Ahmed Rami, Gogate Mandar, Tahir Ahsen, Dashtipour Kia, Al-Tamimi Bassam, Hawalah Ahmad, El-Affendi Mohammed A, Hussain Amir
College of Computer Sciences and Information Technology, Sudan University of Science and Technology, P.O. Box 407 Khartoum, Sudan.
School of Computing, Edinburgh Napier University, Edinburgh EH10 5DT, UK.
Entropy (Basel). 2021 Mar 13;23(3):340. doi: 10.3390/e23030340.
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.
离线阿拉伯文手写识别（OAHR）由于其在办公自动化和文档处理等多个领域的应用，最近在模式识别和图像处理领域发挥了重要作用。然而，OAHR仍然面临着一些挑战，包括阿拉伯文字体的高度变异性及其内在特征，如草书、连字和变音符，人类手写的无限变化，以及缺乏大型公共数据库。在本文中，我们引入了一种基于深度神经网络的新型上下文感知模型，以应对识别离线手写阿拉伯文本的挑战，包括孤立数字、字符和单词。具体而言，我们提出了一种有监督的卷积神经网络（CNN）模型，该模型上下文提取最优特征，并采用批量归一化和随机失活正则化参数。与传统深度学习模型相比，这旨在防止过拟合并进一步提高泛化性能。我们使用多个深度堆叠卷积层来设计所提出的深度CNN（DCNN）架构。该模型经过广泛评估，与包括MADBase（数字）、CMATERDB（数字）、HACDB（字符）、SUST-ALT（数字）、SUST-ALT（字符）和SUST-ALT（名字）在内的六个不同基准数据库上的传统OAHR方法相比，显示出优异的分类准确率。通过利用基于迁移学习（TL）的特征提取，在基准阿拉伯数据库上进行了进一步的实验研究，证明了我们提出的模型相对于最先进的VGGNet-19和MobileNet预训练模型的优越性。最后，使用另一个语言数据库，特别是基准MNIST英文孤立数字数据库进行实验，以评估模型的比较泛化能力，这进一步证实了我们提出的DCNN模型的优越性。
