A New Design Based-Fusion of Features to Recognize Arabic Handwritten Characters
Amani Ali Ahmed Ali1, Suresha M.2
1Amani Ali Ahmed Ali, Department of Computer Science, Taiz University, Taiz, Yemen, MCA, Kuvempu University, Shimoga (Karnataka), India.
2Suresha M., Department of Computer Science and MCA, Kuvempu University, Shimoga (Karnataka), India.
Manuscript received on 18 June 2019 | Revised Manuscript received on 25 June 2019 | Manuscript published on 30 June 2019 | PP: 2570-2574 | Volume-8 Issue-5, June 2019 | Retrieval Number: E7909068519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
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
Keywords: Arabic Handwritten Script, Character Recognition, Features Fusion, Multi-Font Type.
Scope of the Article: Pattern Recognition