An Automatic Algorithm for Evaluating the Precision of Iris Segmentation

Recent developments in the field of nonideal iris recognition have shown that the presence of the degradations such as insufficient contrast, unbalanced illumination, out-of-focus, motion blur, specular reflections, and partial area affect performance of iris recognition systems. Most iris recognition systems are designed to implement a number of processing steps with iris segmentation being one of the first steps. If segmentation is not performed at a certain precision, the error of segmentation will further propagate and will be amplified during the proceeding processing, encoding, and matching steps. This emphasizes a critical need in designing robust iris segmentation algorithms and together with it a need of automatic algorithms evaluating the precision (accuracy) of iris segmentation. Automatic algorithm evaluating the precision of segmentation plays important role for two reasons: (1) it can be placed into a feedback loop to enforce another run of segmentation algorithm that may include more sophisticated steps for high precision segmentation and (2) the outcome of this evaluation can be treated as a quality factor and thus can be used to design a quality driven adaptive iris recognition system. This work analyzes effects of degradations on iris segmentation and proposes and tests an automatic algorithm evaluating the precision of iris segmentation.

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

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

[3]  Anil K. Jain,et al.  Localized Iris Image Quality Using 2-D Wavelets , 2006, ICB.

[4]  Yuanning Liu,et al.  A quality evaluation method of iris images sequence based on wavelet coefficients in "region of interest" , 2004, The Fourth International Conference onComputer and Information Technology, 2004. CIT '04..

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

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

[7]  John Daugman,et al.  Probing the Uniqueness and Randomness of IrisCodes: Results From 200 Billion Iris Pair Comparisons , 2006, Proceedings of the IEEE.

[8]  Luís A. Alexandre,et al.  Iris segmentation methodology for non-cooperative recognition , 2006 .

[9]  D. M. Etter,et al.  Analysis of partial iris recognition , 2005, SPIE Defense + Commercial Sensing.

[10]  Ronald Chung,et al.  Iris Recognition for Iris Titled in Depth , 2003, CAIP.

[11]  Yingzi Du,et al.  Information distance-based selective feature clarity measure for iris recognition , 2007, Electronic Imaging.

[12]  Natalia A. Schmid,et al.  Image quality assessment for iris biometric , 2006, SPIE Defense + Commercial Sensing.

[13]  Luca Bogoni,et al.  Iris Recognition at a Distance , 2005, AVBPA.

[14]  Jinyu Zuo,et al.  A Robust IRIS Segmentation Procedure for Unconstrained Subject Presentation , 2006, 2006 Biometrics Symposium: Special Session on Research at the Biometric Consortium Conference.

[15]  John Daugman,et al.  High Confidence Visual Recognition of Persons by a Test of Statistical Independence , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Natalia A. Schmid,et al.  Performance evaluation of non-ideal iris based recognition system implementing global ICA encoding , 2005, IEEE International Conference on Image Processing 2005.