Image Compression in Iris-Biometric Fuzzy Commitment Schemes

Template protection targets privacy and security risks caused by unprotected storage of biometric data. Meeting properties of irreversibility and unlinkability template protection systems can be applied to secure existing records within biometric databases, i.e. without re-enrollment of registered subjects. The National Institute of Standards and Technology (NIST) demonstrated that iris recognition algorithms can maintain their accuracy and interoperability with compressed images. While template protection schemes are generally conceded highly sensitive to any sort of signal degradation, investigations on the impact of image compression on recognition accuracy have remained elusive. In this work a comprehensive study of different image compression standards applied to iris-biometric fuzzy commitment schemes is presented. It is demonstrated that compressed images, compact enough for transmission across global networks, do not drastically effect the key retrieval performance of a fuzzy commitment scheme.