TY - CONF T1 - Sectored Random Projections for Cancelable Iris Biometrics T2 - 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) Y1 - 2010 A1 - Pillai,J.K. A1 - Patel, Vishal M. A1 - Chellapa, Rama A1 - Ratha,N. K KW - biometric pattern KW - Biometrics KW - Cancelable Biometrics KW - cancelable iris biometrics KW - data mining KW - data privacy KW - Degradation KW - Eyelashes KW - Eyelids KW - Iris KW - iris recognition KW - pattern recognition KW - privacy KW - random processes KW - Random Projections KW - Robustness KW - sectored random projection KW - Secure Biometrics KW - Security KW - security of data AB - 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. JA - 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) PB - IEEE SN - 978-1-4244-4295-9 M3 - 10.1109/ICASSP.2010.5495383 ER -