查看文章

In this paper we present a new adaptive hybrid energy-based fingerprint matching system, which combines both minutiae information available in a fingerprint with the information of the local ridges in their vicinity. A more continuous representation of fingerprints can be obtained by using an energy-based rectangular tessellation with non-overlapped squared cells. However, a fixed tessellation is not efficient in handling non-linear deformations in fingerprints for which we propose an adaptive matching technique that uses dynamic rectangular tessellation to handle them. Each time a match is not found the dynamic tessellation increases its cell size until there is a match or cell size is greater than image size where the fingerprint is rejected. The basic idea of this system is to divide the fingerprint-matching problem into several small sub-problems that involve the use of cell energy minimization for which an iterative …