DocumentCode :
3578984
Title :
Hybrid approach to enhancing fingerprint images using filters in the frequency domain
Author :
Dyre, Shoba ; Sumathi, C.P.
Author_Institution :
Department of Computer Science, SDNB Vaishnav College For Women, Chennai, India
fYear :
2014
Firstpage :
1
Lastpage :
6
Abstract :
Automatic fingerprint recognition has received considerable attention over the past decades as fingerprint is one of the most popular and successful methods used for personal identification. In this paper, a method based on the combination of Fast Fourier transform (FFT) and Gaussian Bandpass Filter is proposed to enhance fingerprint image. Various filters directly generated in the frequency domain have been used and their outcomes are analyzed in order to determine the best filter that can be applied to fingerprint images for enhancement to have better match accuracies. Experiments are conducted on sample fingerprint images that have been collected using an optical fingerprint Reader and its results show the desirable features of the proposed approach.
Keywords :
Band-pass filters; Cutoff frequency; Fingerprint recognition; Fourier transforms; Frequency-domain analysis; Image matching; Noise; Bandpass filters; Biometrics; Fourier Transform; Gaussian; Normalization; fingerprint;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Intelligence and Computing Research (ICCIC), 2014 IEEE International Conference on
Print_ISBN :
978-1-4799-3974-9
Type :
conf
DOI :
10.1109/ICCIC.2014.7238306
Filename :
7238306
Link To Document :
بازگشت