Details
| Original language | English |
|---|---|
| Title of host publication | ICME 2008 |
| Subtitle of host publication | 2008 IEEE International Conference on Multimedia and Expo, Proceedings |
| Pages | 933-936 |
| Number of pages | 4 |
| Publication status | Published - Aug 2008 |
| Event | 2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Hannover, Germany Duration: 23 Jun 2008 → 26 Jun 2008 |
Publication series
| Name | 2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings |
|---|
Abstract
Facial animation has been combined with text-to-speech synthesis to create innovative multimodal interfaces, such as web stores and web-based customer services. This paper presents an image-based facial animation system using Active Appearance Models (AAM) for precisely detecting feature points in the human face, which are required for selecting mouth images from the database of the face model. In order to minimize the impact of human error when creating the training data, a new optimization method for building an AAM is produced. Optimized training set reduces the average feature point location error from 1.15 pixels to 0.17 pixel. The feature points are suitable for automatic morphing between mouth images with large visual differences. Subjective tests show that morphing improves the visual quality of the animation from "fair" to "good".
Keywords
- AAM, Facial animation, Human machine interface, Morphing, Unit selection
ASJC Scopus subject areas
- Computer Science(all)
- Computer Graphics and Computer-Aided Design
- Engineering(all)
- Electrical and Electronic Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
ICME 2008: 2008 IEEE International Conference on Multimedia and Expo, Proceedings. 2008. p. 933-936 4607589 (2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Robust AAM building for morphing in an image-based facial animation system
AU - Liu, Kang
AU - Weissenfeld, Axel
AU - Ostermann, Joern
AU - Luo, Xinghan
PY - 2008/8
Y1 - 2008/8
N2 - Facial animation has been combined with text-to-speech synthesis to create innovative multimodal interfaces, such as web stores and web-based customer services. This paper presents an image-based facial animation system using Active Appearance Models (AAM) for precisely detecting feature points in the human face, which are required for selecting mouth images from the database of the face model. In order to minimize the impact of human error when creating the training data, a new optimization method for building an AAM is produced. Optimized training set reduces the average feature point location error from 1.15 pixels to 0.17 pixel. The feature points are suitable for automatic morphing between mouth images with large visual differences. Subjective tests show that morphing improves the visual quality of the animation from "fair" to "good".
AB - Facial animation has been combined with text-to-speech synthesis to create innovative multimodal interfaces, such as web stores and web-based customer services. This paper presents an image-based facial animation system using Active Appearance Models (AAM) for precisely detecting feature points in the human face, which are required for selecting mouth images from the database of the face model. In order to minimize the impact of human error when creating the training data, a new optimization method for building an AAM is produced. Optimized training set reduces the average feature point location error from 1.15 pixels to 0.17 pixel. The feature points are suitable for automatic morphing between mouth images with large visual differences. Subjective tests show that morphing improves the visual quality of the animation from "fair" to "good".
KW - AAM
KW - Facial animation
KW - Human machine interface
KW - Morphing
KW - Unit selection
UR - http://www.scopus.com/inward/record.url?scp=54049135664&partnerID=8YFLogxK
U2 - 10.1109/ICME.2008.4607589
DO - 10.1109/ICME.2008.4607589
M3 - Conference contribution
AN - SCOPUS:54049135664
SN - 9781424425716
T3 - 2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings
SP - 933
EP - 936
BT - ICME 2008
T2 - 2008 IEEE International Conference on Multimedia and Expo, ICME 2008
Y2 - 23 June 2008 through 26 June 2008
ER -