Comparison of fingerprint enhancement techniques through Mean Square Error and Peak-Signal to Noise Ratio

摘要

In the fingerprint recognition system the main goal of the fingerprint enhancement algorithm is to reduce the noise present in the image. There are several factors that affect the quality of the acquired fingerprint image viz. presence of scars, variations of the pressure between the finger and acquisition sensor, worn artifacts, and environmental conditions during acquisition process. An input fingerprint image is thereby transformed by the enhancement algorithm to reduce the noise present in the image. This paper shows the work performed on the new database of fingerprint images acquired with a 500dpi optical sensor. Three different enhancement algorithms are applied on the images and the qualities of the reconstructed images are compared using mean-square error and peak-signal to noise ratio.