This paper presents a completly automated face recognition system integrating both two dimensional (texture) and three dimensional (shape) features. We introduce a novel fusion strategy that allows to automatically select, for each face, the most relevant features from each modality. The performance is evaluated on the largest public data corpus for face recognition currently available, the Face Recognition Grand Challenge version 2.0.
Face Recognition Based on 2D and 3D Features / S. Arca, R. Lanzarotti, G. Lipori, F.M. Stefanini (LECTURE NOTES IN COMPUTER SCIENCE). - In: Knowledge-Based Intelligent Information and Engineering Systems / [a cura di] B. Apolloni, R. J. Howlett, L. Jain. - Berlin : Springer, 2007. - ISBN 9783540748175. - pp. 455-462 (( Intervento presentato al 11. convegno KES - WIRN International Conference on Knowledge-Based Intelligent Information and Engineering Systems 11th International Conference, XVII ItalianWorkshop on Neural Networks : September 12-14 tenutosi a Vietri sul Mare, Italy nel 2007 [10.1007/978-3-540-74819-9].
Face Recognition Based on 2D and 3D Features
S. ArcaPrimo
;R. LanzarottiSecondo
;G. LiporiUltimo
;
2007
Abstract
This paper presents a completly automated face recognition system integrating both two dimensional (texture) and three dimensional (shape) features. We introduce a novel fusion strategy that allows to automatically select, for each face, the most relevant features from each modality. The performance is evaluated on the largest public data corpus for face recognition currently available, the Face Recognition Grand Challenge version 2.0.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
