Local directional pattern (LDP) based fingerprint matching using SLFNN

Recently a number of biometric indicators are in use for human identification, but the fingerprint based individual identification is still the dominating biometric indicator. In this paper, we present a fingerprint matching system by exploiting local directional pattern (LDP) based features, which are originally proposed for face recognition and facial expression detection. Fingerprint image texture is encoded by computing the response value of edges in different directions from the extracted region of interest (ROI) images. Single hidden layer feed forward neural network (SLFNN) is trained using three training algorithms namely gradient decent with momentum (GDM), resilient propagation (RP), and scaled conjugate gradient (SCG) to detect the match between test and trainee images. The experimental results show that the RP algorithm converges faster and perform well in terms of matching accuracy as compared to the other two algorithms.