Robust Facial Emotion Detection in Low-Light Conditions: A Novel Approach Using Real-Time WebSocket Data Transfer

Facial emotion detection plays a crucial role in human-computer interaction and psychological research. However, existing methods often falter in low-light environments, limiting their real-world applicability. This paper presents a novel approach to enhance the robustness of facial emotion detection systems in low-light conditions using a standard camera and real-time data transfer via WebSocket. Our method employs advanced computer vision techniques, including adaptive histogram equalization and deep learning-based feature extraction, to ensure robust facial feature detection and emotion classification across varied lighting conditions. We will integrate our system with a TurtleBot 4 mobile platform to demonstrate its practical applications in assistive technologies and interactive systems. Experimental results show that our approach achieves 85.2% accuracy in low-light conditions, a significant improvement over baseline models. This research contributes to the development of more versatile and reliable emotion recognition systems for real-world applications.