A new design based-fusion of features to recognize arabic handwritten characters

Abstract

Precise character recognition is a challenging task. The problem of reaching a conclusion in classification technique and feature set selection obviously fetches out in this manuscript with sufficient study. The proposed model processes the issue as well as handling the automatic selection issue of suitable features particularly for multi-font or style of Arabic script to get better character recognition. In this paper, introduced a model depended on fusion strategy for handwritten script recognition and identification of multi-font with SH Roqa, Naskh, Farsi, and Igaza. Experimentation has been performed on AHDB and AHCD data sets. The results of the experimental show an excellent performance with higher accuracy.