Hand Gesture-Based Human-Computer Interaction using MediaPipe and OpenCV

This study presents the design and implementation of a real-time hand gesture recognition system for directional movement using MediaPipe and OpenCV. The system aims to enhance Human-Computer Interaction (HCI) by recognizing four primary hand gestures—forward, backward, left, and right—based on real-time video input from a standard webcam. The proposed method extracts 21 hand landmarks using MediaPipe, then analyzes landmark displacement to determine the direction of movement. Experiments were conducted under three lighting conditions (bright, moderate, dim) and at three distances (200 cm, 300 cm, and 450 cm). Results show that the system achieved 100% recognition accuracy for all gestures at 200 cm. At 300 cm, accuracy slightly decreased, particularly for backward gestures (down to 77.5%). At 450 cm, performance dropped significantly, with accuracy for some gestures falling below 30%, especially under dim lighting. These findings demonstrate that the proposed system performs reliably at short to medium distances and is sensitive to lighting conditions and user proximity. This research contributes to the development of touchless interfaces for smart environments, presentations, and other interactive applications.

Abstract licence: CC BY

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.