摘要
步态对个人身份进行识别受到越来越多生物识别技术研究者的重视。步态能量图是一种有效的步态表征方法.通过提取步态能量图中的动态区域并利用Gabor小波变换对其特征提取,但经过Gabor变换后特征维数较高,必须经过有效的特征融合和选择。由此针对传统的Gabor特征提取后存在特征维数较高的缺点,提出了一种基于集成Gabor特征的步态识别方法。首先,采用均值融合和差分二值编码这两种集成方法,对动态区域Gabor特征图进行多尺度和多角度的集成,获得26张集成Gabor特征图;然后从26张集成Gabor特征图中选出4张作为最终的特征向量;最后将特征向量输入KNN分类器进行步态识别。实验结果表明,基于集成Gabor特征的步态识别方法,能够对步态特征进行有效分离和表达,同时降低维数并紧凑表征数据,对步态信息进行正确归类。
Gait recognition for individual identification has received more and more attention from biometrics researchers. Gait Energy Image is an efficient represent method. Gabor wavelet was used to get magnitude feature of active region of gait energy image, but the images after the Gabor transform generate high dimension feature, which must be processed through effective feature fusion and selection. In order to overcome the shortcoming of high dimension feature of the traditional Gabor feature, a gait recognition method based on integrated Gabor feature is proposed in this paper. Firstly, by means of two integration methods are mean fusion and differential binary encoding, the active region Gabor feature images are integrated in a multi-scale and muhi-angle way and 26 integrated Gabor feature images are obtained, and the 4 images from 26 integrated Gabor feature images are selected as the final feature vector. Finally, the feature vector is input KNN classifier to identify. Experimental results indicate that a gait recognition method based on integrated Gabor feature can separate and express gait features effectively, and reduce dimension and present expression data compactly, meanwhile the expressions are classified correctly.
出处
《电子测量与仪器学报》
CSCD
北大核心
2017年第4期573-579,共7页
Journal of Electronic Measurement and Instrumentation
基金
辽宁省高等学校优秀人才支持计划(LJQ2013013)资助项目
