Randomized Radon transforms for biometric authentication via fingerprint hashing

We present a new technique for generating biometric fingerprint hashes, or summaries of information contained in human fingerprints. Our method calculates and aggregates various key-determined metrics over fingerprint images, producing short hash strings that cannot be used to reconstruct the source fingerprints without knowledge of the key. This can be considered a randomized form of the Radon transform, where a custom metric replaces the standard linebased metric. Resistant to minor distortions and noise, the resulting fingerprint hashes are useful for secure biometric authentication, either augmenting or replacing traditional password hashes. This approach can help increase the security and usability of Web services and other client-server systems.