Robust Iris Localisation in Challenging Scenarios
The use of images acquired in unconstrained scenarios is giving rise to new challenges in the field of iris recognition. Many works in literature reported excellent results in both iris segmentation and recognition but mostly with images acquired in controlled conditions. The intention to broaden the field of application of iris recognition, such as airport security or personal identification in mobile devices, is therefore hindered by the inherent unconstrained nature under which images are to be acquired. The proposed work focuses on mutual context information from iris centre and iris limbic and pupillary contours to perform robust and accurate iris segmentation in noisy images. The developed algorithm was tested on the MobBIO database with a promising \(96\,\%\) segmentation accuracy for the limbic contour.
KeywordsBiometrics Iris segmentation Unconstrained environment Gradient flow Shortest closed path
The authors would like to thank Fundação para a Ciência e Tecnologia (FCT) - Portugal the financial support for the PhD grants with references SFRH/ BD/74263/2010 and SFRH/BD/87392/2012.
- 2.Barzegar, N., Moin, M.: A new approach for iris localisation in iris recognition systems. In: Proceedings of the International Conference on Computer Systems and Applications, pp. 516–523 (2008)Google Scholar
- 5.Daugman, J.: How iris recognition works. In: Proceedings of the International Conference on Image Processing. vol. 1, pp. I-33–I-36 (2002)Google Scholar
- 10.Houhou, N., Lemkaddem, A., Duay, V., Alla, A., Thiran, J.P.: Shape prior based on statistical map for active contour segmentation. In: 15th IEEE International Conference on Image Processing, pp. 2284–2287 (2008)Google Scholar
- 16.Masek, L.: Recognition of human iris patterns for biometric identification. Towards non-cooperative biometric iris recognition. Ph.D. thesis (2003)Google Scholar
- 17.Monteiro, J.C., Oliveira, H.P., Rebelo, A., Sequeira, A.F.: MobBIO 2013: 1st Biometric Recognition with Portable Devices Competition (2013). http://paginas.fe.up.pt/~mobBIO2013/
- 18.Monteiro, J.C., Oliveira, H.P., Sequeira, A.F., Cardoso, J.S.: Robust iris segmentation under unconstrained settings. In: Proceedings of International Conference on Computer Vision Theory and Applications (VISAPP), pp. 180–190 (2013)Google Scholar
- 19.Oliveira, H., Cardoso, J., Magalhaes, A., Cardoso, M.: Simultaneous detection of prominent points on breast cancer conservative treatment images. In: Proceedings of the 19th IEEE International Conference on Image Processing. pp. 2841–2844 (2012)Google Scholar
- 20.Pawar, M., Lokande, S., Bapat, V.: Iris segmentation using geodesic active contour for improved texture extraction in recognition. Int. J. Comput. Appl. 47(16), 448–456 (2012)Google Scholar
- 24.Roy, K., Bhattacharya, P., Suen, C., You, J.: Recognition of unideal iris images using region-based active contour model and game theory. In: 17th IEEE International Conference on Image Processing. pp. 1705–1708 (2010)Google Scholar