Real-Time Hand Gesture-Based Media Player Control Using Computer Vision

Abstract

Advancements in computer vision and human–computer interaction have enabled the development of touchless interfaces that improve user convenience, accessibility, and operational efficiency. This paper presents a real-time hand gesture-based media player control system using computer vision techniques, allowing users to interact with multimedia applications without relying on traditional input devices such as keyboards, mice, or remote controls. The proposed system employs a standard webcam to capture live video frames and utilizes the MediaPipe Hands framework for accurate hand landmark detection and tracking. Gesture recognition is performed by analyzing the spatial relationships between detected hand landmarks, enabling intuitive control of media playback functions, including play, pause, next track, previous track, volume adjustment, and stop. The recognized gestures are translated into corresponding system commands through the PyAutoGUI automation library, providing seamless interaction with the media player in real time.

The proposed approach offers a low-cost and contactless solution that does not require specialized hardware or wearable sensors, making it suitable for smart homes, educational environments, public multimedia kiosks, and assistive technologies for users with physical disabilities. Experimental evaluation demonstrates that the system achieves reliable gesture recognition with high responsiveness under normal lighting conditions while maintaining low processing latency suitable for real-time applications. The integration of MediaPipe and OpenCV provides accurate hand tracking with reduced computational complexity, enabling deployment on conventional personal computers equipped with standard webcams. The results indicate that the proposed system enhances user interaction by offering an intuitive, hygienic, and efficient alternative to conventional media control methods. Future enhancements may incorporate dynamic gesture recognition, deep learning-based classification, multi-user support, and improved robustness under varying environmental conditions to further extend the system's usability and performance.