The Layered Segmentation, Gabor Filtering and Binarization Based On Orientation for Fingerprint Preprocessing

The quality of fingerprint preprocessing affects the accuracy of fingerprint matching directly. The segmentation saves the region that has the clear ridge and valley and assures the quality of preprocessing. The Gabor filter has optimally combined the spatial and frequency domains. It can effectively remove the noise and preserve the true ridge structure. The binarization can change the gray. In this paper we introduce the arithmetic that combines the layered segmentation, the Gabor filtering and the binarization based on orientation. This arithmetic segments the fingerprint image accurately, filtrate the bridge clear and change the gray to 0 and 1. This arithmetic described above has been tested on the fingerprint images from the FVC2004 database. The effect of this arithmetic achieves the anticipative aim that we want to get