Title :
A segmentation perturbation method for improved iris recognition
Author :
Thompson, J.W. ; Flynn, P.J.
Author_Institution :
Dept. of Comput. Sci. & Eng., Univ. of Notre Dame, Notre Dame, IN, USA
Abstract :
A new approach for iris recognition is presented. Perturbations of iris segmentations generated by an existing algorithm are used to generate probe templates that are compared to gallery templates. Information from the perturbation match score distributions is used to boost the recognition accuracy of the original algorithm. Experiments with the technique show performance improvements ranging from 24% to 35%.
Keywords :
image segmentation; iris recognition; improved iris recognition; perturbation match score distributions; segmentation perturbation method; Active contours; Eyelids; Hamming distance; Image segmentation; Iris; Iris recognition; Probes;
Conference_Titel :
Biometrics: Theory Applications and Systems (BTAS), 2010 Fourth IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
978-1-4244-7581-0
Electronic_ISBN :
978-1-4244-7580-3
DOI :
10.1109/BTAS.2010.5634499
