Optimizing Discriminability of Globally Binarized Face Templates

Biometric systems are being increasingly deployed in various applications such as smartphones, passports and visa control, health cards, and crime investigation applications. Storing individuals biometric templates in the biometric system database makes it susceptible to threats. As a result, many biometric template protection schemes have been proposed in order to provide the protection for the biometric data against unauthorized use. Extracting binary templates from real-valued biometric data is an important stage in biometric template protection systems. Moreover, representing biometric data as binary template can speed up the biometric template processing and reduce the storage capacity needed to store the enrolled templates. Global binarization schemes binarize the original real-valued biometric template using a series of transformation functions applied to the entire template. The main defy of any global binarization scheme is the generation of such transformation functions which optimize the within-class variance and between-class variance for the transformed binary template simultaneously. In this paper, we propose a global biometric data binarization scheme that utilizes genetic algorithm to optimize the within-class variance and between-class variance for the transformed binary template simultaneously, which retains the discriminability of the binary template. Experimental results using face data sets demonstrated promising recognition performance without violating the security needs of the biometric system.

[1]  Pong C. Yuen,et al.  Binary Discriminant Analysis for Generating Binary Face Template , 2012, IEEE Transactions on Information Forensics and Security.

[2]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[3]  Pong C. Yuen,et al.  Class-Distribution Preserving Transform for Face Biometric Data Security , 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

[4]  Raymond N. J. Veldhuis,et al.  Practical Biometric Authentication with Template Protection , 2005, AVBPA.

[5]  Evgeny Verbitskiy,et al.  RELIABLE BIOMETRIC AUTHENTICATION WITH PRIVACY PROTECTION , 2007 .

[6]  Jean-Paul M. G. Linnartz,et al.  New Shielding Functions to Enhance Privacy and Prevent Misuse of Biometric Templates , 2003, AVBPA.

[7]  Andrew Beng Jin Teoh,et al.  An effective biometric discretization approach to extract highly discriminative, informative, and privacy-protective binary representation , 2011, EURASIP J. Adv. Signal Process..

[8]  Hao Feng,et al.  Private key generation from on-line handwritten signatures , 2002, Inf. Manag. Comput. Secur..

[9]  P. A. Ramamoorthy,et al.  Principal Component Analysis Based Feature Extraction, Morphological Edge Detection and Localization for Fast Iris Recognition , 2012 .

[10]  Chun Chen,et al.  Biometric Quantization through Detection Rate Optimized Bit Allocation , 2009, EURASIP J. Adv. Signal Process..

[11]  Andrew Beng Jin Teoh,et al.  An analysis on equal width quantization and linearly separable subcode encoding-based discretization and its performance resemblances , 2011, EURASIP J. Adv. Signal Process..

[12]  Chong-Yung Chi,et al.  Non-Cancellation Multistage Kurtosis Maximization with Prewhitening for Blind Source Separation , 2007, 2007 Conference Record of the Forty-First Asilomar Conference on Signals, Systems and Computers.

[13]  Sushma Jaiswal,et al.  BIOMETRIC: CASE STUDY , 2011 .

[14]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[15]  Meng-Hui Lim,et al.  Linearly Separable SubCode: A novel output label with high separability for biometric discretization , 2010, 2010 5th IEEE Conference on Industrial Electronics and Applications.

[16]  Ralf Steinmetz,et al.  Biometric hash based on statistical features of online signatures , 2002, Object recognition supported by user interaction for service robots.

[17]  Andreas Uhl,et al.  A survey on biometric cryptosystems and cancelable biometrics , 2011, EURASIP J. Inf. Secur..

[18]  David G. Stork,et al.  Pattern Classification , 1973 .

[19]  Pong C. Yuen,et al.  Selection of Distinguish Points for Class Distribution Preserving Transform for Biometric Template Protection , 2007, ICB.

[20]  Pong C. Yuen,et al.  Vulnerabilities in binary face template , 2012, 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[21]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[22]  Andrew Beng Jin Teoh,et al.  Cancellable biometrics and user-dependent multi-state discretization in BioHash , 2009, Pattern Analysis and Applications.

[23]  S. Kotsiantis,et al.  Discretization Techniques: A recent survey , 2006 .

[24]  Hyeonjoon Moon,et al.  The FERET Evaluation Methodology for Face-Recognition Algorithms , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Tsuhan Chen,et al.  Biometrics-based cryptographic key generation , 2004, 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763).

[26]  Yevgeniy Dodis,et al.  Fuzzy Extractors: How to Generate Strong Keys from Biometrics and Other Noisy Data , 2004, EUROCRYPT.

[27]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[28]  Pong C. Yuen,et al.  Binary Discriminant Analysis for Face Template Protection , 2010, 2010 20th International Conference on Pattern Recognition.