An Experimental Analysis of the Relationship between Biometric Template Update and the Doddington’s Zoo in Face Verification

TitleAn Experimental Analysis of the Relationship between Biometric Template Update and the Doddington’s Zoo in Face Verification
Publication TypeConference Paper
Year of Publication2009
AuthorsRattani, A, Marcialis, GL, Roli, F
Conference Name14th International Conference on Image Analysis and Processing (ICIAP09)
Date Published09/07/2009
Conference LocationVietri sul Mare (Italy)
Keywordsb04, biometrics, face
Abstract

The problem of biometric template representativeness has recently attracted much attention with the introduction of several template update methods. Automatic template update methods adapt themselves to the intra-class variations of the input data. However, it is possible to hypothesize that the effect of template updating may not be the same for all the clients due to different characteristics of clients present in the biometric database. The goal of this paper is to investigate this hypothesis by explicitly partitioning the database clients into different groups of the  “Doddington’s zoo” as a function of their “intrinsic” characteristics and studying the effect of state of art template “self update” procedure on these different groups. Experimental evaluations on Equinox database with a face verification system based on EBGM algorithm shows the strong evidence of non-uniform update effects on different clients classes and suggest to adapt the update procedures according to the client’s characteristics.

Citation Key 774