FPD: A New Algorithm for Iris Matching and Evaluation Based on Frequency-modulated Phase Difference

Iris recognition is one of the most widely used biometric technologies because of its high reliability and accuracy. While iris recognition usually comprises multiple phases, this paper focuses on two key procedures: iris matching and evaluation. The state-of-the-art of both steps, i.e., Daugman's matching and evaluation algorithms, rely on Hamming Distance. In this paper, we propose a more efficient algorithm based on Frequency-modulated Phase Difference (FPD) in Fourier space. Because FPD is frequency-aware, it effectively detects iris texture landing within particular frequency ranges and significantly improves the matching efficiency. Experiments are carried out on multiple images database showing that FPD is 2.6X faster than Daugman's method while preserving the latter's high accuracy.

[1]  John Daugman,et al.  The importance of being random: statistical principles of iris recognition , 2003, Pattern Recognit..

[2]  Weijie Zhao,et al.  A novel iris patterns matching algorithm of weighted polar frequency correlation , 2014, Other Conferences.

[3]  Andrew P. Paplinski,et al.  Optimization of Iris Codes for Improved Recognition , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops.

[4]  David Chandler,et al.  Biometric Product Testing Final Report , 2001 .

[5]  Arun Ross,et al.  An introduction to biometric recognition , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[6]  Ching Y. Suen,et al.  Towards nonideal iris recognition based on level set method, genetic algorithms and adaptive asymmetrical SVMs , 2011, Eng. Appl. Artif. Intell..

[7]  Philip J. Morrow,et al.  Iris recognition failure over time: The effects of texture , 2012, Pattern Recognit..

[8]  John Daugman,et al.  Statistical Richness of Visual Phase Information: Update on Recognizing Persons by Iris Patterns , 2001, International Journal of Computer Vision.

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

[10]  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.

[11]  Manesh Kokare,et al.  Iris Recognition Without Iris Normalization , 2010 .

[12]  Ching Y. Suen,et al.  Iris segmentation using variational level set method , 2011 .

[13]  Chin-Wang Tao,et al.  Iris Recognition Using Possibilistic Fuzzy Matching on Local Features , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[14]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[15]  Wei Li,et al.  A Novel Iris Location Method for Fast Iris Recognition , 2009, 2009 2nd International Congress on Image and Signal Processing.

[16]  Wei Li,et al.  Fast Iris Segmentation by Rotation Average Analysis of Intensity-Inversed Image , 2009, AICI.

[17]  Dexin Zhang,et al.  Personal Identification Based on Iris Texture Analysis , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

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

[19]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Richard P. Wildes,et al.  Iris recognition: an emerging biometric technology , 1997, Proc. IEEE.

[22]  Jane You,et al.  Recognition of unideal iris images using region-based active contour model and game theory , 2010, 2010 IEEE International Conference on Image Processing.