作者: Ala Balti , Mounir Sayadi , Farhat Fnaiech
DOI: 10.1109/IPAS.2014.7043292
关键词:
摘要: Our objective of this project is to apply the theory linear algebra called “singular value decomposition (SVD)” digital image processing, specifically for fingerprint images verification. For optimal recognition, we proceed in two steps. In first step, begin by identifying features with SVD approach. second classification accuracy proposed approach evaluated Back Propagation Neural Network (BPNN) classifier. I have implemented many extensive experiments, they prove that based on a novel and BPNN give better results verification than several other methods.