An Improved Revocable Fuzzy Vault Scheme for Face Recognition Under Unconstrained Illumination Conditions

Abstract

The paper presents an improved fuzzy vault approach for face recognition under unconstrained environments. First, we parameterize the number of chaff points needed and determine the threshold separating the genuine points from the chaff points in the vault. The second improvement consists of enhancing the security of the fuzzy vault. Clancy et al. (in: Proceedings of ACM SIGMM2003, 2003) and Mihailescu (in: Computer Vision and Pattern Recognition (cs.CV); Cryptography and Security (cs.CR), 2007) discussed brute-force attacks to prove the weaknesses of the popular Juels and Sudan fuzzy vault method for some parameters such as the total number of points in the vault. To remedy such limitations, we introduce a cancellable and revocable biometric approach for face recognition based on the local binary patterns histograms. In addition to the revocability of the biometric data, we also achieved very recognition accuracy of more than 95% outperforming many of the exiting biometric approaches. More importantly, the proposed approach is developed to secure biometric data and achieve excellent recognition accuracy even under unconstrained environments.