Handwritten Farsi(Arabic) word recognition: A holistic approach using discrete HMM

Pattern Recognition

Volumn 34, Issue 5, 2001, Pages 1057-1065

  Dehghan, M ^a   Faez, K ^a   Ahmadi, M ^b   Shridhar, M ^c  

^a AMIRKABIR UNIVERSITY OF TECHNOLOGY   (Iran)

^b UNIVERSITY OF WINDSOR   (Canada)

^c Department of Electrical and Computer Engineering   (United States)

Author keywords

Farsi Arabic handwritting recognition; Handwritten word recognition; Hidden Markov model; Parameter smoothing; Self organizing feature map

Indexed keywords

PATTERN RECOGNITION;

EID: 0035342519     PISSN: 00313203     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0031-3203(00)00051-0     Document Type: Article

References (11)

1. Variable duration hidden Markov and morphological segmentation for handwritten word recognition
2. HMM-KNN word recognition engine for bank cheque processing
3. An off-line cursive handwriting recognition system
4. A lexicon driven approach to handwritten word recognition for real-time applications
5. Off-line Arabic character recognition: The state of the art
6. Survey and bibliography of Arabic optical text recognition
7. A tutorial on hidden Markov models and selected applications in speech recognition
8. Threshold selection using Renyi's entropy
9. Algorithm for stroke width compensation of handwritten characters
10. Use of Kohonen self-organising feature maps for HMM parameter smoothing in speech recognition