Real-Time Hand Gesture Recognition with Finger Counting (Using OpenCV and Mediapipe)

Computer science

Hand gesture recognition plays a crucial role in human-computer interaction, allowing people to communicate with machines in a more natural, intuitive, and efficient way. This paper presents a real-time hand gesture recognition system that utilizes computer vision techniques and Mediapipe’s hand landmark detection to count raised fingers accurately. The implemented pipeline starts by accessing live video from a standard camera and then processes each frame to extract hand landmarks. Subsequently, an algorithm identifies the number of raised fingers for both left and right hands by analyzing landmark positions. The system performs robustly under different lighting conditions and hand orientations, making it suitable for a range of applications, including interactive games, education, sign language recognition, and industrial automation. The main contribution of this paper lies in its lightweight, cost-effective, and real-time approach for gesture recognition, demonstrating the potential of computer vision to enable more natural human-machine interaction.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.