Sectored Random Projections for Cancelable Iris Biometrics

TitleSectored Random Projections for Cancelable Iris Biometrics
Publication TypeConference Papers
Year of Publication2010
AuthorsPillai JK, Patel VM, Chellappa R, Ratha NK
Conference Name2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)
Date Published2010/03//
ISBN Number978-1-4244-4295-9
Keywordsbiometric pattern, Biometrics, Cancelable Biometrics, cancelable iris biometrics, data mining, data privacy, Degradation, Eyelashes, Eyelids, Iris, iris recognition, pattern recognition, privacy, random processes, Random Projections, Robustness, sectored random projection, Secure Biometrics, Security, security of data

Privacy and security are essential requirements in practical biometric systems. In order to prevent the theft of biometric patterns, it is desired to modify them through revocable and non invertible transformations called Cancelable Biometrics. In this paper, we propose an efficient algorithm for generating a Cancelable Iris Biometric based on Sectored Random Projections. Our algorithm can generate a new pattern if the existing one is stolen, retain the original recognition performance and prevent extraction of useful information from the transformed patterns. Our method also addresses some of the drawbacks of existing techniques and is robust to degradations due to eyelids and eyelashes.