Fingerprint Recognition Using Hybrid Matching Algorithm

Fingerprint matching is one of the most important problems in fingerprint recognitionrnsystem. Generally, fingerprint matching algorithm can be classified into two: minutiae basedrnand non‐minutiae based. In minutiae based matching, ridge endings and ridge bifurcationsrnare used as discriminative features for matching, but in non‐minutiae based, features otherrnthan minutiae are used.rnHybrid approaches by combining minutiae with other non‐minutiae based matchingrnmethods are used to improve fingerprint matching methods. In this paper, alignment‐basedrnelastic matching algorithm, is used for minutiae based matching and new non‐minutiaernmethod proposed which solve the shortcomings of the algorithms proposed by Jain et.al.rnThe experiment was done on 320 fingerprints of Fingerprint Verification Competition 2002rnset‐B databases and showed that the hybrid matching algorithm improved the Equal ErrorrnRate from ~11.8 % to 7.55% than the minutiae based matching algorithm.rnKeyword: Image processing, Fingerprint recognition, local orientation, local frequency,rnminutiae, absolute average deviation from the mean, Gabor filter.

Get Full Work

Report copyright infringement or plagiarism