Fingerprint Reference Point Detection Based on High Curvature Points

The problem considered in this paper is associated with the image processing and the design of algorithm which allows selecting reference point on the fingerprint image. The reference point is used to align between the fingerprints in the fingerprint authentication systems faster than the conventional techniques. The reference point is the point with maximum curvature on the friction ridge, which is usually located in the central fingerprint area. Fingerprint homogeneous ridges are extracted from the image and then are processed by the IPAN99 algorithm which allows to detect curvatures of these lines. The experimental results on datasets of FVC2000, FVC2002, FVC2004 and NIST, show the high efficiency and satisfactory accuracy of the proposed algorithm. Proposed solution allows detecting reference points more precisely than other algorithms.