위치이동에 무관한 지문인식 정합 알고리즘에 관한 연구

Abstract

- This paper presents a new matching algorithm for fingerprint recognition, which is robust to image translation. The basic idea of this paper is to estimate the translation vector of an input fingerprint image using N minutiae at which the gradient of the ridge direction field is large. Using the estimated translation vector we select minutiae irrelevant to the translation. We experimentally prove that the presented algorithm results in good performance even if there are large translation and pseudo-minutiae.