Hand Gesture Recognition For Human-Computer Interaction

With the rapid development of information technology, computers, smart phones, smart TVs and other smart devices have become a part of daily life. Introducing the gesture to human-computer interaction systems, and so people can communicate with intelligent devices through gestures defined, this change will bring great convenience to our life.This article describes an interactive system based on gesture recognition. The system consists of video capture module, video image analysis modules, intelligent devices response modules. Video image analysis is the core module of the system, consisting of the human face detection, motion detection and gesture recognition three parts.This paper focuses on gesture recognition algorithm research for Human-Computer Interaction, we propose two gesture recognition algorithms.Contour-based gesture recognition algorithm makes use of the skin color feature and movement information to complete the target of gesture segmentation and contour extraction. We get the approximate polygon and the direction of the gesture through gestures contours simplify and ellipse fitting. Based on such information, we extract the contour features of the hand gesture. We achieve a multi-scale and multi-angle gesture recognition algorithm.Contour-based gesture recognition algorithm is ineffective when the color of the background is similar to that of the skin. Multiple-classifiers based gesture recognition algorithm overcome this defect. The algorithm gets the size and the direction of the gesture by hand tracking algorithm which has the ability of segmentation and can give us the rough outline of the tracked hand. Based on this information, we rotate the image and get the upright image of the hand gesture. Then we extract the HOG feature of the upright hand image, and use multiple classifiers to classify the gesture. The algorithm has a better recognition rate wthere the background color is similar to the skin or complex.