Real-time mobile application for Arabic sign alphabet recognition using pre-trained CNN

The recognition of alphabet signs is pivotal for the educational, linguistic, and cognitive development of individuals. This paper delves into the application of Convolutional Neural Networks (CNNs) on the ArASL database, a compilation of Arabic alphabet sign language images. Several CNN architectures underwent testing for image classification, with the EfficientNet B7 model emerging as the most effective, achieving an outstanding test accuracy of 99.24%. Capitalizing on the success of this optimized model, we have developed a real-time application with a dual purpose: to serve as a user-friendly tool for learning Arabic sign language and to enhance communication for individuals who are deaf or hard of hearing. The application, designed for seamless integration into users' daily lives, facilitates an intuitive engagement with the Arabic sign language alphabet. Its real-time functionality empowers users to learn and communicate effortlessly, breaking down barriers and fostering inclusivity in communication. This research contributes not only to the field of computer vision and deep learning but also to the broader spectrum of inclusive education and accessibility. By harnessing cutting-edge technology, our application represents a significant step forward in leveraging artificial intelligence for the betterment of education.