Fingerprint Authentication System Based on Minutiae and Direction Field Toning Technique

Abstract

Fingerprint authentication refers to the automated method of verifying a match between two human fingerprints. Fingerprints are one of many forms of biometrics used to identify the individuals and verify their identity. Minutiae points are local ridge characteristics which can provide unique information. The conventional methods have utilized this minutiae information only as a point set. As a global feature, orientation field has extremely higher inter-personal variation than that of minutiae points. This proposed method describes the implementation of an Automatic Fingerprint Identification System (AFIS) which incorporates both local and global features of the fingerprints and operates in three stages: (1) minutiae extraction (2) reconstruction of orientation field and (3) fusion matching. An Improved Gabor filter algorithm is used for reliable minutiae extraction. From this extracted minutiae, the orientation field is reconstructed by using Interpolation-Model based (IM) method and utilized in the matching stage. This reconstructed orientation field matching is then fused with the minutiae-based matching. Thus the proposed scheme can enhance the performance of the system and obtain better matching accuracy than conventional methods.