Robust varying-resolution iris recognition

A less intrusive iris capturing system usually requires a long stand-off distance, large capture volume, and no restriction of a static subject. These factors make iris recognition more challenging than that from today's close-range iris systems. In this paper we propose a novel algorithm toward robust iris recognition in less intrusive environments. Our algorithm consists of two parts: 1) a novel iris segmentation method that can handle variable resolutions (from 50 pixels to 350 pixels), lighting, and partial occlusion, which can cause the majority of pixels or edges in a captured image are outliers. 2) a new feature encoding method that is robust for non-ideal iris images due to noise, blur, occlusion, and down-sampling. Through a careful analysis of the iris image acquisition process and extensive simulation, we show that, contrary to the common belief that iris diameter has a significant impact on recognition accuracy, it is the image noise that reduces accuracy in low resolution images when an accurate segmentation can be obtained. Using high-quality low noise images acquired by digital SLR cameras, we showed that our iris recognition algorithm can achieve state-of-the-art performance (e.g., FRR at 0.0015 with FAR 0.001) on very low resolution images with iris diameter around 60 pixels.

[1]  Jitendra Malik,et al.  Learning Probabilistic Models for Contour Completion in Natural Images , 2008, International Journal of Computer Vision.

[2]  Ashok A. Ghatol,et al.  Iris recognition: an emerging biometric technology , 2007 .

[3]  Gang Song,et al.  Untangling Cycles for Contour Grouping , 2007, 2007 IEEE 11th International Conference on Computer Vision.

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

[5]  Damon L. Woodard,et al.  Non-ideal iris segmentation using graph cuts , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[6]  Naphtali Rishe,et al.  A highly accurate and computationally efficient approach for unconstrained iris segmentation , 2010, Image Vis. Comput..

[7]  Xin Li.  Modeling Intra-class Variation for Nonideal Iris Recognition , 2006, ICB.

[8]  Ruigang Yang,et al.  Image deblurring for less intrusive iris capture , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  H. Proenca,et al.  The NICE.I: Noisy Iris Challenge Evaluation - Part I , 2007, 2007 First IEEE International Conference on Biometrics: Theory, Applications, and Systems.

[11]  Bin Li,et al.  Iris Recognition Algorithm Using Modified Log-Gabor Filters , 2006, 18th International Conference on Pattern Recognition (ICPR'06).

[12]  Guodong Guo,et al.  A System for Automatic Iris Capturing , 2005 .

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

[14]  Tieniu Tan,et al.  Efficient and robust segmentation of noisy iris images for non-cooperative iris recognition , 2010, Image Vis. Comput..

[15]  Marios Savvides,et al.  Unconstrained Iris Acquisition and Recognition Using COTS PTZ Camera , 2010, EURASIP J. Adv. Signal Process..

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

[17]  Patrick J. Flynn,et al.  Experiments with an improved iris segmentation algorithm , 2005, Fourth IEEE Workshop on Automatic Identification Advanced Technologies (AutoID'05).

[18]  James R. Matey,et al.  Iris on the Move: Acquisition of Images for Iris Recognition in Less Constrained Environments , 2006, Proceedings of the IEEE.

[19]  Dexin Zhang,et al.  DCT-Based Iris Recognition , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Tieniu Tan,et al.  Toward Accurate and Fast Iris Segmentation for Iris Biometrics , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[22]  Kang Ryoung Park,et al.  A new iris segmentation method for non-ideal iris images , 2010, Image Vis. Comput..

[23]  Arun Ross,et al.  Iris Segmentation Using Geodesic Active Contours , 2009, IEEE Transactions on Information Forensics and Security.

[24]  Luís A. Alexandre,et al.  The UBIRIS.v2: A Database of Visible Wavelength Iris Images Captured On-the-Move and At-a-Distance , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.