Hand Posture Recognition with standard webcam for Natural Interaction

Abstract

This paper presents an experimental prototype designed for natural human-computer interaction in an environmental intelligence system. Using computer vision resources, it analyzes the images captured by a webcam to recognize a person’s hand movements. There is now a strong trend in interpreting these hand and body movements in general, with computer vision, which is a very attractive field of research. In this study, a mechanism for natural interaction was implemented by analyzing images captured by a webcam based on hand geometry and posture, to show its movements in our model. A camera is installed in such a manner that it can discriminate the movements a person makes using Background Subtraction. Then hands are searched for assisted by segmentation by skin color detection and a series of classifiers. Finally, the geometric characteristics of the hands are extracted to distinguish defined control action positions.