Iris Segmentation Using the Generalized Structure Tensor
2012 (English)Conference paper, Presentation (Other academic)
We present a new iris segmentation algorithm based on the Generalized Structure Tensor (GST). We compare this approach with traditional iris segmentation systems based on Hough transform and integro-differential operators. Results are given using the CASIA-IrisV3-Interval database with respect to a segmentation made manually by a human expert. The proposed algorithm outperforms the baseline approaches, pointing out the validity of the GST as an alternative to classic iris segmentation systems. We also detect the cross positions between the eyelids and the outer iris boundary. Verification results using a publicly available iris recognition system based on 1D Log-Gabor wavelets are also given, showing the benefits of the eyelids removal step.
Place, publisher, year, edition, pages
IdentifiersURN: urn:nbn:se:hh:diva-19478OAI: oai:DiVA.org:hh-19478DiVA: diva2:549739
SSBA Symposium 2012 (SSBA2012), Stockholm, Sweden, 8-9 mars, 2012