Abstract. Multi-modal person identity authentication is gaining more and more attention in the biometrics area. Combining di erent modalities increases the performance and robustness of identity authentication systems. The authentication problem is a binary classi cation problem. The fusion of di erent modalities can be therefore performed by binary classi ers. We propose to evaluate di erent binary classi cation schemes (SVM, MLP, C4.5, Fisher's linear discriminant, Bayesian classi er) on a large database (295 subjects) containing audio and video data. The identity authentication is based on two modalities: face and speech.
IDIAP{RR 99-03
The paper presents results of the face verification contest that was organized in conjunction with International Conference on Pattern Recognition 2000 [14]. Participants had to use identical data sets from a large, publicly available multimodal database XM2VTSDB. Training and evaluation was carried out according to an a priori known protocol ([7]). Verification results of all tested algorithms have been collected and made public on the XM2VTSDB website [15], facilitating large scale experiments on classifier combination and fusion. Tested methods included, among others, representatives of the most common approaches to face verificationelastic graph matching, Fisher's linear discriminant and Support vector machines.
Abstract. For the development and evaluation of methods for person identi cation, veri cation, and other tasks, databases play an important role. Despite this fact, there exists no measure whether a given database is su cient to train and/or to test a given algorithm. This paper proposes a method to \grade" the complexity of a database, respectively to validate whether a database is appropriate for the simulation of a given application. Experiments support the argumentation that the complexity of a data set is not equivalent to its size. The \ rst nearest neighbor" method applied to image vectors is shown to perform reasonably well for person identication, respectively the mean square distance for person veri cation. This suggests to use them as a minimal performance measure for other algorithms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.