95 articles 

inria-00108306, version 1

Online Arabic Handwriting Recognition Using Hidden Markov Models

Fadi Biadsy () 1, Jihad El-Sana () 2, Nizar Habash () 3

Tenth International Workshop on Frontiers in Handwriting Recognition (2006)

Abstract: Online handwriting recognition of Arabic script is a difficult problem since it is naturally both cursive and unconstrained. The analysis of Arabic script is further complicated in comparison to Latin script due to obligatory dots/stokes that are placed above or below most letters. This paper introduces a Hidden Markov Model (HMM) based system to provide solutions for most of the difficulties inherent in recognizing Arabic script including: letter connectivity, position-dependent letter shaping, and delayed strokes. This is the first HMM-based solution to online Arabic handwriting recognition. We report successful results for writerdependent and writer-independent word recognition.

  • 1:  Department of Computer Science [New York]
  • Columbia University
  • 2:  Department of Computer Science
  • Ben-Gurion University of the Negev
  • 3:  Center for Computational Learning Systems (CCLS)
  • Columbia University
  • Domain : Computer Science/Document and Text Processing
    Computer Science/Computer Vision and Pattern Recognition
  • Keywords : Online Handwriting Recognition – Arabic – HMM
  • Comment : http://www.suvisoft.com
  • inria-00108306, version 1
  • oai:hal.inria.fr:inria-00108306
  • From: 
  • Submitted on: Friday, 20 October 2006 13:22:52
  • Updated on: Friday, 20 October 2006 13:31:20