In view of the different dangers to which users of contactless biometric systems are exposed, we have developed a contactless secure revocable model based on random projection and DFT (Discret Fourier Tansformation) to enhance contactless fingerprint authentication. Two matrices emerge, namely that corresponding to the terminations and that corresponding to the bifurcations. These matrices are then transformed in a first time thanks to the random projection. In a second time we apply to them the Discret Fourier Transformation called the DFT.This proposed non-contact revocable fingerprint model meets the requirements of revocability, diversity, security and non-reversibility. The evaluation of our model through its results gives the most promising results compared to those existing. The equal error rate (EER) obtained are respectively equal to 0.19% for FVC2002 DB1, 1% for FVC2002 DB2, 4.29% for FVC2002 DB3 and 9.01% for FVC2004 DB2.

large quantity of biometric models has rapidly proliferated in biometric applications. Due to the fact that biometric systems expose users to enormous risks that endanger , we improved an existing technics technique and adapted it to the contactless system. The proposed model, in this article, propose a very secure fingerprint model protection technique in which a cylindrical curve is generated as a user secure model for a contactless fingerprint. During the construction of our model, we use three invariants intra-personals characteristics, namely the set of distances between the detailed points and the center of mass, the orientation information of the detailed points and the number of endings between the minutiae points and the singular point. The results of the experimental analysis performed on the FVC databases (2000, 2002 and 2004) and our own database show a highly encouraging performance and present the viability of the proposed technique.