A Hand Gesture Recognition Method Based on Multi-Feature Fusion and Template Matching

Abstract Vision-based hand gesture recognition methods commonly use a single feature of hand gesture for classification. There are some problems as follows: recognition inaccuracy, system instability and ambiguous recognition results. This paper proposes a hand gesture recognition method based on multi-feature fusion and template matching. The method detects hand-shaped contour region and obtains the maximum contour according to skin color feature, by extracting angle count, skin color angle, and non-skin color angle in combination with Hu invariant moments features of the largest hand-shaped region for sample training. Euclidean distance template matching technique is applied for hand gesture classification and recognition. Experiments show that the method is effective for extracting features of different hand gestures and real-time recognition of ten kinds of hand gestures.