The Optimization of Fingerprint Parameters with Genetic Algorithms

An accurate Access Control System is critical in a wide range of application domains such as national ID cards, electronic commerce systems, and automated banking systems. A Biometrics based Access Control System based on a person’s physiological or behavioral characteristics is inherently more reliable and more capable in differentiating between an authorized person and a fraudulent imposter than traditional methods. The objective is to design a fingerprint-based biometric system which is capable of achieving a fully automatic “positive personal identification” with a high level of confidence. In the paper I’ve chosen, the authors suggest an optimization approach for fingerprint authentication using genetic algorithms to select the parameters used for fingerprint matching. Their application was planned so that it could be used without a great deal of effort for different biometric systems. Instead of estimating the required parameters, which is what most methods do, in this process the parameters are determined with the help of genetic algorithms. Their test database consisted of 1200 fingerprints of 12 persons. For the confirmation of the results, the databases of the Fingerprint Verification Contests of the years 2000, 2002, and 2004 were examined in addition. In the best case an improvement in the recognition performance of 38% was observed. Keywords; parameters; Biometrics; Equal Error Rate (EER); BioGINA; minutiae; genetic algorith; optimization