Iris Localization Using Mixture of Gamma Distributions in the Segmentation Process

This paper contributes to more accurate iris segmentation. We propose a new approach for iris image segmentation based on mixture of Gamma distributions modeling and an extended Expectation Maximization (EM) algorithm. We apply our approach to segment iris images from the CASIA (Chinese Academy of Sciences Institute of Automation)-Iris-Twins testing database. The accuracy of our algorithm is proved based on Kullback Leibler distance computation.

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

[2]  Surjeet Singh,et al.  Segmentation Techniques for Iris Recognition System , 2011 .

[3]  Seongwon Cho,et al.  Iris Recognition Using Wavelet Features , 2004, J. VLSI Signal Process..

[4]  N. Ueda,et al.  Mixture density estimation via EM algorithm with deterministic annealing , 1994, Proceedings of IEEE Workshop on Neural Networks for Signal Processing.

[5]  Peihua Li,et al.  Robust and accurate iris segmentation in very noisy iris images , 2010, Image Vis. Comput..

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

[7]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

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

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

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

[11]  R. Redner,et al.  Mixture densities, maximum likelihood, and the EM algorithm , 1984 .

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