Arabic handwritten words recognition based on a planar hidden markov model
Joint Authors
Bin Imarah, Najwa
Touj, Samih
Amiri, Hamid
Source
The International Arab Journal of Information Technology
Issue
Vol. 2, Issue 4 (31 Oct. 2005), pp.318-325, 8 p.
Publisher
Publication Date
2005-10-31
Country of Publication
Jordan
No. of Pages
8
Main Subjects
Information Technology and Computer Science
Topics
Abstract EN
Off-line recognition of handwritten words is a difficult task due to the high variability and uncertainty of human writing.
The majority of the recent systems are constrained by the size of the lexicon to deal with and the number of writers.
In this paper, we propose an approach for multi-writers Arabic handwritten words recognition.
The developed method uses multiple sources of information at the description and the classification levels.
A hybrid planar Markovien modeling permitting to follow the horizontal and vertical variations of the writing has been adopted.
This modeling is based on different levels of segmentation : horizontal, natural and vertical.
The process of segmentation conducts to the decomposition of the writing in a limited set of elementary entities, with simplified morphologies specific to every horizontal band.
The choice of different type of primitives is then imposed in order to assure an efficient description.
Different architectures of modeling proved also to be indispensable.
The classification is finally achieved using a Planar Hidden Markov Model.
American Psychological Association (APA)
Touj, Samih& Bin Imarah, Najwa& Amiri, Hamid. 2005. Arabic handwritten words recognition based on a planar hidden markov model. The International Arab Journal of Information Technology،Vol. 2, no. 4, pp.318-325.
https://search.emarefa.net/detail/BIM-12308
Modern Language Association (MLA)
Touj, Samih…[et al.]. Arabic handwritten words recognition based on a planar hidden markov model. The International Arab Journal of Information Technology Vol. 2, no. 4 (Oct. 2005), pp.318-325.
https://search.emarefa.net/detail/BIM-12308
American Medical Association (AMA)
Touj, Samih& Bin Imarah, Najwa& Amiri, Hamid. Arabic handwritten words recognition based on a planar hidden markov model. The International Arab Journal of Information Technology. 2005. Vol. 2, no. 4, pp.318-325.
https://search.emarefa.net/detail/BIM-12308
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 324-325
Record ID
BIM-12308