Designing an Arabic Handwritten Segmentation System

  • Mohamed E. M. Musa Sudan University of Science and Technology. Khartoum, Sudan,
  • Bodoor A. Bashir Sudan University of Science and Technology. Khartoum, Sudan,
  • Mohamed N. I. Ismail College of Science, King Faisal University, Al-Ahsa, Saudi Arabia
Keywords: Arabic pattern recognition, word segmentation, morphological features.


The greatest difficulty facing the recognition of Arabic handwritten words is segmentation, because Arabic handwriting is cursive with complex multi-form styles. Hence, intensive research efforts are needed to reach an effective Arabic handwriting segmentation system. This paper presents a system which uses morphological features of the Arabic characters for segmentation. The proposed system segments non-overlapped (horizontally connected -e.g. "حسن") as well as overlapped (vertically connected - e.g. "نجد") characters. The result is not very good one. However, it arrives at good directives for more research. As the writing was freely without any restrictions, both over-segmentation and under-segmentation problems affect the system. 


Sari, Souici and Sellami, "Off-Line Handwritten Arabic Character Segmentation Algorithm: ACSA ", Proceeding of the eighth International workshop on frontiers in handwriting recognition, (2002).

Abuhaiba, "A Discrete Arabic script for Better Automatic Document Understanding ", the Arabian Journal for Science and Engineering, (April 2003).

Touj, Amara and Amiri, "Two Approaches for Arabic Scrip recognition-based Segmentation Using the Hough Transform ", Document Analysis and Recognition, Volume 2, Page (s): 654 - 658, (2007).

Ayman Mohammad Bahaa Eldeen Sadeq, "Intelligent Neural System for Character Recognition", A Thesis Submitted in Partial Fulfillment of the Requirements of the Degree of Master of Science in Electrical Engineering (Computer & Systems), (1999).

Bushofa and Spann, "Segmentation and recognition of Arabic Characters by Structural Classification ", Image and Vision Computing, (1997).

Fakir, Hassani and Sodeyama, "On the Recognition of

How to Cite
E. M. Musa, M., A. Bashir, B., & Ismail, M. N. I. (2016). Designing an Arabic Handwritten Segmentation System. International Journal of Computer (IJC), 20(1), 199-209. Retrieved from