【摘要】 针对目前手势识别方法受手势旋转、平移、缩放的影响,导致手势识别率偏低的问题,提出一种基于手势主方向和类-Hausdorff距离模板匹配的手势识别方法.首先把分割后的手势图像进行标准化处理,并求出标准化图像中的手势主方向;然后根据手势主方向建立二维手势直角坐标系提取空间手势特征;再利用空间手势坐标点分布特征方法对手势进行初步识别;最后利用类-Hausdorff距离模板匹配的思想识别最终的手势.实验结果表明,在光照相对稳定的条件下,该方法能够实时准确地实现手势识别,总体识别率达到95%;对发生旋转的手势识别率能超过90%.更多还原

【Abstract】 Since current gesture recognition algorithms are influenced by rotation, translation and scaling, and which can lead to lower recognition rate, this paper proposes a gesture recognition algorithm which is based on the main direction of gesture and Hausdorff-like distance template matching. Firstly, we converted the segmented gesture image to standardized image and calculated the main direction of gesture in the standardized image. Then, we built a 2D rectangular coordinate system to extract the gesture features. Next, we used the method of hand coordinates distribution features to preliminarily recognize the gesture. Finally, the thought of Hausdorff-like distance was used to recognize the final gesture. Experimental results show that this algorithm can achieve real-time correct gestures recognition in relatively stable light conditions. The overall recognition rate can reach 95% and the recognition rate of rotation gestures is more than 90%.更多还原