基于信息融合的三维人脸识别

廖广军 曾玮 刘屿 李致富 胡跃明

doi:10.3969/j.issn.1000-565X.2013.11.003

华南理工大学学报(自然科学版) >

2013 , Vol. 41 >Issue 11: 16 - 22

DOI: https://doi.org/10.3969/j.issn.1000-565X.2013.11.003

电子、通信与自动控制

基于信息融合的三维人脸识别

展开

1．华南理工大学自动化科学与工程学院，广东广州 510640; 2．华南理工大学精密电子制造装备教育部工程中心，广东广州 510640; 3．华南理工大学机械与汽车工程学院，广东广州 510640

廖广军(1981- )，男，博士生，主要从事模式识别的应用研究． E-mail:gdliaogj@gmail．com

收稿日期: 2013-05-24

修回日期: 2013-08-09

网络出版日期: 2013-10-11

基金资助

国家“863” 计划项目 (2012AA041312);国家自然科学基金资助项目(61203060);公安部应用创新课题(2012YYCXGDST081);2013 年广东省省级科技计划项目;华南理工大学中央高校基本科研业务费专项资金资助项目(2013ZM0098);广东警官学院院级重点项目(2011- Z02)

收起

Three- Dimension Face Recognition Based on Information Fusion

Expand

1.School of Automation Science and Engineering,South China University of Technology,Guangzhou 510640,Guangdong,China;2.Engineering Research Center for Precision Electronic Manufacturing Equipments of the Ministry of Education,South ChinaUniversity of Technology,Guangzhou 510640,Guangdong,China; 3.School of Mechanical and Automotive Engineering,SouthChina University of Technology,Guangzhou 510640,Guangdong,China

廖广军(1981- )，男，博士生，主要从事模式识别的应用研究． E-mail:gdliaogj@gmail．com

Received date: 2013-05-24

Revised date: 2013-08-09

Online published: 2013-10-11

Supported by

Fold

摘要

为了克服二维人脸识别的不足，提出采用 Kinect 采集设备并基于信息融合进行三维人脸识别．在人脸检测方面，利用双眼位置定位人脸，并通过肤色模型和深度信息实现人脸过滤．在人脸识别方面，将动态时间规整算法应用于人脸轮廓快速提取，并提出了一种改进的局部区域二值化特征( LBP) 匹配来实现人脸识别，将彩色图像信息和人脸生理特征信息的分析应用于区域 LBP 算法的权值确定．实验表明: 文中提出的基于信息融合的三维人脸识别方法具有使用价值，识别方法的实时性和鲁棒性方面得到一定提升．

关键词： 人脸检测; 三维人脸识别; 信息融合; 动态时间规整; 区域二值化特征匹配

本文引用格式

廖广军曾玮刘屿李致富胡跃明 . 基于信息融合的三维人脸识别[J]. 华南理工大学学报(自然科学版), 2013 , 41(11) : 16 -22 . DOI: 10.3969/j.issn.1000-565X.2013.11.003

Abstract

In order to overcome the disadvantages of two- dimension face recognition,a three- dimension methodusing a Kinect instrument is proposed based on the information fusion.In this method,for the face detection,theeyes' location is used to locate the face,and the skin color model as well as the depth information is employed torealize the face filtering.For the face recognition,the DTW (Dynamic Time Warping) algorithm is applied to therapid extraction of the face contour,and an improved LBP (Local Binary Pattern) matching algorithm is proposed,in which the weight value distribution is determined by analyzing the color image information and the face physiolo-gical characteristics.Experimental results show that the proposed method for face recognition is applicable and is ofimproved real- time capability and robustness.

Key words： face detection; three- dimension face recognition; information fusion; dynamic time warping; localbinary pattern matching

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract