Breadth-first-based decision algorithm for facial biometrics

The challenge of facial biometrics is the decision rule of how to determine whether the claimant is the genuine user. It is an important issue that the decision rule affects the accuracy of performance. Therefore, the study proposes a breadth-first-based decision algorithm for facial biometrics. The proposed algorithm searches different graph paths to obtain a verified decision to accept or reject the claimant. Based on experiments on multiple face databases, we achieve a high performance and reliable facial biometric system.