This paper presents a new approach to identify persons using their fingerprints. The proposed approach is based on the Polynomial Discrete Radon Transform (PDRT). The PDRT extends the Classical Radon Transform (RT) by generalizing the curves used for the projection. In fact, the classical Radon projection is restricted to straight lines. However, the PDRT method projects the image along polynomial curves following different directions. The proposed technique enables the extraction of directional characteristics from the fingerprint of the hand. Since several methods in the literature reached a level of success on fingerprint recognition, this paper proposes a new identification method which is invariant to geometrical transformations such as translation and rotation. In addition, it is robust to noise. To evaluate the performance of this approach, we have tested it on a database containing 128 fingerprint images. The obtained result confirms the efficiency of the method.