Decision-level Fusion in Fingerprint Verification

DMCA

Decision-level Fusion in Fingerprint Verification (2001)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Salil Prabhakar , Anil K. Jain

Venue:	PATTERN RECOGNITION
Citations:	57 - 10 self

BibTeX

@ARTICLE{Prabhakar01decision-levelfusion,
    author = {Salil Prabhakar and Anil K. Jain},
    title = {Decision-level Fusion in Fingerprint Verification},
    journal = {PATTERN RECOGNITION},
    year = {2001},
    volume = {35},
    pages = {861--874}
}

OpenURL

Abstract

A scheme is proposed for classifier combination at decision level which stresses the importance of classier selection during combination. The proposed scheme is optimal (in the Neyman-Pearson sense) when sufficient data are available to obtain reasonable estimates of the join densities of classifier outputs. Four different fingerprint matching algorithms are combined using the proposed scheme to improve the accuracy of a fingerprint verification system. Experiments conducted on a large fingerprint database ( 2,700 ngerprints) conrm the effectiveness of the proposed integration scheme. An overall matching performance increase of 3% is achieved. We further show that a combination of multiple impressions or multiple fingers improves the verification performance by more than 4% and 5%, respectively. Analysis of the results provide some insight into the various decision-level classifier combination strategies.

Keyphrases

decision-level fusion fingerprint verification various decision-level classifier combination strategy verification performance sufficient data large fingerprint database different fingerprint matching algorithm proposed scheme overall matching performance increase join density decision level integration scheme neyman-pearson sense classifier output multiple finger fingerprint verification system multiple impression reasonable estimate

DMCA