A Novel Approach to Address Sensor Interoperability Using Gabor Filter

Abstract

Biometric authentication using fingerprint is one of the unique and reliable method of verification processes. Biometric System suffers a signiûcant loss of performance when the sensor is changed during enrollment and authentication process. In this paper fingerprint sensor interoperability problem is addressed using Gabor ûlter and classifying images into good and poor quality. Gabor ûlters play an important role in many application areas for the enhancement of various types of fingerprint images. Gabor ûlters can remove noise, preserve the real ridges and valley structures, and it is used for fingerprint image enhancement. Experimental results on the FVC2004 databases show improvements of this approach.