An enhancement of image filtering for fingerprint recognition

Moh. Azzoubi, Einas Almarghni (2016) An enhancement of image filtering for fingerprint recognition. Masters thesis, Universiti Tun Hussein Onn Malaysia.

[img]PDF
10Mb

Abstract

Fingerprint recognition is being widely applied in personal identification for the purpose of high degree security through matching processes between two human fingerprints. In fact, many different techniques have been proposed to generate satisfactory fingerprint identification. The widely used minutiae-based representation does not utilize the significant component of the rich discriminatory information available in fingerprints. Moreover, local ridge structures cannot be completely characterized by minutiae. Furthermore, the minutiae-based matching poses difficulty in quickly matching two fingerprint images containing different numbers of unregistered minutiae points. Thus, an enhancement algorithm had been introduced by using the Gabor filter-based matching to capture both local and global details in a fingerprint as a compact fixed-length Fingercode. The filtering was improved through the use of separable filtering by dividing the complex filtering two-dimension into two one-dimensions for lowpass and bandpass. The filtering was employed to feature extraction in the proposed algorithm with eight different directions. The last step of the proposed algorithm was fingerprint matching, which had been based on the Euclidean Distance between the two corresponding Fingercodes. The proposed algorithm could be personalized based on the values of Euclidean Distance and threshold. In addition, the proposed algorithm of Enhancement of Gabor for filtering techniques was compared with an ordinary Gabor filter algorithm and displayed high value of accuracy at 99% and 98% of recognition rate.

Item Type:Thesis (Masters)
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800-8360 Electronics
ID Code:9157
Deposited By:Mr. Mohammad Shaifulrip Ithnin
Deposited On:21 Jun 2017 11:44
Last Modified:21 Jun 2017 11:44

Repository Staff Only: item control page