Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | FG 2017 - 12th IEEE International Conference onAutomatic Face and Gesture Recognition |
| Untertitel | MAIN CONFERENCE+ First International Workshop on Adaptive Shot Learning for Gesture Understanding and Production (ASL4GUP 2017), Biometrics in the Wild (Bwild 2017), Heterogeneous Face Recognition (HFR 2017), Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation (DCER&HPE 2017, )3d Facial Expression Recognition and Analysis Challenge (FERA 2017) |
| Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers Inc. |
| Seiten | 658-665 |
| Seitenumfang | 8 |
| ISBN (elektronisch) | 9781509040230 |
| Publikationsstatus | Veröffentlicht - 28 Juni 2017 |
| Veranstaltung | 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017 - Washington, USA / Vereinigte Staaten Dauer: 30 Mai 2017 → 3 Juni 2017 |
Abstract
In this paper, we present a new statistical model for human faces. Our approach is built upon a tensor factorisation model that allows controlled estimation, morphing and transfer of new facial shapes and expressions. We propose a direct parametrisation and regularisation for person and expression related terms so that the training database is well utilised. In contrast to existing works we are the first to reveal that the expression subspace is star shaped. This stems from the fact that increasing the strength of an expression approximately forms a linear trajectory in the expression subspace, and all these linear trajectories intersect in a single point which corresponds to the point of no expression or the point of apathy. After centring our analysis to this point, we then demonstrate how the dimensionality of the expression subspace can be further reduced by projection pursuit with the help of the fourth-order moment tensor. The results show that our method is able to achieve convincing separation of the person specific and expression subspaces as well as flexible, natural modelling of facial expressions for wide variety of human faces. By the proposed approach, one can morph between different persons and different expressions even if they do not exist in the database. In contrast to the state-of-the-art, the morphing works without causing strong deformations. In the application of expression classification, the results are also better.
ASJC Scopus Sachgebiete
- Ingenieurwesen (insg.)
- Medientechnik
- Informatik (insg.)
- Artificial intelligence
- Informatik (insg.)
- Maschinelles Sehen und Mustererkennung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
FG 2017 - 12th IEEE International Conference onAutomatic Face and Gesture Recognition: MAIN CONFERENCE+ First International Workshop on Adaptive Shot Learning for Gesture Understanding and Production (ASL4GUP 2017), Biometrics in the Wild (Bwild 2017), Heterogeneous Face Recognition (HFR 2017), Joint Challenge on Dominant and Complementary Emotion Recognition Using Micro Emotion Features and Head-Pose Estimation (DCER&HPE 2017, )3d Facial Expression Recognition and Analysis Challenge (FERA 2017). Institute of Electrical and Electronics Engineers Inc., 2017. S. 658-665 7961804.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Apathy Is the Root of All Expressions
AU - Graßhof, Stella
AU - Ackermann, Hanno
AU - Brandt, Sami S.
AU - Ostermann, Jorn
PY - 2017/6/28
Y1 - 2017/6/28
N2 - In this paper, we present a new statistical model for human faces. Our approach is built upon a tensor factorisation model that allows controlled estimation, morphing and transfer of new facial shapes and expressions. We propose a direct parametrisation and regularisation for person and expression related terms so that the training database is well utilised. In contrast to existing works we are the first to reveal that the expression subspace is star shaped. This stems from the fact that increasing the strength of an expression approximately forms a linear trajectory in the expression subspace, and all these linear trajectories intersect in a single point which corresponds to the point of no expression or the point of apathy. After centring our analysis to this point, we then demonstrate how the dimensionality of the expression subspace can be further reduced by projection pursuit with the help of the fourth-order moment tensor. The results show that our method is able to achieve convincing separation of the person specific and expression subspaces as well as flexible, natural modelling of facial expressions for wide variety of human faces. By the proposed approach, one can morph between different persons and different expressions even if they do not exist in the database. In contrast to the state-of-the-art, the morphing works without causing strong deformations. In the application of expression classification, the results are also better.
AB - In this paper, we present a new statistical model for human faces. Our approach is built upon a tensor factorisation model that allows controlled estimation, morphing and transfer of new facial shapes and expressions. We propose a direct parametrisation and regularisation for person and expression related terms so that the training database is well utilised. In contrast to existing works we are the first to reveal that the expression subspace is star shaped. This stems from the fact that increasing the strength of an expression approximately forms a linear trajectory in the expression subspace, and all these linear trajectories intersect in a single point which corresponds to the point of no expression or the point of apathy. After centring our analysis to this point, we then demonstrate how the dimensionality of the expression subspace can be further reduced by projection pursuit with the help of the fourth-order moment tensor. The results show that our method is able to achieve convincing separation of the person specific and expression subspaces as well as flexible, natural modelling of facial expressions for wide variety of human faces. By the proposed approach, one can morph between different persons and different expressions even if they do not exist in the database. In contrast to the state-of-the-art, the morphing works without causing strong deformations. In the application of expression classification, the results are also better.
UR - http://www.scopus.com/inward/record.url?scp=85026320597&partnerID=8YFLogxK
U2 - 10.1109/fg.2017.83
DO - 10.1109/fg.2017.83
M3 - Conference contribution
AN - SCOPUS:85026320597
SP - 658
EP - 665
BT - FG 2017 - 12th IEEE International Conference onAutomatic Face and Gesture Recognition
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 12th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2017
Y2 - 30 May 2017 through 3 June 2017
ER -