Fingerprint classification using Support Vector Machine

Abstract

Fingerprint is one of the widely used biometric identification to identify the identity of a person due reliability and acceptability. Fingerprint classes are divided into five such as, arch, tented arch, left loop, right loop and whorl. The fingerprint classification provides indexing to the database to reduce the searching and mapping process. There are many algorithms that have been used by researchers to develop fingerprint classification model, such as the Neural Network (NN) algorithm, Genetic algorithm and Support Vector Machine (SVM) algorithm. In this study, SVM algorithm is used for developing fingerprint classification model. Fingerprint dataset used in this study was obtained from the Fingerprint Verification Competition (FVC), FVC2000 and FVC2002. The result of this study shows that SVM gave a high percentage of accuracy of the fingerprint classification which was 92.5%.