Addis Ababa University Libraries Electronic Thesis and Dissertations: AAU-ETD! >
Institute of Technology >
Thesis - Computer Engineering  >

Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/2904

Advisors: Dr. ASSEFA DAGNE
Keywords: Gabor filter
absolute average deviation from the mean
local frequency
local orientation
Fingerprint recognition
Image processing
Copyright: Aug-2003
Date Added: 10-May-2012
Publisher: AAU
Abstract: Fingerprint matching is one of the most important problems in fingerprint recognition system. Generally, fingerprint matching algorithm can be classified into two: minutiae based and non‐minutiae based. In minutiae based matching, ridge endings and ridge bifurcations are used as discriminative features for matching, but in non‐minutiae based, features other than minutiae are used. Hybrid approaches by combining minutiae with other non‐minutiae based matching methods are used to improve fingerprint matching methods. In this paper, alignment‐based elastic matching algorithm, is used for minutiae based matching and new non‐minutiae method proposed which solve the shortcomings of the algorithms proposed by Jain et.al. The experiment was done on 320 fingerprints of Fingerprint Verification Competition 2002 set‐B databases and showed that the hybrid matching algorithm improved the Equal Error Rate from ~11.8 % to 7.55% than the minutiae based matching algorithm.
URI: http://hdl.handle.net/123456789/2904
Appears in:Thesis - Computer Engineering

Files in This Item:

File Description SizeFormat
134.93 MBAdobe PDFView/Open

Items in the AAUL Digital Library are protected by copyright, with all rights reserved, unless otherwise indicated.


  Last updated: May 2010. Copyright © Addis Ababa University Libraries - Feedback