Fingerprint Verification Based on STFT Analysis and Zernike Moments

This paper presents a scheme of fingerprint verification based using Zernike invariant moments. In this study we uses an enhanced image-based fingerprint verification algorithm .It reduces multi-spectral noise by enhancing a fingerprint image to accurately and reliably determine a reference point, and then aligns the image according to the position and orientation of reference point to avoid time-consuming alignment. A set of fixed-length moment features, is extracted from tessellated cells on a region of interest (ROI) centered at the reference point. After determination the ROI, Zernike moments were computed from each block of ROI as the feature of fingerprint features. The similarity between an input and a template in a database is evaluated by K-NN classifier. The proposed scheme can improve performance of verification and is more robust with respect to the fingerprint image quality.