Robust matching of fingerprints using pseudo-Zernike moments

Fingerprint recognition is a type of physiological biometrics. In this paper, a system is proposed for fingerprints matching. The proposed system contains three phases. In the first phase, which is preprocessing, background removal and contrast enhancement are performed. In the second phase, a series of features are extracted from the fingerprint patches using pseudo-Zernike moments. Finally, in the third phase, which is the recognition phase, the fingerprint matching is done using the Euclidean distance between the input samples and the stored templates. The proposed system is invariant to the size, translation and rotation of fingerprints, and is accurate and fast. The proposed system has been evaluated on two data sets of FVC 2004 and FVC 2006. It can be observed that the proposed method is more accurate than similar methods.