Novel Deep Convolutional Neural Network-Based Contextual Recognition of Arabic Handwritten Scripts

Rami Ahmed; Mandar Gogate; Ahsen Tahir; Kia Dashtipour; Bassam Al-Tamimi; Ahmad Hawalah; Mohammed A El-Affendi; Amir Hussain

doi:10.3390/e23030340

Novel Deep Convolutional Neural Network-Based Contextual Recognition of Arabic Handwritten Scripts

Entropy (Basel). 2021 Mar 13;23(3):340. doi: 10.3390/e23030340.

Authors

Rami Ahmed¹, Mandar Gogate², Ahsen Tahir^{2

3}, Kia Dashtipour², Bassam Al-Tamimi⁴, Ahmad Hawalah⁵, Mohammed A El-Affendi⁶, Amir Hussain²

Affiliations

¹ College of Computer Sciences and Information Technology, Sudan University of Science and Technology, P.O. Box 407 Khartoum, Sudan.
² School of Computing, Edinburgh Napier University, Edinburgh EH10 5DT, UK.
³ Department of Electrical Engineering, University of Engineering and Technology, Lahore 54890, Pakistan.
⁴ Smart Big Data Ltd., London N1 7GU, UK.
⁵ College of Computer Science and Engineering, Taibah University, Madina 42353, Saudi Arabia.
⁶ Department of Computer Science, College of Computer and Information Sciences, Prince Sultan University, Riyadh 12435, Saudi Arabia.

Abstract

Offline Arabic Handwriting Recognition (OAHR) has recently become instrumental in the areas of pattern recognition and image processing due to its application in several fields, such as office automation and document processing. However, OAHR continues to face several challenges, including high variability of the Arabic script and its intrinsic characteristics such as cursiveness, ligatures, and diacritics, the unlimited variation in human handwriting, and the lack of large public databases. In this paper, we introduce a novel context-aware model based on deep neural networks to address the challenges of recognizing offline handwritten Arabic text, including isolated digits, characters, and words. Specifically, we propose a supervised Convolutional Neural Network (CNN) model that contextually extracts optimal features and employs batch normalization and dropout regularization parameters. This aims to prevent overfitting and further enhance generalization performance when compared to conventional deep learning models. We employ a number of deep stacked-convolutional layers to design the proposed Deep CNN (DCNN) architecture. The model is extensively evaluated and shown to demonstrate excellent classification accuracy when compared to conventional OAHR approaches on a diverse set of six benchmark databases, including MADBase (Digits), CMATERDB (Digits), HACDB (Characters), SUST-ALT (Digits), SUST-ALT (Characters), and SUST-ALT (Names). A further experimental study is conducted on the benchmark Arabic databases by exploiting transfer learning (TL)-based feature extraction which demonstrates the superiority of our proposed model in relation to state-of-the-art VGGNet-19 and MobileNet pre-trained models. Finally, experiments are conducted to assess comparative generalization capabilities of the models using another language database , specifically the benchmark MNIST English isolated Digits database, which further confirm the superiority of our proposed DCNN model.

Keywords: Arabic handwritten; DCNN; batch normalization; databases; dropout.