Saturday August 23, 2014
Quick summaryFusing the scores of several biometric systems is a very promising approach to improve the overall system's accuracy. Despite many works in the literature, it is surprising that there is no coordinated effort in making a benchmark database available.
Fusion here involves multimodal fusion and intramodal fusion (fusing systems using the same biometric modality but different features, or same features but using different classifiers).
Building baseline systems from scratch often prevents researchers from putting more efforts in understanding the fusion problem. This website :
DownloadDownload the files here.
Matlab 6.5 or higher (for the tools only)
Getting started%start matlab
% run FP-2 protocol and fuse with mean operator
%Wait for your fusion results!
%run the tutorials
The use of this database or tools provided here should refer to the following publication:
Norman Poh and Samy Bengio, Database, Protocol and Tools for Evaluating Score-Level Fusion Algorithms in Biometric Authentication, Pattern Recognition, Volume 39, Issue 2, Pages 223-233, 2006. (Honorable Mention in the Best PR Journal Paper Awards in 2006)
Norman Poh and Samy Bengio, Non-Linear Variance Reduction Techniques in Biometric Authentication, in Multimodal User Authentication Workshop, Santa Barabara, pages 123-130, 2006.
Some reported results can be found in: