Comprehensive assessment of iris image quality

Iris image quality critically determines iris recognition performance and the quality metrics of iris images are also useful prior information for adaptive selection of optimal recognition strategy. Iris image quality is jointly determined by multiple factors such as focus, occlusion, off-angle, deformation, etc. So it is a complex problem to assess the overall quality score of an iris image. This paper proposes a novel framework for comprehensive assessment of iris image quality. The contributions of the paper include three aspects: (i) Three novel approaches are proposed to estimate the quality metrics (QM) of defocus, motion blur and off-angle in an iris image respectively, (ii) A fusion method based on likelihood ratio is proposed to combine six quality factors of an iris image into an unified quality score. (iii) A statistical quantization method based on t-test is proposed to adaptively classify the iris images in a database into a number of quality levels. Extensive experiments demonstrate the proposed framework can effectively assess the overall quality of iris images. And the relationship between iris recognition results and the quality level of iris images can be explicitly formulated.

[1]  Natalia A. Schmid,et al.  Global and local quality measures for NIR iris video , 2009, 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[2]  Natalia A. Schmid,et al.  Adaptive biometric authentication using nonlinear mappings on quality measures and verification scores , 2010, 2010 IEEE International Conference on Image Processing.

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

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

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

[6]  Tieniu Tan,et al.  Robust and Fast Assessment of Iris Image Quality , 2006, ICB.

[7]  Yingzi Du,et al.  A Selective Feature Information Approach for Iris Image-Quality Measure , 2008, IEEE Transactions on Information Forensics and Security.

[8]  Anil K. Jain,et al.  Likelihood Ratio-Based Biometric Score Fusion , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Elham Tabassi,et al.  Performance of Biometric Quality Measures , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Tieniu Tan,et al.  Ordinal Measures for Iris Recognition , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Alin Achim,et al.  18th IEEE International Conference on Image Processing, ICIP 2011, Brussels, Belgium, September 11-14, 2011 , 2011, ICIP.

[12]  Natalia A. Schmid,et al.  Estimating and Fusing Quality Factors for Iris Biometric Images , 2010, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.