《计算机应用研究》|Application Research of Computers

基于SEF-GHEI及协同表示的步态识别研究

Gait recognition based on SEF-GHEI and synergy representation

免费全文下载 (已被下载 次)  
获取PDF全文
作者 徐守坤,邱亮,石林,李宁
机构 1.常州大学 信息科学与工程学院 数理学院,江苏 常州 213164;2.闽江学院 福建省信息处理与智能控制重点实验室,福州 350108
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2019)06-066-1917-04
DOI 10.19734/j.issn.1001-3695.2018.01.0052
摘要 将协同表示方法应用于步态识别中可以解决稀疏表示方法计算耗时的问题,但提取步态特征采用的GEI算法没有考虑步态内部轮廓边界信息,导致识别率不高。针对此问题,提出使用融合Hog和GEI算法的方法提取步态特征,在此基础上使用协同表示的方法训练,再通过计算测试样本的最小重构误差进行分类。实验结果表明,该方法在单一视角下步态识别准确率平均提高了1.315%,以及跨视角下步态识别准确率平均提高了6.51%,说明该方法是可行的。
关键词 稀疏表示; 协同表示; GEI算法; Hog算法
基金项目 闽江学院福建省信息处理与智能控制重点实验室开放课题资助项目(MJUKF201740)
本文URL http://www.arocmag.com/article/01-2019-06-066.html
英文标题 Gait recognition based on SEF-GHEI and synergy representation
作者英文名 Xu Shoukun, Qiu Liang, Shi Lin, Li Ning
机构英文名 1.School of Mathematics & Physics,School of Information Science & Engineering,Changzhou University,Changzhou Jiangsu 213164,China;2.Fujian Provincial Key Laboratory of Information Processing & Intelligent Control,Minjiang University,Fuzhou 350108,China
英文摘要 Applying collaborative representation method to gait recognition research can solve the problem of time-consuming calculation of sparse representation. While the GEI algorithm for extracting gait features does not consider gait internal outline information, resulting a low recognition rate. To address this problem, this paper proposed a novel method to extract gait features by using a fusion Hog and GEI algorithm. On the basis of this method, it trained the samples by using collaborative representation method and classified the samples according to the minimum reconstruction error. The experimental results show that the accuracy of the proposed method is 1.315% higher than that of the collaborative representation in a single view, and the accuracy of gait recognition is increased by 6.51% over the cross view.
英文关键词 sparse representation; collaborative representation; GEI algorithm; Hog algorithm
参考文献 查看稿件参考文献
 
收稿日期 2018/1/5
修回日期 2018/2/22
页码 1917-1920
中图分类号 TP391.41
文献标志码 A