PRNU-based detection of morphed face images

In the recent past, face recognition systems have been found to be highly vulnerable to attacks based on morphed biometrie samples. Such attacks pose a severe security threat to biometric recognition systems across various applications. Apart from some algorithms, which have been reported to reveal practical detection performance on small in-house datasets, approaches to effectively detect morphed face images of high quality have remained elusive. In this paper, we propose a morph detection algorithm based on an analysis of photo response non-uniformity (PRNU). It is based on a spectral analysis of the variations within the PRNU caused by the morphing process. On a comprehensive database of 961 bona fide and 2,414 morphed face images practical performance in terms of detection equal error rate (D-EER) is achieved. Additionally, the robustness of the proposed morph detection algorithm towards different post-processing procedures, e.g. histogram equalization or sharpening, is assessed.

[1]  Kannan Ramchandran,et al.  Spatially adaptive statistical modeling of wavelet image coefficients and its application to denoising , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[2]  Jana Dittmann,et al.  Modeling Attacks on Photo-ID Documents and Applying Media Forensics for the Detection of Facial Morphing , 2017, IH&MMSec.

[3]  J. Fridrich,et al.  Digital image forensics , 2009, IEEE Signal Processing Magazine.

[4]  Xufeng Lin,et al.  Enhancing Sensor Pattern Noise via Filtering Distortion Removal , 2016, IEEE Signal Processing Letters.

[5]  Jessica Fridrich,et al.  Sensor Defects in Digital Image Forensic , 2013 .

[6]  Sébastien Marcel,et al.  Biometric Systems under Morphing Attacks: Assessment of Morphing Techniques and Vulnerability Reporting , 2017, 2017 International Conference of the Biometrics Special Interest Group (BIOSIG).

[7]  Jan Lukás,et al.  Camera identification from printed images , 2008, Electronic Imaging.

[8]  Jana Dittmann,et al.  Benchmarking face morphing forgery detection: Application of stirtrace for impact simulation of different processing steps , 2017, 2017 5th International Workshop on Biometrics and Forensics (IWBF).

[9]  Nalini K. Ratha,et al.  Enhancing security and privacy in biometrics-based authentication systems , 2001, IBM Syst. J..

[10]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[11]  Mo Chen,et al.  Determining Image Origin and Integrity Using Sensor Noise , 2008, IEEE Transactions on Information Forensics and Security.

[12]  Davis E. King,et al.  Dlib-ml: A Machine Learning Toolkit , 2009, J. Mach. Learn. Res..

[13]  Kiran B. Raja,et al.  On the vulnerability of face recognition systems towards morphed face attacks , 2017, 2017 5th International Workshop on Biometrics and Forensics (IWBF).

[14]  Sébastien Marcel,et al.  Handbook of Biometric Anti-Spoofing , 2019, Advances in Computer Vision and Pattern Recognition.

[15]  Davide Maltoni,et al.  The magic passport , 2014, IEEE International Joint Conference on Biometrics.

[16]  Christoph Busch,et al.  Is your biometric system robust to morphing attaeks? , 2017, 2017 5th International Workshop on Biometrics and Forensics (IWBF).

[17]  Davide Maltoni,et al.  On the Effects of Image Alterations on Face Recognition Accuracy , 2016, Face Recognition Across the Imaging Spectrum.

[18]  Kiran B. Raja,et al.  Transferable Deep-CNN Features for Detecting Digital and Print-Scanned Morphed Face Images , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).