A new fingerprint identification approach based on SVD features

Abstract

Our objective is to apply the theory of linear algebra called singular value decomposition (SVD) and a set of invariant moment features to fingerprint images identification. For optimal recognition, we proceed in two steps. In the first step, we begin by identifying the fingerprint feature with SVD approach and invariant moment. In the second step, the classification accuracy of the proposed approach is evaluated with absolute distance classifier. I have implemented many extensive experiments, they prove that the fingerprint identification based on Invariants Moments and SVD features give better results than several other features and methods.