A Fast Adaboosting Based Method for Iris and Pupil Contour Detection

The iris localization plays a fundamental role in the recognition process because the speed and performance of the iris recognition system largely depends on the quality of the pupil and iris detection. This process includes the detection of inner (pupil) and outer (iris) boundaries. In this paper we present a new method for iris and pupil boundaries detection based on Adaboosting technique for localization of circular objects and an algorithm based on the elements of analytic geometry, in particular, the determination of the bounded circumference of a tangential square that encloses the pupil and iris. The proposed approach overcomes the limitations that had previous methods regarding the use of images obtained under not controlled conditions like specular light reflected in the pupil or in the iris. We experimented our approach comparing the results in detection with the results obtained by Daugman algorithm using images from two contrasting databases, CASIA and UBIRIS.

[1]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[2]  José Francisco Martínez-Trinidad,et al.  Progress in Pattern Recognition, Image Analysis and Applications, 12th Iberoamericann Congress on Pattern Recognition, CIARP 2007, Valparaiso, Chile, November 13-16, 2007, Proceedings , 2008, CIARP.

[3]  Ashok A. Ghatol,et al.  Iris recognition: an emerging biometric technology , 2007 .

[4]  Richard P. Wildes,et al.  Iris recognition: an emerging biometric technology , 1997, Proc. IEEE.

[5]  José Rodríguez,et al.  A New Method for Iris Pupil Contour Delimitation and Its Application in Iris Texture Parameter Estimation , 2005, CIARP.

[6]  Tieniu Tan,et al.  A fast and robust iris localization method based on texture segmentation , 2004, SPIE Defense + Commercial Sensing.

[7]  John Daugman,et al.  High Confidence Visual Recognition of Persons by a Test of Statistical Independence , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  John Daugman,et al.  Demodulation by Complex-Valued Wavelets for Stochastic Pattern Recognition , 2003, Int. J. Wavelets Multiresolution Inf. Process..

[9]  Richard C. Waters,et al.  Mitsubishi Electric Research Laboratories, Inc. , 2000 .

[10]  Richard P. Wildes,et al.  Reliable and fast eye finding in close-up images , 2002, Object recognition supported by user interaction for service robots.