北京航空航天大学学报 ›› 2015, Vol. 41 ›› Issue (4): 732-736.doi: 10.13700/j.bh.1001-5965.2014.0289

• 论文 • 上一篇    下一篇

基于局部径向二值模式的三维人脸识别

刘青, 孙军华   

  1. 北京航空航天大学 仪器科学与光电工程学院, 北京 100191
  • 收稿日期:2014-05-21 修回日期:2014-09-26 出版日期:2015-04-20 发布日期:2015-05-08
  • 通讯作者: 孙军华(1975—),男,湖北荆门人,副教授,sjh@buaa.edu.cn,主要研究方向为光电精密测量、机器视觉和图像理解. E-mail:sjh@buaa.edu.cn
  • 作者简介:刘青(1989—),女,河北邯郸人,硕士生,602919926@163.com
  • 基金资助:

    国家自然科学基金资助项目(61275162)

3D face recognition based on local radial binary pattern

LIU Qing, SUN Junhua   

  1. School of Instrumentation Science and Opto-electronics Engineering, Beijing University of Aeronautics and Astronautics, Beijing 100191, China
  • Received:2014-05-21 Revised:2014-09-26 Online:2015-04-20 Published:2015-05-08

摘要:

针对人脸识别中局部特征的提取,提出了局部径向二值模式(LRBP,Local Radial Binary Pattern),并将其用于三维人脸识别.首先,对经过预处理的人脸深度图像进行区域划分;然后用局部径向二值模式提取子区域的特征序列,并将其链接在一起构成三维人脸的特征向量;最后,利用Fisherface方法对三维人脸特征向量进行训练和识别.在中国科学院自动化研究所三维人脸数据库中选取样本,利用LRBP对其进行识别,结果表明该方法在基本不损失识别率的前提下,可以有效提高识别的效率.

关键词: 模式识别, 三维人脸识别, 局部特征, 二值模式, 局部径向二值模式

Abstract:

An operator named local radial binary pattern (LRBP) was proposed for extracting local features in face recognition. The binary sequence encoding scheme of the LRBP is different from that of the local binary pattern. Firstly, the proposed LRBP operator was used in 3D face recognition. 3D face depth images were preprocessed and divided into subregions. Then the signature sequences of the subregions were extracted by the LRBP operator. The feature vectors of a 3D face depth image were obtained by connecting the signature sequences of all the subregions of the image. Finally, the 3D face feature vectors were trained and recognized using the Fisherface method. Experiments were conducted using the 3D face database of Institute of Automation, Chinese Academy of Sciences. The results show that the proposed method can effectively promote the efficiency of 3D face recognition without reducing the recognition rates.

Key words: pattern recognition, 3D face recognition, local feature, binary pattern, local radial binary pattern

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发