Performance of Automatic Fingerprint Identification System (AFIS) is greatly affected by its matching rate, means it should have low False Acceptance Rate (FAR) and False Rejection Rate (FRR). Minutiae based fingerprint matching techniques are normally used for fingerprint matching. In this paper, we present a new technique for fingerprint image postprocessing. This postprocessing is used to eliminate a large number of false extracted minutiae from skeletonized fingerprint images. We propose a windowing postprocessing method that takes into account the neighborhood of each minutia within defined window and check for minutia validation and invalidation. The results are confirmed by visual inspections of validated minutiae of the FVC2004 reference fingerprint image database. Experimental results obtained by the proposed approach show efficient reduction of false minutiae.
展开▼
