Recognition of handwritten Arabic (Indian) numerals using skeleton matching

Bassam Alqaralleh (Al Hussein Bin Talal University)
Malek Zakarya Alksasbeh (Al Hussein Bin Talal University)
Tamer Abukhalil (Al Hussein Bin Talal University)
Harbi Almahafzah (Al Hussein Bin Talal University)
Tawfiq Al Rawashdeh (Al Hussein Bin Talal University)

Indonesian Journal of Electrical Engineering and Computer Science
Vol 19, No 3: September 2020

This paper brings into discussion the problem of recognizing Arabic numbers using a monocular camera as the only sensor. When a digital image is presented in this application, optical character recognition (OCR) can be exploited to comprehend numerical data. However, there has been a limited success when applied to the handwritten Arabic (Indian) numbers. This paper aims to overcome this limitation and introduces optical character recognition system based on skeleton matching. The proposed approach is used for handwritten Arabic numbers only. The experimental results indicate the effectiveness of the proposed optical character recognition system even for numbers written in worst case. The right system achieves a recognition rate of 99.3 %.