A TinyDL Model for Gesture-Based Air Handwriting Arabic Numbers and Simple Arabic Letters Recognition

Abstract

The application of tiny machine learning (TinyML) in human-computer interaction is revolutionizing gesture recognition technologies. However, there remains a significant gap in the literature regarding the effective recognition of complex scripts, such as Arabic, in real-time applications. This research aims to bridge this gap by leveraging TinyML for the accurate recognition of Arabic numbers and simple letters through gesture-based air handwriting. For the first time, we introduce a novel tiny deep learning (TinyDL) model that utilizes a lightweight convolutional neural network (CNN) architecture specifically designed to handle the intricacies of the Arabic script and adaptable for the TinyML domain. Despite the widespread use of CNNs in gesture recognition, our model stands out by achieving an exceptional accuracy rate of 97.5% in decoding 2D gesture inputs of Arabic numerals and letters. This high level of accuracy demonstrates the effectiveness of our TinyDL model in addressing the unique challenges posed by Arabic script recognition, thereby making it a user-friendly and accessible solution. Moreover, our research contributes to the advancement of TinyML applications in real-world gesture recognition apps, showcasing the potential of TinyML in transforming the interaction between humans and digital devices.

Keywords

• Arabic letters recognition
• Arabic numerals
• convolutional neural networks (CNN)
• deep learning (DL)
• gesture-based recognition
• human-computer interaction