Automated Fingerprint Identification Systems (AFIS) are commonly used by law enforcement agencies to narrow down the possible suspects from a criminal database. AFIS do not use all discriminatory features available in fingerprints but typically use only some types of features automatically extracted by a feature extraction algorithm. Latent fingerprints obtained from crime scenes are usually partial in nature which results to only very few number of reliable minutiae. Comparing a partial minutiae pattern to a full minutiae pattern is a difficult problem. Towards solving this challenge, we propose a method that exploits extended fingerprint features (unusual/rare minutiae) not commonly considered in typical minutiae-based matchers. The method we propose in this work can be combined with any existing minutiae-based matcher. We first compute a quantitative measure based on least squares between latent and tenprint minutiae points, with rare minutia feature as reference point. Then the similarity score of the reference minutiae-based matcher is modified based on the least square quantitative measure. The modified similarity score thus obtained incorporates the contribution of rare minutia features. We use a realistic forensic fingerprint casework database in our experiments which contains rare minutia features obtained from Guardia Civil, the Spanish law enforcement agency. Experiments are conducted using two reference minutiae-based matchers, namely: NIST-Bozorth3 and VeriFinger. We report a significant improvement in the rank identification accuracies when the reference minutiae matchers are augmented with our proposed algorithm based on rare minutia features.
展开▼