A Real-time Gesture Recognition Algorithm on Video Surveillance

摘要

In this paper we have described a real-time technique for detecting the presence of a hand, and determining hand gestures. The algorithm consists of two steps, the first is to location the hand area and eliminate noise, then seek for angles of the fingers and location of fingertip. With these features, the correct recognition of each finger spell is achieved. According to the recognition results of difference illumination, the algorithm has a good performance.