The segmentation problem in Arabic Character Recognition the state of the art

• Main Author: Zeki, Ahmed M.
• Format: Conference or Workshop Item
• Language: English
• Published: 2005
• Subjects: Q Science (General); QA75 Electronic computers. Computer science
• Online Access: http://irep.iium.edu.my/31486/1/The_Segmentation_Problem.pdf; http://irep.iium.edu.my/31486/; http://dx.doi.org/10.1109/ICICT.2005.1598538
• Institution: Universiti Islam Antarabangsa Malaysia

Arabic characters are used in several languages other than Arabic, despite to this fact; Arabic Character Recognition (ACR) has not received enough interests by researchers. Little researchprogress has been achieved comparing to the one done on the Latin or Chinese and the solutions available in the market are still far from being perfect. However, recent years have shown a considerable increase in the number of research papers. The cursive nature of Arabic writing makes the process of recognition a very challenging one. Several methods to segment the Arabic words into characters have been proposed in the past two decades. This paper seeks to provide a comprehensive review of the methods proposed by researchers to segment. There is a room for research in this area; hence, the speech aims at promoting the research among Muslim researchers to work on ACR by addressing the challenges posed by the nature of the characters. The segmentation methods are categorized in nine different methods based on the techniques used. The advantages and drawback of each one are discussed.