一种基于稀疏表示的手势识别算法
A gesture recognition algorithm based on sparse representation
张勤 1赵健 1孙道达 1胡江华 1冯宁1
作者信息
- 1. 西北大学信息科学与技术学院,陕西西安710127
- 折叠
摘要
针对经典手势识别方法中在旋转变化与偏移情况下识别率不高的问题,提出一种基于稀疏表示的手势识别算法.通过最小二乘法求解手势特征的稀疏表示,利用Sebastien手势库训练构建出稀疏表示手势冗余字典,最后根据残差最小值实现手势识别.实验结果表明:在手势发生旋转变化和偏移的情况下,所提出的基于稀疏表示的手势识别算法识别率高于经典的最近邻分类手势识别算法.
Abstract
Sparse representation is proposed for the classic gesture recognition method under an angle rotation and offset variation,in which the recognition rate is not high.Sparse representation is solved by the least square method,then the redundant dictionary is gained from the Sebastien training samples,and will be used to sparsely represent the test gestures to classify the gesture images by the residual error minimum classification.The experimental results show that the test signal samples which were classified by sparse representation could be identified with a higher rate than the classic neighbor nearest classification,even if there is a certain angle rotation and offset variation of the gesture.
关键词
稀疏表示/手势识别/特征提取/最小二乘法Key words
sparse representation/gesture recognition/feature extraction/least square algorithm引用本文复制引用
基金项目
出版年
2013
NETL
NSTL
维普
万方数据