Development of an Improved Fingerprint Feature Extraction Algorithm for Personal Verification

Simple item page
dc.creatorAtuegwu, Charity, Daramola , S.A, Okokpujie, Kennedy O., Noma-Osaghae, Etinosa
dc.date2018
dc.date.accessioned2025-04-01T16:38:18Z
dc.descriptionNew and sophisticated technologies are regularly developed to counter every new wave of breaches in data security. At the heart of some of these technologies is the personal verification system that rests on the oars of biometrics. Biometric systems use unique physical and behavioral traits for identification or verification. In this paper, an improved fingerprint feature extraction algorithm for personal verification is proposed. The improved fingerprint feature extraction algorithm is capable of recognizing authorized individuals and differentiating them from fraudulent imposters. The input images were preprocessed before extracting robust features for matching. Euclidean distance was used for classification. The proposed system was tested using the fingerprint images of fifty registered individuals and thirty imposters. The results obtained were a False Acceptance Rate and False Rejection Rate of 16% and 24% respectively. It is also faster than other feature extraction algorithms by forty (40) seconds Keywords: Fingerprint, biometrics, robust features, division into blocks, ridge pattern, euclidean distance, personal verification, feature extraction, classification.
dc.formatapplication/pdf
dc.identifierhttp://eprints.covenantuniversity.edu.ng/10694/
dc.identifier.urihttps://repository.covenantuniversity.edu.ng/handle/123456789/40306
dc.languageen
dc.publisherResearch India Publications.
dc.subjectAC Collections. Series. Collected works, T Technology (General)
dc.titleDevelopment of an Improved Fingerprint Feature Extraction Algorithm for Personal Verification
dc.typeArticle

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
14_64011-IJAER ok 6608-6612.pdf
Size:
395.55 KB
Format:
Adobe Portable Document Format
Download

Collections

EPrint