Fast Algorithm for Iris Detection
The paper presents a fast algorithm for iris detection. The idea behind the algorithm comes from well-known Daugman’s circular edge detector based on smoothed integro-differential operators. We use binning instead of convolution which is a bit more suitable for new generation of application processors (e.g. AP7000 from Atmel)and new CMOS imagers offering binning on demand. We also reformulated the inner function of the operator. These two steps allow for finding geometrical parameters of iris somewhat faster and with, we believe, comparable robustness offered by Daugman’s solution. In the paper the idea, the implementation and some results of rough tests of the code running on AP7000 application processor are presented. Also, possible improvements are discussed.
Keywordsbinning iris segmentation integro-differential operator
- 1.Jain, A., Bolle, R., Pankanti, S. (eds.): Biometrics: Personal Identification in a Networked Society. Kluwer, Norwell (1999)Google Scholar
- 3.Daugman, J.G.: The importance of being random: statistical principles of iris recognition. Pattern Recognition 36(2), 279–291Google Scholar
- 4.Cho, D.H., Park, K.R., Rhee, D.W.: Real-Time Iris Localization for Iris Recognition in Cellular Phone, snpd-sawn. In: SNPD/SAWN 2005. Sixth Int. Conf. on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing and First ACIS Int. Workshop on Self-Assembling Wireless Networks, pp. 254–259 (2005)Google Scholar
- 5.Feng, X., Fang, C., Ding, X., Wu, Y.: Iris Localization with Dual Coarse-to-fine Strategy. In: ICPR 2006. icpr.18h Int. Conf. on Pattern Recognition, pp. 553–556 (2006)Google Scholar