Neural network based segmentation algorithm for Arabic characters recognition
Author
Source
Journal of Babylon University : Journal of Applied and Pure Sciences
Issue
Vol. 19, Issue 3 (30 Sep. 2011), pp.823-828, 6 p.
Publisher
Publication Date
2011-09-30
Country of Publication
Iraq
No. of Pages
6
Main Subjects
Information Technology and Computer Science
Library Sciences
Topics
Abstract EN
This paper presents a novel holistic technique for classifying Arabic handwritten text documents, which it is performed in several steps.
First, the Arabic handwritten document images are segmented into their connected parts.
A simple heuristic segmentation algorithm is used which finds segmentation points in printed and cursive handwritten words.
Second, several features are extracted from these connected parts and then combined to represent a word with one consolidated feature vector.
Finally, Neocognitron type of the neural network is used to learn and classify the different fonts into word classes.
American Psychological Association (APA)
Rashid, Nada A.. 2011. Neural network based segmentation algorithm for Arabic characters recognition. Journal of Babylon University : Journal of Applied and Pure Sciences،Vol. 19, no. 3, pp.823-828.
https://search.emarefa.net/detail/BIM-287934
Modern Language Association (MLA)
Rashid, Nada A.. Neural network based segmentation algorithm for Arabic characters recognition. Journal of Babylon University : Journal of Applied and Pure Sciences Vol. 19, no. 3 (2011), pp.823-828.
https://search.emarefa.net/detail/BIM-287934
American Medical Association (AMA)
Rashid, Nada A.. Neural network based segmentation algorithm for Arabic characters recognition. Journal of Babylon University : Journal of Applied and Pure Sciences. 2011. Vol. 19, no. 3, pp.823-828.
https://search.emarefa.net/detail/BIM-287934
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 828
Record ID
BIM-287934