Fingerprint Image Recognition Using Walidlet Transform

The choice of an object representation is crucial for the effective performance of cognitive tasks such as fingerprint image (FPI) recognition, this is because how robustly and efficiently recognition tasks can be performed depends on the choice f the feature representation.This paper introduces Walidlet transform (WLT) coefficients as an effective and efficient FPI representation. The WLT represent FPI with sets of weighted coefficients that are specially chosen to reflect the properties of the represent FPI.The WLT parameters are chosen according to a specific discrete scheme that is based on the discrete Multiwvelet transform. The optimized parameter choice of the WLT allows the representation to be very sparse and specific to the represented FPI. It has been shown that the specificity of the parameters can be exploited for the recognition of FPI & the recognition rates are shown to be as high as 97%