A Simple and Effective Method for Hand Gesture Recognition

摘要

Hand gesture recognition is very important for HCI (human computer interaction). We introduce a simple method to recognize hand gestures. After the hand region is segmented from the background, the distance signature is constructed to describe the shapes of hand gestures. Then, the recognition of hand gestures is accomplished using the KNN classifier. The experimental results on one image collection of hand gestures demonstrate that our method works well for hand gesture recognition. Moreover, our method shows better performance than a state-of-art method on another data set of hand gestures.