| 基于Radon变换特征提取的步态识别 |
| |
| 引用本文： | 张前进,徐素莉,孙炎增.基于Radon变换特征提取的步态识别[J].数据采集与处理,2010,25(2). |
| |
| 作者姓名： | 张前进 徐素莉 孙炎增 |
| |
| 作者单位： | 河南科技大学电子信息工程学院,洛阳,471003 |
| |
| 基金项目： | 河南省重点科技攻关项目 |
| |
| 摘 要： | 提出了一种基于Radon变换特征提取的步态识别算法.该算法根据步态轮廓图下肢的宽度信息确定步态运动准周期性,对二进制准周期步态轮廓序列进行Radon变换构造特征向量模板.对特征向量进行主成分分析,并采用k-近邻法进行步态特征分类.在CASIA步态数据库上和CAS识别算法进行了详细的比较,实验结果表明,该算法在性能上有较大程度的提高,是一种有效的步态识别方法.
|
| 关 键 词： | 步态识别 Radon变换 主成分分析 特征提取 |
Feature Extraction Based on Radon Transform for Gait Recognition |
| |
| Zhang Qianjin,Xu Suli,Sun Yanzeng.Feature Extraction Based on Radon Transform for Gait Recognition[J].Journal of Data Acquisition & Processing,2010,25(2). |
| |
| Authors: | Zhang Qianjin Xu Suli Sun Yanzeng |
| |
| Affiliation: | Zhang Qianjin,Xu Suli,Sun Yanzeng(School of Electronics , Information Engineering,Henan University of Science , Technology,Luoyang,471003,China) |
| |
| Abstract: | A novel feature extraction algorithm is proposed for the gait recognition based on Radon transform.For each image sequence,the algorithm obtains the gait quasi-periodicity by analyzing the width information of the gait contour edge of lower limbs.Radon transform is applied to the binary quasi-periodicity image sequence for feature vector constructing.The principal component analysis is used for feature vector construction,and the k-nearest neighbor classifier is adopted to recognize subjects.Compared the al... |
| |
| Keywords: | gait identification Radon transform principal component analysis feature extraction |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
