Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | Proceedings of the 14th IAPR International Conference on Machine Vision Applications |
| Untertitel | MVA 2015 |
| Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers Inc. |
| Seiten | 584-587 |
| Seitenumfang | 4 |
| ISBN (elektronisch) | 9784901122153 |
| Publikationsstatus | Veröffentlicht - Juli 2015 |
| Veranstaltung | 14th IAPR International Conference on Machine Vision Applications, MVA 2015 - Tokyo, Japan Dauer: 18 Mai 2015 → 22 Mai 2015 |
Abstract
Candide-3 is a well-known model, used to represent triangular meshes of human faces. It is common to only estimate 17 to 21 of the 79 model parameters. We show that these are insufficient to fit model vertices to facial feature points with low error and if more parameters are estimated, the model mesh deforms to unnatural configurations. To overcome this problem, we propose a novel solution: Given facial feature points, we propose to estimate the model parameters in subsets in which they are uncorrelated. Additionally we present a term to penalize topologically incorrect triangular mesh configurations. As a result the average mean squared error between facial feature points and model vertices is reduced by 90%, while face topology is preserved.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Angewandte Informatik
- Informatik (insg.)
- Maschinelles Sehen und Mustererkennung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
Proceedings of the 14th IAPR International Conference on Machine Vision Applications: MVA 2015. Institute of Electrical and Electronics Engineers Inc., 2015. S. 584-587 7153259.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Estimation of Face Parameters using Correlation Analysis and a Topology Preserving Prior
AU - Grasshof, Stella
AU - Ackermann, Hanno
AU - Ostermann, Jorn
PY - 2015/7
Y1 - 2015/7
N2 - Candide-3 is a well-known model, used to represent triangular meshes of human faces. It is common to only estimate 17 to 21 of the 79 model parameters. We show that these are insufficient to fit model vertices to facial feature points with low error and if more parameters are estimated, the model mesh deforms to unnatural configurations. To overcome this problem, we propose a novel solution: Given facial feature points, we propose to estimate the model parameters in subsets in which they are uncorrelated. Additionally we present a term to penalize topologically incorrect triangular mesh configurations. As a result the average mean squared error between facial feature points and model vertices is reduced by 90%, while face topology is preserved.
AB - Candide-3 is a well-known model, used to represent triangular meshes of human faces. It is common to only estimate 17 to 21 of the 79 model parameters. We show that these are insufficient to fit model vertices to facial feature points with low error and if more parameters are estimated, the model mesh deforms to unnatural configurations. To overcome this problem, we propose a novel solution: Given facial feature points, we propose to estimate the model parameters in subsets in which they are uncorrelated. Additionally we present a term to penalize topologically incorrect triangular mesh configurations. As a result the average mean squared error between facial feature points and model vertices is reduced by 90%, while face topology is preserved.
UR - http://www.scopus.com/inward/record.url?scp=84941254201&partnerID=8YFLogxK
U2 - 10.1109/mva.2015.7153259
DO - 10.1109/mva.2015.7153259
M3 - Conference contribution
AN - SCOPUS:84941254201
SP - 584
EP - 587
BT - Proceedings of the 14th IAPR International Conference on Machine Vision Applications
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 14th IAPR International Conference on Machine Vision Applications, MVA 2015
Y2 - 18 May 2015 through 22 May 2015
ER -