S. Pothalaiah, M.Purushotham, S.Dinesh, P.Santosh

Abstract

Gesture recognition technology is an efficient, direct and natural human-computer interaction method, which is an active research topic in the field of computer vision. At the same time, the high degree of freedom of the hand leads to the characteristics of complex gestures, diverse changes, and high-speed movement, which makes gesture recognition technology one of the most challenging topics. In this paper, different gestures are recognized in the HSV and YCgCr colour spaces, and the detection and feature extraction based on Python are realized with the help of OPENCV2.3.1 visual library and Microsoft Visual Studio. In this paper, the related technologies of natural gesture recognition based on computer vision, such as gesture image acquisition and pre- processing, gesture image segmentation and feature extraction, and gesture modelling, etc., are proposed, and a solution suitable for virtual mouse system is proposed.