Skip to main navigation Skip to search Skip to main content

Matching score fusion methods

  • SUNY Buffalo

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

1 Scopus citations

Abstract

The matching system can be defined as a type of classifier which calculates the confidence score for each class separately from other classes. Biometric systems are one example of the matching systems. In this chapter we discuss the score fusion methods which are suitable for such systems. In particular, we describe the complexity types of combination methods and characterize some of the existing fusion methods using these types. The higher complexity combination methods account for particular score dependencies typically present in matching systems. We analyze such dependencies and provide suggestions on how more powerful higher complexity combinations can be constructed. The known properties of combination methods are summarized in the five claims, and the theoretical proofs of two claims are provided.

Original languageEnglish
Title of host publicationHandbook of Statistics
PublisherElsevier B.V.
Pages151-175
Number of pages25
DOIs
StatePublished - 2013

Publication series

NameHandbook of Statistics
Volume31
ISSN (Print)0169-7161

Keywords

  • Biometric systems
  • Classifier combination
  • Identification
  • Matching systems
  • Verification

Fingerprint

Dive into the research topics of 'Matching score fusion methods'. Together they form a unique fingerprint.

Cite this