| 引用本文: | 赵志杰,孙小英,金雪松,孙华东,卢鑫.多重图像轮廓特征结合的步态识别算法[J].哈尔滨工业大学学报,2016,48(4):182.DOI:10.11918/j.issn.0367-6234.2016.04.031 |
| ZHAO Zhijie,SUN Xiaoying,JIN Xuesong,SUN Huadong,LU Xin.Gait recognition based on multiple image silhouette feature combination[J].Journal of Harbin Institute of Technology,2016,48(4):182.DOI:10.11918/j.issn.0367-6234.2016.04.031 |
|
| 摘要: |
| 为提高图像步态识别率，研究了一种基于图像轮廓多特征的步态识别算法.该算法首先从图像轮廓的基础上选取了图像步态的3个特征；然后，通过建立不变矩、帧差百分比的动态特征，并结合改进的角度距离的静态特征，实现了图像轮廓特征的提取；最后，通过对传统的K近邻法改进，完成了图像步态识别.实验结果表明：单用静态特征的步态识别率最高为91.94%；结合动态特征，并在改进分类器下获得最高为99.19%的识别率.
|
| 关键词: 步态识别 轮廓 不变矩 帧差百分比 角度距离 |
| DOI：10.11918/j.issn.0367-6234.2016.04.031 |
| 分类号:TP391.4 |
| 文献标识码:A |
| 基金项目:国家自然科学基金(NSFC61401123);黑龙江省自然科学基金 (F201245). |
|
| Gait recognition based on multiple image silhouette feature combination |
|
ZHAO Zhijie1,SUN Xiaoying1,JIN Xuesong1,SUN Huadong1,LU Xin2
|
|
(1.School of Computer and Information Engineering, Harbin University of Commerce, 150028 Harbin, China; 2.School of Electronics and Information Engineering, Harbin Institute of Technology, 150001 Harbin, China)
|
| Abstract: |
| This paper proposes a gait recognition algorithm based on three kinds of features from the image's silhouette. It extracts silhouette features by establishing dynamic information of invariant moment and percentage of frame difference, combining the modified angle distance of static information. It realizes the gait recognition via a modified K neighbor method. The experimental result shows that the recognition ratio achieves 91.94% with the static featureis only, and reaches 99.19% with the dynamic features under the improved classifier.
|
| Key words: gait recognition silhouette invariant moment percentage of frame difference point distance |
