Novel algorithm for fingerprint mosaicing using phase correlation method

摘要

Fingerprint is most important and widely used biometrics trait for identification. However, the fingerprint identification is still a challenging task in forensic science for criminal investigation and identification due to less area of region of interest (i.e.ridges and valleys) in the obtained fingerprints. Entire fingerprint is obtained only when it is given intentionally. But, in the case of criminal incidents, it is not always possible to get entire fingerprints. In such cases, obtained fingerprints are often partial i.e. having less region of interest. If it is possible to get more than one partial fingerprint of same finger these can be combined to increase the area of interest using mosaicing process. Image mosaicing using the conventional phase correlation method uses Fourier domain approach to find m atching point or overlapping region in images which are translated with respect to each other. The algorithm uses phase correlation property to find translation parameter for registration. The method is less complex and fast but still has disadvantages. It does not show correct result when one or both fingerprints contain the tip (top curvature part) of finger. The proposed modified algorithm solves the problem using edge of fingerprint and shows satisfactory results and improves robustness of phase correlation method.