National Institute of Applied Sciences and Technology (INSAT) at University of Carthage, LARATSI Laboratory, Cedex 1080, Tunis, Tunisia.
MedTech at South Mediterranean University, Cedex 1053, Tunis, Tunisia.
Comput Intell Neurosci. 2022 Jan 11;2022:9965426. doi: 10.1155/2022/9965426. eCollection 2022.
Handwritten characters recognition is a challenging research topic. A lot of works have been present to recognize letters of different languages. The availability of Arabic handwritten characters databases is limited. Motivated by this topic of research, we propose a convolution neural network for the classification of Arabic handwritten letters. Also, seven optimization algorithms are performed, and the best algorithm is reported. Faced with few available Arabic handwritten datasets, various data augmentation techniques are implemented to improve the robustness needed for the convolution neural network model. The proposed model is improved by using the dropout regularization method to avoid data overfitting problems. Moreover, suitable change is presented in the choice of optimization algorithms and data augmentation approaches to achieve a good performance. The model has been trained on two Arabic handwritten characters datasets AHCD and Hijja. The proposed algorithm achieved high recognition accuracy of 98.48% and 91.24% on AHCD and Hijja, respectively, outperforming other state-of-the-art models.
手写字符识别是一个具有挑战性的研究课题。已经有很多工作致力于识别不同语言的字母。阿拉伯文手写字符数据库的可用性有限。受此研究课题的启发，我们提出了一种卷积神经网络来对手写阿拉伯字母进行分类。此外，还进行了七种优化算法的实验，并报告了最佳算法。由于可用的阿拉伯文手写数据集很少，我们实现了各种数据增强技术来提高卷积神经网络模型所需的鲁棒性。通过使用辍学正则化方法来避免数据过拟合问题，对所提出的模型进行了改进。此外，还对优化算法和数据增强方法的选择进行了适当的改进，以获得良好的性能。该模型在两个阿拉伯文手写字符数据集 AHCD 和 Hijja 上进行了训练。所提出的算法在 AHCD 和 Hijja 上的识别准确率分别达到了 98.48%和 91.24%，优于其他最先进的模型。
