| 基于HMM的步态身份识别 |
| |
| 引用本文： | 高大利,吴清江,孙凌. 基于HMM的步态身份识别[J]. 计算机工程与应用, 2006, 42(16): 53-56,166 |
| |
| 作者姓名： | 高大利 吴清江 孙凌 |
| |
| 作者单位： | 华侨大学信息学院计算机系,福建泉州,362021;泉州师范学院计算机系,福建泉州,362000;华侨大学信息学院计算机系,福建泉州,362021;南京理工大学计算机系,南京,210094;河南商业高等专科学校计算机系,郑州,450044 |
| |
| 摘 要： | 随着生物识别悄然兴起,生物识别技术逐渐成为新的身份识别技术。步态识别是生物特征识别技术的一个新兴子领域。文章就是将隐马尔可夫模型(HMM,HiddenMarkovModel)方法运用在步态身份识别中,并进行了其识别性能的研究。该文给出了一个基于HMM的步态身份识别方案,并进行了图像预处理,HMM参数训练和识别的研究,得出了一些有意义的结论。同时在中国科学院自动化研究所提供的CASIA步态数据库上进行了步态身份识别实验,实验结果表明:在侧面视角下采用此方法,具有较好的识别率。
|
| 关 键 词： | 步态识别 HMM模型 HMM训练 |
| 文章编号： | 1002-8331-（2006）16-0053-04 |
| 收稿时间： | 2005-09-01 |
| 修稿时间： | 2005-09-01 |
Gait-based Person Identification Using HMM |
| |
| Gao Dali,Wu Qingjiang,Sun Ling. Gait-based Person Identification Using HMM[J]. Computer Engineering and Applications, 2006, 42(16): 53-56,166 |
| |
| Authors: | Gao Dali Wu Qingjiang Sun Ling |
| |
| Affiliation: | 1Department of Computer Science,Huaqiao National University,Quanzhou,Fujian 362021;2Quanzhou Teachers College, Quanzhou, Fujian 362000; 3Nanjing University of Science and Technology,Nanjing 210094; 4Henan Business College,Zhengzhou 450044 |
| |
| Abstract: | With the emergence of the biometric identification technology,it has gradually become the new technology about identification.The gait recognition is one of the new field in the feature recognition on biology.We implement the HMM(Hiddden Markow Model) method in the gait recognition,and have been studied in the recognition capability.Inthis dissertation,we provid a project of gait recognition on HMM,took on the image preprocessing,the training HMM parameters,and identifying from a test sequence,and got some very significant conclusion.At the same time,we take the experiment on gait database of CASIA provided by Institute of Automation,Chinese Academy of Sciences.The experimental results show that the proposed approach is excellent in recognition rate by HMM on the angle of view from the profile. |
| |
| Keywords: | gait recognition HMM model HMM training |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
