A Comparative Analysis of Fingerprint Enhancement Technique through Absolute Mean Brightness Error and Entropy

Abstract

An enhancement algorithm is applied on the i nput fingerprint image to improve the image quality and to repair broken ridges. There are various enhancement schemes used for enhancing an image which includes gray scales manipulation, Histogram Equalization, Fast Fourier Transformed enhancement and Gabor Filter. There are several factors that affect the quality of the acquired fingerprint image via presence of scars, variations of the pressure between the finger, worn artifacts and acquisition sensor etc. This paper shows the work performed on the new database of fingerprint image acquired with a 500dpi optical sensor. Three different enhancement algorithms are applied on the input image and the qualities of the reconstructed image are compared using Absolute mean brightness error, peak–signal to noiseratio and Entropy