Improving Video-based Iris Recognition Via Local Quality Weighted Super Resolution

In this paper we address the problem of iris recognition at a distance and on the move. We introduce two novel quality measures, one computed Globally (GQ) and the other Locally (LQ), for fusing at the pixel level the frames (after a bilinear interpolation step) extracted from the video of a given person. These measures derive from a local GMM probabilistic characterization of good quality iris texture. Experiments performed on the MBGC portal database show a superiority of our approach compared to score-based or average image-based fusion methods. Moreover, we show that the LQ-based fusion outperforms the GQ-based fusion with a relative improvement of 4.79% at the Equal Error Rate functioning point

[1]  G. Fahmy.  Super-Resolution Construction of IRIS Images from a Visual Low Resolution Face Video , 2007, 2007 National Radio Science Conference.

[2]  Dexin Zhang,et al.  Efficient iris recognition by characterizing key local variations , 2004, IEEE Transactions on Image Processing.

[3]  Arun Ross,et al.  Information fusion in low-resolution iris videos using Principal Components Transform , 2011, 2011 IEEE Workshop on Applications of Computer Vision (WACV).

[4]  Sridha Sridharan,et al.  Quality-Driven Super-Resolution for Less Constrained Iris Recognition at a Distance and on the Move , 2011, IEEE Transactions on Information Forensics and Security.

[5]  Bernadette Dorizzi,et al.  How a local quality measure can help improving iris recognition , 2012, 2012 BIOSIG - Proceedings of the International Conference of Biometrics Special Interest Group (BIOSIG).

[6]  Patrick J. Flynn,et al.  Iris Recognition Using Signal-Level Fusion of Frames From Video , 2009, IEEE Transactions on Information Forensics and Security.

[7]  B. Dorizzi,et al.  A new probabilistic Iris Quality Measure for comprehensive noise detection , 2007, 2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems.

[8]  S. Sridharan,et al.  Focus-score weighted super-resolution for uncooperative iris recognition at a distance and on the move , 2010, 2010 25th International Conference of Image and Vision Computing New Zealand.

[9]  Bernadette Dorizzi,et al.  The Viterbi algorithm at different resolutions for enhanced iris segmentation , 2012, 2012 5th IAPR International Conference on Biometrics (ICB).

[10]  Bernadette Dorizzi,et al.  Specific Texture Analysis for Iris Recognition , 2005, AVBPA.

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

[12]  Shaogang Gong,et al.  Audio- and Video-based Biometric Person Authentication , 1997, Lecture Notes in Computer Science.

[13]  Sridha Sridharan,et al.  Feature-domain super-resolution for iris recognition , 2011, 2011 18th IEEE International Conference on Image Processing.