- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Knowledge Graph Search feature is available on CiNii Labs
- 【Updated on June 30, 2025】Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
Facial tracking and reconstruction based facial muscle model
-
- ISHIKAWA Takahiro
- Seikei University
-
- YAZAKI Kazuhiko
- Seikei University
-
- SERA Hajime
- Seikei University
-
- MORISHIMA Shigeo
- Seikei University
Bibliographic Information
- Other Title
-
- 顔面筋肉モデルに基づく表情トラッキングと再合成
Search this article
Description
Muscle based face image synthesis is one of the most realistic approach to realize life-like agent in computer. Facial muscle model is composed of facial tissue elements and muscles. In this model, forces are calculated effecting facial tisssue element by contraction of each muscle strength, so the combination of each muscle parameter decide a specific facial expression. Now each muscle parameter is decided on trial and error procedure comparing the sample photograph and generated image using our Muscle-Editor to generate a specific face image. In this paper, we propose the strategy of automatic estimation of facial muscle parameters from movements of facial expression using neural network. This corresponds to the non-realtime 3D facial motion tracking from 2D image under the physics based condition.
Journal
-
- Technical report of IEICE. HIP
-
Technical report of IEICE. HIP 97 (388), 39-46, 1997-11-20
The Institute of Electronics, Information and Communication Engineers
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1574231877183437568
-
- NII Article ID
- 110003272190
-
- NII Book ID
- AN10487237
-
- Text Lang
- ja
-
- Data Source
-
- CiNii Articles