A robust method based on static hand gesture recognition for human-computer interaction under complex background

Abstract

An appearance-based approach needs usually a perfect segmentation. However, it is a difficult task especially under complex background. As a result, it limits the robustness for application. In this chapter, we design a new method for static hand gesture recognition in complex background for human-computer interface (HCI). In this method, we do not need perfect segmentation or hand tracking. The Hu invariant moment features are extracted from a binary image after simple segmentation and served as the input of our classifier, which is constructed beforehand based on support vector machines (SVM) algorithm. Furthermore, a Euclidean distance is calculated to combine with SVM model for avoiding the non-hand gestures. Tests on the testing dataset show the proposed method exhibits a recognition rate near 100%. Experimental results on a simple HCI system on real-time demonstrated the effectiveness, speediness and robustness of the system under cluttered background. © 2012 Springer Science+Business Media B.V.