A new clustering approach for face identification

Anis Chaari (1) , Sylvie Lelandais (1) , Mohamed Ben Ahmed (2)

1 IBISC - Informatique, Biologie Intégrative et Systèmes Complexes
2 RIADI - Laboratoire de recherche en Génie Logiciel, Applications distribuées, Systèmes décisionnels et Imagerie intelligente [Manouba]

We propose in this paper a search approach which aim to improve identification in biometric databases. We work with face images and we develop appearance-based Eigenfaces and Fisherfaces methods to generate holistic and discriminant features and attributes. These features, which describe faces, are often used to establish the required identity in a classical identification process. In this work we introduce a clustering process upstream the identification process which divides faces into partitions according to their features similarities. Indeed, we aim to split biometric databases into partitions in order to simplify the recognition task within these databases. This paper describes the proposed clustering approach, the Eigenfaces and Fisherfaces representation methods and preliminary clustering results on the XM2VTS data corpus.

Mots clés: Biometrics; Clustering algorithms; Image processing

Domaines: Sciences de l'ingénieur [physics]

Anis Chaari, Sylvie Lelandais, Mohamed Ben Ahmed. A new clustering approach for face identification. 1st International Workshops on Image Processing Theory, Tools and Applications (IPTA 2008), Nov 2008, Sousse, Tunisia. (elec. proc), ⟨10.1109/IPTA.2008.4743736⟩. ⟨hal-00870470⟩