Performance of Machine Learning and Deep Learning on Arabic Handwritten Text Recognition

Abstract

This paper proposes machine learning and deep learning techniques for recognizing Arabic handwritten text. Finally, this paper introduces a comparative study between them in term of their performance. Actually, the classification of Arabic handwritten text plays a vital role in the computer vision domain, where traditional machine learning techniques and deep learning techniques are commonly used by researchers. In this paper, both machine learning and deep learning techniques are proposed and evaluated for recognizing Arabic handwritten text. Several experiments were carried out using both machine learning and deep learning on two different databases the AHCR and ADBase. The AHCR contains 28000 images of handwritten Arabic alphabet letters written by 100 writers. While the ADBase contains 70,000 images of handwritten Arabic digits written by 700 writers. The experimental results on both databases have demonstrated that the performance of the deep learning outperforms machine learning.