From the Perspective of CNN to Adversarial Iris Images

IrisCode, the most influential iris recognition algorithm, has been extensively applied in national identity programmes and border controls. Currently over one billion people spanning approximately 170 nationalities have been enrolled in IrisCode. It is vital to thoroughly study this crucial algorithm, especially for issues related to its security. How to generate iris images from its templates is one of such security issues. The existing generation methods can produce images from iris templates and the synthetic images can be used to match other real iris images. However, their quality is very low with obvious artifacts. Considering the feature extraction process of IrisCode as a non-differentiable shallow convolutional neural network and using a differentiable function to approximate its step function, the generation process can be formulated as an unconstrained minimization problem. It can be mathematically proven that the solution of this formulation is the same as that of the convex polyhedral cone method proposed before. By exploiting the unconstrained formulation and the step function directly, a constrained convex minimization formulation with an inputted iris image selected by a search function as an information carrier is derived. The experimental results on the UBIRIS.v1 database and the WVU database demonstrate that the proposed algorithm can generate high quality iris images and significantly outperform the previous methods in terms of visual quality and six image quality metrics. They can also be matched with other real iris images in the two databases.

[1]  Adams Wai-Kin Kong,et al.  Modeling IrisCode and Its Variants as Convex Polyhedral Cones and Its Security Implications , 2013, IEEE Transactions on Image Processing.

[2]  Alex ChiChung Kot,et al.  An Improved Scheme for Full Fingerprint Reconstruction , 2012, IEEE Transactions on Information Forensics and Security.

[3]  K.W. Bowyer,et al.  The Best Bits in an Iris Code , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Alan C. Bovik,et al.  Making a “Completely Blind” Image Quality Analyzer , 2013, IEEE Signal Processing Letters.

[5]  David Zhang,et al.  An Analysis of IrisCode , 2010, IEEE Transactions on Image Processing.

[6]  Seyed-Mohsen Moosavi-Dezfooli,et al.  Universal Adversarial Perturbations , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  John Daugman,et al.  High Confidence Visual Recognition of Persons by a Test of Statistical Independence , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Tieniu Tan,et al.  Ordinal palmprint represention for personal identification [represention read representation] , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[9]  Alan C. Bovik,et al.  Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality , 2011, IEEE Transactions on Image Processing.

[10]  Hugo Proença,et al.  IRINA: Iris Recognition (Even) in Inaccurately Segmented Data , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  A. Ross,et al.  Segmenting Non-Ideal Irises Using Geodesic Active Contours , 2006, 2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference.

[12]  Fei Zhou,et al.  Comparative competitive coding for personal identification by using finger vein and finger dorsal texture fusion , 2014, Inf. Sci..

[13]  Marios Savvides,et al.  How to Generate Spoofed Irises From an Iris Code Template , 2011, IEEE Transactions on Information Forensics and Security.

[14]  Anil K. Jain,et al.  Learning Fingerprint Reconstruction: From Minutiae to Image , 2015, IEEE Transactions on Information Forensics and Security.

[15]  Yilong Yin,et al.  Learning discriminative binary codes for finger vein recognition , 2017, Pattern Recognit..

[16]  Adams Wai-Kin Kong,et al.  IrisCode Decompression Based on the Dependence between Its Bit Pairs , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Luís A. Alexandre,et al.  UBIRIS: A Noisy Iris Image Database , 2005, ICIAP.

[18]  John Daugman,et al.  How iris recognition works , 2002, IEEE Transactions on Circuits and Systems for Video Technology.

[19]  Yang Hu,et al.  Optimal Generation of Iris Codes for Iris Recognition , 2017, IEEE Transactions on Information Forensics and Security.

[20]  Patrick J. Flynn,et al.  Improved Iris Recognition through Fusion of Hamming Distance and Fragile Bit Distance , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  John Daugman,et al.  Information Theory and the IrisCode , 2016, IEEE Transactions on Information Forensics and Security.

[22]  Alan C. Bovik,et al.  Blind/Referenceless Image Spatial Quality Evaluator , 2011, 2011 Conference Record of the Forty Fifth Asilomar Conference on Signals, Systems and Computers (ASILOMAR).

[23]  Liping Yan,et al.  Palmprint Recognition Using Neighboring Direction Indicator , 2016, IEEE Transactions on Human-Machine Systems.

[24]  Hugo Proenca Iris Recognition: What Is Beyond Bit Fragility? , 2015, IEEE Transactions on Information Forensics and Security.

[25]  John Daugman,et al.  600 million citizens of India are now enrolled with biometric ID , 2014 .

[26]  John Daugman,et al.  New Methods in Iris Recognition , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[27]  Adams Wai-Kin Kong A Statistical Analysis of IrisCode and Its Security Implications , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Patrizio Campisi,et al.  Hill-Climbing Attacks on Multibiometrics Recognition Systems , 2015, IEEE Transactions on Information Forensics and Security.