Face verification has been widely studied during the past two decades. One of the challenges is the rising concern about the security and privacy of the template database. In this paper, we propose a secure face verification system which employs a user dependent one way transformation based on a two stage hashing algorithm. We first hash the face image using a two stages
robust image hashing technique, then the result hash vector is encrypted using Advanced Encryption Standard (AES). Both the hashing and the encryption/decryption keys are generated from the user claimed ID, using a modified password-based key driven algorithm. The proposed system is tested on the ORL (AT&T) face database.