Show simple item record

AuthorJiang, Richard
AuthorAl-Maadeed, Somaya
AuthorBouridane, Ahmed
AuthorCrookes, Danny
AuthorCelebi, M. Emre
Available date2021-09-01T10:02:41Z
Publication Date2016
Publication NameIEEE Transactions on Information Forensics and Security
ResourceScopus
URIhttp://dx.doi.org/10.1109/TIFS.2016.2555792
URIhttp://hdl.handle.net/10576/22350
AbstractWith the rapid development of Internet-of-Things (IoT), face scrambling has been proposed for privacy protection during IoT-targeted image/video distribution. Consequently, in these IoT applications, biometric verification needs to be carried out in the scrambled domain, presenting significant challenges in face recognition. Since face models become chaotic signals after scrambling/encryption, a typical solution is to utilize the traditional data-driven face recognition algorithms. While chaotic pattern recognition is still a challenging task, in this paper, we propose a new ensemble approach - many-kernel random discriminant analysis (MK-RDA) - to discover discriminative patterns from the chaotic signals. We also incorporate a salience-aware strategy into the proposed ensemble method to handle the chaotic facial patterns in the scrambled domain, where the random selections of features are made on semantic components via salience modeling. In our experiments, the proposed MK-RDA was tested rigorously on three human face data sets: the ORL face data set, the PIE face data set, and the PUBFIG wild face data set. The experimental results successfully demonstrate that the proposed scheme can effectively handle the chaotic signals and significantly improve the recognition accuracy, making our method a promising candidate for secure biometric verification in the emerging IoT applications. 2016 IEEE.
Languageen
PublisherInstitute of Electrical and Electronics Engineers Inc.
SubjectBiometrics
Discriminant analysis
Internet of things
Semantics
Speech recognition
Biometric verification
Face recognition algorithms
face scrambling
Internet of Things (IOT)
many kernels
Mobile biometrics
Recognition accuracy
User privacy
Face recognition
TitleFace Recognition in the Scrambled Domain via Salience-Aware Ensembles of Many Kernels
TypeArticle
Pagination1807-1817
Issue Number8
Volume Number11
dc.accessType Open Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record