Abstract
Learning to write the Arabic alphabet is crucial for Arab children's cognitive development, enhancing their memory and retention skills. However, the lack of Arabic language educational applications may hamper the effectiveness of their learning experience. To bridge this gap, SamAbjd was developed, an interactive web application that leverages deep learning techniques, including air-writing recognition, to teach Arabic letters. SamAbjd was tailored to user needs through extensive surveys conducted with mothers and teachers, and a comprehensive literature review was performed to identify effective teaching methods and models. The development process involved gathering data from three publicly available datasets, culminating in a collection of 31,349 annotated images of handwritten Arabic letters. To enhance the dataset's quality, data preprocessing techniques were applied, such as image denoising, grayscale conversion, and data augmentation. Two models were experimented with using a convolution neural network (CNN) and Visual Geometry Group (VGG16) to evaluate their effectiveness in recognizing air-written Arabic characters. Among the CNN models tested, the standout performer was a seven-layer model without dropout, which achieved a high testing accuracy of 96.40%. This model also demonstrated impressive precision and F1-score, both around 96.44% and 96.43%, respectively, indicating successful fitting without overfitting. The web application, built using Flask and PyCharm, offers a robust and user-friendly interface. By incorporating deep learning techniques and user feedback, the web application meets educational needs effectively.