Fusion of Statistical and Structural Fingerprint Classifiers

TitleFusion of Statistical and Structural Fingerprint Classifiers
Publication TypeConference Paper
Year of Publication2003
AuthorsMarcialis, GL, Roli, F, Serrau, A
EditorKittler, J, Nixon, MS
Conference Name4th Internation Audio- and Video-Based Person Authentication
Volume2688
Pagination310-317
Date Published09/06/2003
PublisherSpringer
Conference LocationGuildford
Keywordsbio01, biometria, biometrics, fingerprint, MCS
Abstract

Classification is an important step towards fingerprint recognition. Inthe classification stage, fingerprints are usually associated to one of the fiveclasses “A”, “L”, “R”, “T”, “W”. The aim is to reduce the number ofcomparisons that are necessary for recognition. Many approaches to fingerprintclassification have been proposed so far, but very few works investigated thepotentialities of combining statistical and structural algorithms. In this paper, anapproach to fusion of statistical and structural fingerprint classifiers is presentedand experiments that show the potentialities of such fusion are reported.

Citation Key 28