Iris Biometrics: Indexing and Retrieving Heavily Degraded Data

Most of the methods to index iris biometric signatures were designed for decision environments with a clear separation between genuine and impostor matching scores. However, in case of less controlled data acquisition, images will be degraded and the decision environments poorly separated. This paper proposes an indexing/retrieval method for degraded images and operates at the code level, making it compatible with different feature encoding strategies. Gallery codes are decomposed at multiple scales, and according to their most reliable components at each scale, the position in an n-ary tree determined. In retrieval, the probe is decomposed similarly, and the distances to multiscale centroids are used to penalize paths in the tree. At the end, only a subset of the branches is traversed up to the last level. When compared with related strategies, the proposed method outperforms them on degraded data, particularly in the performance range most important for biometrics . Finally, according to the computational cost of the retrieval phase, the number of enrolled identities above which indexing is computationally cheaper than an exhaustive search is determined.

[1]  Hugo Proença,et al.  Iris Recognition: On the Segmentation of Degraded Images Acquired in the Visible Wavelength , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Arun Ross,et al.  Indexing iris images using the Burrows-Wheeler Transform , 2010, 2010 IEEE International Workshop on Information Forensics and Security.

[3]  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.

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

[5]  Arun Ross,et al.  Indexing iris images , 2008, 2008 19th International Conference on Pattern Recognition.

[6]  Sistema político,et al.  Unique Identification Authority of India , 2011 .

[7]  Niladri B. Puhan,et al.  Coarse indexing of iris database based on iris colour , 2011, Int. J. Biom..

[8]  David Zhang,et al.  A Novel Method for Coarse Iris Classification , 2006, ICB.

[9]  I. Johnstone,et al.  Ideal spatial adaptation by wavelet shrinkage , 1994 .

[10]  Phalguni Gupta,et al.  An iris retrieval technique based on color and texture , 2010, ICVGIP '10.

[11]  Phalguni Gupta,et al.  Robust iris indexing scheme using geometric hashing of SIFT keypoints , 2010, J. Netw. Comput. Appl..

[12]  Zhenan Sun,et al.  Coarse Iris Classification by Learned Visual Dictionary , 2007, ICB.

[13]  Richa Singh,et al.  Improving Iris Recognition Performance Using Segmentation, Quality Enhancement, Match Score Fusion, and Indexing , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[14]  Jian Fu,et al.  Use of Artificial Color filtering to improve iris recognition and searching , 2005, Pattern Recognit. Lett..

[15]  S. Mallat A wavelet tour of signal processing , 1998 .

[16]  Phalguni Gupta,et al.  Indexing Iris Biometric Database Using Energy Histogram of DCT Subbands , 2009, IC3.

[17]  Qin Zhao,et al.  A new approach for noisy iris database indexing based on color information , 2011, 2011 6th International Conference on Computer Science & Education (ICCSE).

[18]  Feng Hao,et al.  A Fast Search Algorithm for a Large Fuzzy Database , 2008, IEEE Transactions on Information Forensics and Security.

[19]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

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