Based On The Local Growth And Integration Of Fingerprint Matching Algorithm

Recently, personal identification has been one of the most indispensable parts in people's daily life with the development of the science and technology. As one of the important parts, Biometrics has drawn more and more research interest and industrial focus due to its high safety, stability, and convenience.As the most famous and widely used technology, though fingerprint identification has received more attention and been studied for a long time, there are still some unsolved challenging problems: such as non-linear distortion in fingerprint images, fingerprint matching based on unstable minutiae, low-quality image enhancement and so on. In this paper, we set focus on fingerprint matching only using minutiae, and propose a novel fingerprint matching algorithm based on local structure compatibility, which has been evaluated on FVC database. The main contribution to fingerprint matching in this work includes:First, local structure compatibility was proposed, which describes the mutual relationship between the neighboring local structures. And this compatibility could be thought as the stability of the neighboring structures'relative positions during a certain transformation. The compatibility is also the basis of the local structure's similarity adjustment.Secondly, a novel fingerprint matching algorithm based on local structure compatibility was proposed. The algorithm only uses the minutiae to construct local structures and form the similarity matrix (TSM) between two images. Based on the compatibility, we adjust the similarity of each matching pair according to their neighbors'matching status in order to make the genuine matching pair distinct from the others. At last, we use an extended searching step to gain more pairs so as to avoid simply depending on only one reference pair or transformation parameter. The evaluation on the FVC2004 database demonstrated improvement compared to the congeneric methods.