An improved eLBPH method for facial identity recognition: Expression-specific weighted local binary pattern histogram
Xi, Xuanyang1; Qin, Zhengke2; Ding, Shuguang3; Qiao, Hong1; Xi, XY
2015
Conference NameIEEE International Conference on Robotics and Biomimetics (ROBIO)
Source Publication2015 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND BIOMIMETICS (ROBIO)
Conference DateDEC 06-09, 2015
Conference PlaceZhuhai, PEOPLES R CHINA
AbstractFace perception is one of the most important tasks in robot vision especially for service robots. The spatially enhanced local binary pattern histogram (eLBPH) method has been proved to be effective forfacial image representation and analysis, but the expression factor isn't considered and the region-dividing method is rough. In this paper, inspired by the biological mechanism of human memory and face perception, we improve the eLBPH and propose a new method, expression-specific weighted localbinary pattern histogram (EWLBPH). Accordingly, the new method introduces a semantic division process and an extended modulation process into the classical eLBPH. What's more, for the facialexpression recognition, we propose a novel method which utilizes the convolutional deep belief network (CDBN) to extract discriminative information and represent them effectively. Finally, through experiments we verify the rationality and effectiveness of the improvement and two psychophysical findings.
KeywordFace Recognition Classification
Indexed ByEI
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12847
Collection复杂系统管理与控制国家重点实验室_机器人理论与应用
Corresponding AuthorXi, XY
Affiliation1.State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences
2.Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences
3.Institute of Applied Mathematics, AMSS, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Xi, Xuanyang,Qin, Zhengke,Ding, Shuguang,et al. An improved eLBPH method for facial identity recognition: Expression-specific weighted local binary pattern histogram[C],2015.
Files in This Item: Download All
File Name/Size DocType Version Access License
IEEE Xplore下载.pdf(687KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xi, Xuanyang]'s Articles
[Qin, Zhengke]'s Articles
[Ding, Shuguang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xi, Xuanyang]'s Articles
[Qin, Zhengke]'s Articles
[Ding, Shuguang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xi, Xuanyang]'s Articles
[Qin, Zhengke]'s Articles
[Ding, Shuguang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: IEEE Xplore下载.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.