Gesture recognition and response system for special education using computer vision and human-computer interaction technology.

Gesture recognition has emerged as a pivotal technology for enhancing human-computer interaction (HCI), especially in the context of special education. This study presents a comprehensive gesture recognition and response system that leverages advanced deep learning architectures, including AlexNet, VGG19, ResNet and MobileNet, combined with machine learning algorithms such as support vector machines (SVM) and random forest. The proposed system achieves state-of-the-art performance, with an accuracy of 95.4%, demonstrating its effectiveness in recognising complex gestures with high precision. To address the challenges of deploying gesture recognition systems on resource-constrained devices, the study incorporates genetic algorithms (GAs) for model compression. This optimisation reduces the model size by 42%, significantly enhancing its suitability for real-time applications on mobile and embedded platforms. Additionally, inference time is reduced by 45%, enabling faster response times essential for interactive educational environments. The system was evaluated using a diverse gesture dataset, ensuring robustness across varying lighting conditions, user demographics, and physical differences. The findings highlight the potential of integrating gesture recognition systems into special education, where they can serve as assistive tools for individuals with disabilities, fostering inclusive and engaging learning experiences. This work not only advances the field of gesture recognition but also underscores the importance of model optimisation for real-world applications. Future research will focus on expanding the gesture library, integrating multimodal inputs such as speech, and enhancing system adaptability through continuous learning mechanisms.