article · IEEE Access
Gesture recognition technologies increasingly rely on tiny machine learning to enable direct human-computer interaction, yet recognising complex scripts such as Arabic in real time remains difficult. To address this limitation, a lightweight deep learning model based on a convolutional neural network architecture was developed to process gesture-based air handwriting. The system is designed to handle the structural complexities of Arabic script within the strict resource constraints of edge devices. When tested on two-dimensional gesture inputs of Arabic numerals and simple letters, the model achieved a recognition accuracy of 97.5 percent. This demonstrates that compact machine learning models can deliver high accuracy on intricate scripts, offering a practical approach for expanding responsive gesture-based interfaces.
Interacting with devices through gestures often requires substantial computing power, making real-time recognition difficult on low-power hardware. By successfully interpreting Arabic script with high accuracy using a compact model, this work shows how touchless, air-handwriting interfaces can become faster, more accessible, and viable for everyday digital devices without depending on heavy cloud computing resources.
The technology could enable real-time, touchless text and number entry on resource-constrained devices, serving users of Arabic script in applications such as smart appliances, wearables, or public kiosks. The work represents applied and tested research, having validated model performance on two-dimensional gesture data, though integration into commercial products and varied operational environments remains to be demonstrated.
AI-generated from the published abstract. Always read the original work before citing.
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.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2024.3406631
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
