Iris Recognition in Nonideal Situations
Most of the state-of-the-art iris recognition algorithms focus on processing and recognition of the ideal iris images which are captured in a controlled environment. In this paper, we process the nonideal iris images which are acquired in an unconstrained situation and are affected severely by gaze deviation, eyelids and eyelashes occlusion, non uniform intensity, motion blur, reflections, etc. To segment the nonideal iris images accurately, we deploy a variational level set based curve evolution scheme, which uses significantly larger time step for numerically solving the evolution partial differential equation (PDE), and therefore, speeds up the curve evolution process drastically. Genetic Algorithms (GAs) are deployed to select the subset of informative features by combining the valuable outcomes from the multiple feature selection criteria without compromising the recognition accuracy. The verification performance of the proposed scheme is validated using three nonideal iris datasets, namely, UBIRIS Version 2, ICE 2005, and WVU datasets.
KeywordsIris recognition variational level set method curve evolution genetic algorithms nonideal situations
Unable to display preview. Download preview PDF.
- 5.Ross, A., Shah, S.: Segmenting non-ideal irises using geodesic active contours. In: Biometric Consortium Conference, IEEE Biometrics symposium, pp. 1–6 (2006)Google Scholar
- 6.Li, C., Xu, C., Gui, C., Fox, M.D.: Level set evolution without re-initialization: a new variational formulation. In: Int. Conf. on Comp. Vis. and Pattern Recog., vol. 1, pp. 430–436 (2005)Google Scholar
- 8.Roy, K., Bhattacharya, P.: Adaptive asymmetrical SVM and genetic algorithms based iris recognition. In: Int. Conf. on Pattern Recog., pp. 1–4 (2008)Google Scholar
- 9.Roy, K., Bhattacharya, P.: Level set approaches and adaptive asymmetrical SVMs applied for nonideal iris recognition. In: Kamel, M., Campilho, A. (eds.) ICIAR 2009. LNCS, vol. 5627, pp. 418–428. Springer, Heidelberg (2009)Google Scholar
- 12.Iris Challenge Evaluation (ICE) dataset found, http://iris.nist.gov/ICE/
- 13.Iris Dataset obtained from West Virginia University (WVU), http://www.wvu.edu/
- 14.UBIRIS dataset obtained from department of computer science, University of Beira Interior, Portugal, http://iris.di.ubi.pt/