Optimal Iris Fuzzy Sketches

Fuzzy sketches, introduced as a link between biometry and cryptography, are a way of handling biometric data matching as an error correction issue. The authors focus here on iris biometrics and look for the best error-correcting code in that respect. They show that two-dimensional iterative min-sum decoding leads to results near the theoretical limits. In particular, they experiment the techniques on the Iris Challenge Evaluation (ICE) database and validate the findings.