Which 3D Geometric Facial Features Give ...
Type de document :
Communication dans un congrès avec actes
DOI :
Titre :
Which 3D Geometric Facial Features Give Up Your Identity ?
Auteur(s) :
Ballihi, Lahoucine [Auteur]
FOX MIIRE [LIFL]
Laboratoire de Recherche en Informatique et Télécommunications [Rabat] [GSCM-LRIT]
Ben Amor, Boulbaba [Auteur]
FOX MIIRE [LIFL]
Institut TELECOM/TELECOM Lille1
Daoudi, Mohamed [Auteur]
FOX MIIRE [LIFL]
Institut TELECOM/TELECOM Lille1
Srivastava, Anuj [Auteur]
Department of Statistics [Tallahassee, FL]
Aboutajdine, Driss [Auteur]
Laboratoire de Recherche en Informatique et Télécommunications [Rabat] [GSCM-LRIT]
FOX MIIRE [LIFL]
Laboratoire de Recherche en Informatique et Télécommunications [Rabat] [GSCM-LRIT]
Ben Amor, Boulbaba [Auteur]
FOX MIIRE [LIFL]
Institut TELECOM/TELECOM Lille1
Daoudi, Mohamed [Auteur]
FOX MIIRE [LIFL]
Institut TELECOM/TELECOM Lille1
Srivastava, Anuj [Auteur]
Department of Statistics [Tallahassee, FL]
Aboutajdine, Driss [Auteur]
Laboratoire de Recherche en Informatique et Télécommunications [Rabat] [GSCM-LRIT]
Titre de la manifestation scientifique :
International Conference on Biometrics
Ville :
New Delhi
Pays :
Inde
Date de début de la manifestation scientifique :
2012-03-29
Titre de l’ouvrage :
International Conference on Biometrics
Date de publication :
2012-03-30
Discipline(s) HAL :
Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
Résumé en anglais : [en]
The 3D face recognition literature has many papers that represent facial shapes as collections of curves of different kinds (level-curves, iso-level curves, radial curves, profiles, geodesic polarization, iso-depth lines, ...
Lire la suite >The 3D face recognition literature has many papers that represent facial shapes as collections of curves of different kinds (level-curves, iso-level curves, radial curves, profiles, geodesic polarization, iso-depth lines, iso-stripes, etc.). In contrast with the holistic approaches, the approaches that match faces based on whole surfaces, the curve-based parametrization allows local analysis of facial shapes. This, in turn, facilitates handling of pose variations (probe image may correspond to a part of the face) or missing data (probe image is altered by occlusions. An important question is: Does the use of full set of curves leads to better performances? Among all facial curves, are there ones that are more relevant than others for the recognition task? We explicitly address these questions in this paper. We represent facial surfaces by collections of radial curves and iso-level curves, such that shapes of corresponding curves are compared using a Riemmannian framework, select the most discriminative curves (geometric features) using boosting. The experiment involving FRGCv2 dataset demonstrates the effectiveness of this feature selection by achieving 98.02% as rank-1 recognition rate. This selec- tion also results in a more compact signature which sig- nificantly reduces the computational cost and the storage requirements for the face recognition system.Lire moins >
Lire la suite >The 3D face recognition literature has many papers that represent facial shapes as collections of curves of different kinds (level-curves, iso-level curves, radial curves, profiles, geodesic polarization, iso-depth lines, iso-stripes, etc.). In contrast with the holistic approaches, the approaches that match faces based on whole surfaces, the curve-based parametrization allows local analysis of facial shapes. This, in turn, facilitates handling of pose variations (probe image may correspond to a part of the face) or missing data (probe image is altered by occlusions. An important question is: Does the use of full set of curves leads to better performances? Among all facial curves, are there ones that are more relevant than others for the recognition task? We explicitly address these questions in this paper. We represent facial surfaces by collections of radial curves and iso-level curves, such that shapes of corresponding curves are compared using a Riemmannian framework, select the most discriminative curves (geometric features) using boosting. The experiment involving FRGCv2 dataset demonstrates the effectiveness of this feature selection by achieving 98.02% as rank-1 recognition rate. This selec- tion also results in a more compact signature which sig- nificantly reduces the computational cost and the storage requirements for the face recognition system.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :
Fichiers
- https://hal.archives-ouvertes.fr/hal-00726082/document
- Accès libre
- Accéder au document
- https://hal.archives-ouvertes.fr/hal-00726082/document
- Accès libre
- Accéder au document
- https://hal.archives-ouvertes.fr/hal-00726082/document
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- Ballihi-ICB-2012.pdf
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document