Enhancing Template Security of Face Biometrics by Using Edge Detection and Hashing
This addresses privacy and security concerns for users of face biometric systems by preventing cross-matching and enabling template revocation, though it is incremental in nature.
The paper tackles the security risks of storing raw facial images in biometric systems by proposing a method using edge detection and hashing to generate cancellable templates, achieving consistent performance with the Roberts Cross operator across diverse datasets.
In this paper we address the issues of using edge detection techniques on facial images to produce cancellable biometric templates and a novel method for template verification against tampering. With increasing use of biometrics, there is a real threat for the conventional systems using face databases, which store images of users in raw and unaltered form. If compromised not only it is irrevocable, but can be misused for cross-matching across different databases. So it is desirable to generate and store revocable templates for the same user in different applications to prevent cross-matching and to enhance security, while maintaining privacy and ethics. By comparing different edge detection methods it has been observed that the edge detection based on the Roberts Cross operator performs consistently well across multiple face datasets, in which the face images have been taken under a variety of conditions. We have proposed a novel scheme using hashing, for extra verification, in order to harden the security of the stored biometric templates.