Computationally Efficient Serial Combination of Rotation-invariant and Rotation Compensating Iris Recognition Algorithms

Rotation compensation is one of the computational bottlenecks in large scale iris-based identification schemes, since a significant amount of Hamming distance computations is required in a single match due to the necessary shifting of the iris codes to compensate for eye tilt. To cope with this problem, a serial classifier combination approach is proposed for iris-based identification, combining rotation-invariant pre-selection with a traditional rotation compensating iris code-based scheme. The primary aim, a reduction of computational complexity, can easily be met at comparable recognition accuracy, the computational effort required is reduced to 20% or even less of the fully fledged iris code based scheme. As a by-product, the recognition accuracy is shown to be additionally improved in open-set scenarios.

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

[2]  Andreas Uhl,et al.  Parallel versus Serial Classifier Combination for Multibiometric Hand-Based Identification , 2009, ICB.

[3]  Mayank Vatsa,et al.  Reducing the False Rejection Rate of Iris Recognition Using Textural and Topological Features , 2008 .

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

[5]  Arun Ross,et al.  Handbook of Multibiometrics , 2006, The Kluwer international series on biometrics.

[6]  Peng-Fei Zhang,et al.  A novel iris recognition method based on feature fusion , 2004, Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826).

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

[8]  Chul-Hyun Park,et al.  Extracting and Combining Multimodal Directional Iris Features , 2006, ICB.

[9]  Andreas Uhl,et al.  Rotation-invariant Iris Recognition - Boosting 1D Spatial-domain Signatures to 2D , 2008, ICINCO-SPSMC.

[10]  Thad Welch,et al.  Use of one-dimensional iris signatures to rank iris pattern similarities , 2006 .

[11]  Tieniu Tan,et al.  Improving iris recognition accuracy via cascaded classifiers , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

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

[13]  Nalini Ratha,et al.  An efficient, two-stage iris recognition system , 2009, 2009 IEEE 3rd International Conference on Biometrics: Theory, Applications, and Systems.