首页>
外国专利>
Hand Feature Extraction Algorithm using Curvature Analysis For Recognition of Various Hand Feature
Hand Feature Extraction Algorithm using Curvature Analysis For Recognition of Various Hand Feature
展开▼
机译:基于曲率分析的手部特征提取算法用于各种手部特征的识别
展开▼
页面导航
摘要
著录项
相似文献
摘要
The present invention relates to a hand feature extraction method based on curvature analysis for recognizing various hand gestures, and more particularly, to a hand feature extraction method based on curvature analysis, which comprises: (a) extracting hand candidates extracted from a hand region, And a hand region of the hand candidate group; And (b) the hand area It is the step that extracts the feature from the hand, it extracts the feature from the hand outline, the boundary point between the fingers, the boundary point, the outline feature point, the finger it extracts the center point, And a feature extracting step of extracting a feature of the hand gesture. In order to extract a feature necessary for hand gesture recognition, it is based on a curvature analysis based on a finger, The feature extraction algorithm is based on the color model. It detects the hand region in the input image through the skin color range filter and the labeling, and extracts the features of the number and the finger attachment by using the outline and the feature point and the curvature information extracted from them. Hand gesture It is an expression. Experimental results show that recognition rate and frame rate are similar to those of existing algorithms, but gestures can be defined with extracted features. In that case, the number is four times that of existing algorithms, there was.;
展开▼