Analysis of Procedures used to build an Optimal Fingerprint Recognition System

Fingerprint recognition is one of the most widely use operation, due the big number of applications requiring this operation, so seeking a good method of fingerprint features extraction is a vital task. In this paper we will investigate three method of image features extraction: minutiae, RCSLP and c_clustering methods, we will analyze the performances of these methods, and we will for fixing the features when the fingerprint rotated. The obtained features will be used to feed a selected type with a selected architecture ANN in order to show which type of ANN gives the best results of fingerprint recognition.