Iris boundaries segmentation using the generalized structure tensor. A study on the effects of image degradation

We present a new iris segmentation algorithm based on the Generalized Structure Tensor (GST), which also includes an eyelid detection step. It is compared with traditional segmentation systems based on Hough transform and integro-differential operators. Results are given using the CASIA-IrisV3-Interval database. Segmentation performance under different degrees of image defocus and motion blur is also evaluated. Reported results shows the effectiveness of the proposed algorithm, with similar performance than the others in pupil detection, and clearly better performance for sclera detection for all levels of degradation. Verification results using 1D Log-Gabor wavelets are also given, showing the benefits of the eyelids removal step. These results point out the validity of the GST as an alternative to other iris segmentation systems.