4D Facial Expression Recognition by Learning ...
Document type :
Article dans une revue scientifique: Article original
Title :
4D Facial Expression Recognition by Learning Geometric Deformations
Author(s) :
Ben Amor, Boulbaba [Auteur]
FOX MIIRE [LIFL]
Institut TELECOM/TELECOM Lille1
Drira, Hassen [Auteur]
Institut TELECOM/TELECOM Lille1
FOX MIIRE [LIFL]
Berretti, Stefano [Auteur]
Dipartimento di Sistemi e Informatica [DSI]
Daoudi, Mohamed [Auteur]
Institut TELECOM/TELECOM Lille1
FOX MIIRE [LIFL]
Srivastava, Anuj [Auteur]
Department of Statistics [Tallahassee, FL]
FOX MIIRE [LIFL]
Institut TELECOM/TELECOM Lille1
Drira, Hassen [Auteur]

Institut TELECOM/TELECOM Lille1
FOX MIIRE [LIFL]
Berretti, Stefano [Auteur]
Dipartimento di Sistemi e Informatica [DSI]
Daoudi, Mohamed [Auteur]

Institut TELECOM/TELECOM Lille1
FOX MIIRE [LIFL]
Srivastava, Anuj [Auteur]
Department of Statistics [Tallahassee, FL]
Journal title :
IEEE Transactions on Cybernetics
Pages :
2443-2457
Publisher :
IEEE
Publication date :
2014-03-17
ISSN :
2168-2267
HAL domain(s) :
Informatique [cs]/Vision par ordinateur et reconnaissance de formes [cs.CV]
Informatique [cs]/Apprentissage [cs.LG]
Informatique [cs]/Apprentissage [cs.LG]
English abstract : [en]
In this paper, we present an automatic approach for facial expression recognition from 3D video sequences. In the proposed solution, the 3D faces are represented by collections of radial curves and a Riemannian shape ...
Show more >In this paper, we present an automatic approach for facial expression recognition from 3D video sequences. In the proposed solution, the 3D faces are represented by collections of radial curves and a Riemannian shape analysis is applied to effectively quantify the deformations induced by the facial expressions, in a given subsequence of 3D frames. This is obtained from the \textit{Dense Scalar Field}, which denotes the shooting directions of the geodesic paths constructed between pairs of corresponding radial curves of two faces. As the resulting Dense Scalar Fields show a high dimensionality, LDA transformation is applied to the dense feature space. Two methods are then used for classification: (i) 3D motion extraction with temporal HMM modeling; and (ii) Mean deformation capturing with Random Forest. While a dynamic HMM on the features is trained in the first approach, the second one computes mean deformations under a window and applies multi-class Random Forest. Both of the proposed classification schemes on the scalar fields showed comparable results and outperformed earlier studies on facial expression recognition from 3D video sequences.Show less >
Show more >In this paper, we present an automatic approach for facial expression recognition from 3D video sequences. In the proposed solution, the 3D faces are represented by collections of radial curves and a Riemannian shape analysis is applied to effectively quantify the deformations induced by the facial expressions, in a given subsequence of 3D frames. This is obtained from the \textit{Dense Scalar Field}, which denotes the shooting directions of the geodesic paths constructed between pairs of corresponding radial curves of two faces. As the resulting Dense Scalar Fields show a high dimensionality, LDA transformation is applied to the dense feature space. Two methods are then used for classification: (i) 3D motion extraction with temporal HMM modeling; and (ii) Mean deformation capturing with Random Forest. While a dynamic HMM on the features is trained in the first approach, the second one computes mean deformations under a window and applies multi-class Random Forest. Both of the proposed classification schemes on the scalar fields showed comparable results and outperformed earlier studies on facial expression recognition from 3D video sequences.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
ANR Project :
Collections :
Source :
Files
- https://hal.archives-ouvertes.fr/hal-00949002/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-00949002/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-00949002/document
- Open access
- Access the document
- document
- Open access
- Access the document
- DaoudiIEEESMC.pdf
- Open access
- Access the document
- document
- Open access
- Access the document
- DaoudiIEEESMC.pdf
- Open access
- Access the document