首页 | 本学科首页   官方微博 | 高级检索  
     

一种步态识别方法
引用本文:田光见,赵荣椿.一种步态识别方法[J].计算机科学,2005,32(9):180-181.
作者姓名:田光见  赵荣椿
作者单位:西北工业大学计算机学院,西安,710072;西北工业大学计算机学院,西安,710072
摘    要:步态识别作为一种新的生物特征识别技术,通过人走路的姿势实现对个人身份的识别和认证.算法利用步态轮廓图像边界到重心的距离矢量对步态轮廓图像进行描述,采用步态图像的高宽比进行步态的准周期性分析.利用隐马尔可夫模型进行步态时变数据匹配识别.算法在CMU数据库上面进行实验取得了较高的正确识别率.

关 键 词:生物特征识别  步态识别  特征提取  隐马尔可夫模型

A Method of Gait Recognition
TIAN Guang-Jian,ZHAO Rong-Chun.A Method of Gait Recognition[J].Computer Science,2005,32(9):180-181.
Authors:TIAN Guang-Jian  ZHAO Rong-Chun
Affiliation:Department of Computer Science and Technology, Northwestern Poly-technieal Universlty,Xi'an 710072
Abstract:Gait recognition refers to automatic identification of an individual based on his/her style of walking; it's a new biometrics recognition technology. This paper attempts to describe gait contour by using the distance between the contour centroid and the pixels on the edge, to make quasi-periodic analysis on height and width ratio of gait image, and to solve the problems resulting from image sequence of different gait cycle by HMM. By utilizing the algorithm in the paper, the experiments made on CMU database have achieved comparatively high correction identification ratio.
Keywords:Biometrics  Gait recognition  Feature extraction  Hidden markov model
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机科学》浏览原始摘要信息
点击此处可从《计算机科学》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号