Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Face Recognition in the Scrambled Domain via Salience-Aware Ensembles of Many Kernels
AU - Jiang, Richard
AU - Al-Maadeed, Somaya
AU - Bouridane, Ahmed
AU - Crookes, Danny
AU - Celebi, M. Emre
PY - 2016/8/1
Y1 - 2016/8/1
N2 - With 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.
AB - With 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.
KW - Facial biometrics
KW - face scrambling
KW - many manifolds
KW - many kernels
KW - random discriminant analysis
KW - mobile biometrics
KW - Internet-of-things
KW - user privacy
U2 - 10.1109/TIFS.2016.2555792
DO - 10.1109/TIFS.2016.2555792
M3 - Journal article
VL - 11
SP - 1807
EP - 1817
JO - IEEE Transactions on Information Forensics and Security
JF - IEEE Transactions on Information Forensics and Security
SN - 1556-6013
IS - 8
ER -