average power ratio; Plasma welding; Probability distribution; Tin; Topology; White spaces; Writing;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1996., Proceedings of the 13th International Conference on

Conference_Location

Vienna

ISSN

1051-4651

Print_ISBN

0-8186-7282-X

Type

conf

DOI

10.1109/ICPR.1996.546821

Filename

546821