Deakin home > Deakin University Library > Deakin Research Online > Individual stable space : an approach to face recognition under uncontrolled conditions
Openly accessible

Individual stable space : an approach to face recognition under uncontrolled conditions

Geng, Xin, Zhou, Zhi-Hua and Smith-Miles, K. 2008, Individual stable space : an approach to face recognition under uncontrolled conditions, IEEE transactions on neural networks, vol. 19, no. 8, pp. 1354-1368.

Attached Files (Some files may be inaccessible until you login with your Deakin Research Online credentials)
Name Description MIMEType Size Downloads
geng-individualstable-2008.pdf Published version application/pdf 748.57KB 115

Title Individual stable space : an approach to face recognition under uncontrolled conditions
Author(s) Geng, Xin
Zhou, Zhi-Hua
Smith-Miles, K.
Journal name IEEE transactions on neural networks
Volume number 19
Issue number 8
Start page 1354
End page 1368
Publisher IEEE
Place of publication Piscataway, N.J.
Publication date 2008
ISSN 1045-9227
1941-0093
Keyword(s) Face recognition (FR)
individual stable space (ISS)
machine learning
neural networks
pattern recognition
Summary There usually exist many kinds of variations in face images taken under uncontrolled conditions, such as changes of pose, illumination, expression, etc. Most previous works on face recognition (FR) focus on particular variations and usually assume the absence of others. Instead of such a ldquodivide and conquerrdquo strategy, this paper attempts to directly address face recognition under uncontrolled conditions. The key is the individual stable space (ISS), which only expresses personal characteristics. A neural network named ISNN is proposed to map a raw face image into the ISS. After that, three ISS-based algorithms are designed for FR under uncontrolled conditions. There are no restrictions for the images fed into these algorithms. Moreover, unlike many other FR techniques, they do not require any extra training information, such as the view angle. These advantages make them practical to implement under uncontrolled conditions. The proposed algorithms are tested on three large face databases with vast variations and achieve superior performance compared with other 12 existing FR techniques.
Language eng
Field of Research 080109 Pattern Recognition and Data Mining
HERDC Research category C1 Refereed article in a scholarly journal
HERDC collection year 2008
Copyright notice ©2008, IEEE
Persistent URL http://hdl.handle.net/10536/DRO/DU:30017604

Document type: Journal Article
Collections: School of Engineering and Information Technology
Open Access Collection
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in Deakin Research Online is owned by the author, with all rights reserved.

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 3 times in TR Web of Science
Scopus Citation Count Cited 7 times in Scopus
Access Statistics: 319 Abstract Views, 115 File Downloads  -  Detailed Statistics
Created: Fri, 14 Aug 2009, 13:55:08 EST