论文信息 - Information analysis of iris biometrics for the needs of cryptology key extraction

Information analysis of iris biometrics for the needs of cryptology key extraction

The paper presents a rigorous analysis of iris biometric information for the synthesis of an optimized system for the extraction of a high quality cryptology key. Estimations of local entropy and mutual information were identified as segments of the iris most suitable for this purpose. In order to optimize parameters, corresponding wavelets were transformed, in order to obtain the highest possible entropy and mutual information lower in the transformation domain, which set frameworks for the synthesis of systems for the extraction of truly random sequences of iris biometrics, without compromising authentication properties. [Projekat Ministarstva nauke Republike Srbije, br. TR32054 i br. III44006]

Saša Adamović | Milan Milosavljević | S. Adamovic | M. Milosavljevic

[1] Peter Kovesi,et al. MATLAB Functions for Computer Vision and Image Analysis , 2004 .

[2] Jaihie Kim,et al. Iris Feature Extraction Using Independent Component Analysis , 2003, AVBPA.

[3] D. Kerbyson,et al. Circle detection using Hough transform filters , 1995 .

[4] Feng Hao,et al. Combining Crypto with Biometrics Effectively , 2006, IEEE Transactions on Computers.

[5] John Daugman. How iris recognition works , 2004 .

[6] Carmen Sánchez Ávila,et al. Two different approaches for iris recognition using Gabor filters and multiscale zero-crossing representation , 2005, Pattern Recognit..

[7] Patrick J. Flynn,et al. Image understanding for iris biometrics: A survey , 2008, Comput. Vis. Image Underst..

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