Similarity-Based Matching for Face Authentication

Christophe Rosenberger (1) , Luc Brun (2)

1 Equipe SAFE - Laboratoire GREYC - UMR6072
2 Equipe Image - Laboratoire GREYC - UMR6072

We propose in this paper a face authentication method based on a similarity measure. The SIFT descriptor is used to define some interest keypoints characterized by an invariant parameter. A graph is then built where nodes correspond to these keypoints. We model the authentication problem as a graph matching process. Experimental results on the AR database show an EER equals to 12% with only one image used for the enrollment and with images simulating real conditions.

Domaines: Traitement des images [eess.IV]

Christophe Rosenberger, Luc Brun. Similarity-Based Matching for Face Authentication. International Conference on Pattern Recognition (ICPR'2008), Dec 2008, Tampa, Florida, United States. pp.1-4, ⟨10.1109/ICPR.2008.4761860⟩. ⟨hal-00846773⟩