Muscle based face image synthesis is one of the most realistic approaches to the realization of a life-like agent in computers. A facial muscle model is composed of facial tissue elements and simulated muscles. In this model, forces are calculated effecting a facial tissue element by contraction of each muscle string, so the combination of each muscle contracting force decides a specific facial expression. This muscle parameter is determined on a trial and error basis by comparing the sample photograph and a 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 2D markers'movements located on a face using a neural network. This corresponds to the non-realtime 3D facial motion capturing from 2D camera image under the physics based condition.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Takahiro ISHIKAWA, Shigeo MORISHIMA, Demetri TERZOPOULOS, "3D Face Expression Estimation and Generation from 2D Image Based on a Physically Constraint Model" in IEICE TRANSACTIONS on Information,
vol. E83-D, no. 2, pp. 251-258, February 2000, doi: .
Abstract: Muscle based face image synthesis is one of the most realistic approaches to the realization of a life-like agent in computers. A facial muscle model is composed of facial tissue elements and simulated muscles. In this model, forces are calculated effecting a facial tissue element by contraction of each muscle string, so the combination of each muscle contracting force decides a specific facial expression. This muscle parameter is determined on a trial and error basis by comparing the sample photograph and a 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 2D markers'movements located on a face using a neural network. This corresponds to the non-realtime 3D facial motion capturing from 2D camera image under the physics based condition.
URL: https://global.ieice.org/en_transactions/information/10.1587/e83-d_2_251/_p
Copy
@ARTICLE{e83-d_2_251,
author={Takahiro ISHIKAWA, Shigeo MORISHIMA, Demetri TERZOPOULOS, },
journal={IEICE TRANSACTIONS on Information},
title={3D Face Expression Estimation and Generation from 2D Image Based on a Physically Constraint Model},
year={2000},
volume={E83-D},
number={2},
pages={251-258},
abstract={Muscle based face image synthesis is one of the most realistic approaches to the realization of a life-like agent in computers. A facial muscle model is composed of facial tissue elements and simulated muscles. In this model, forces are calculated effecting a facial tissue element by contraction of each muscle string, so the combination of each muscle contracting force decides a specific facial expression. This muscle parameter is determined on a trial and error basis by comparing the sample photograph and a 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 2D markers'movements located on a face using a neural network. This corresponds to the non-realtime 3D facial motion capturing from 2D camera image under the physics based condition.},
keywords={},
doi={},
ISSN={},
month={February},}
Copy
TY - JOUR
TI - 3D Face Expression Estimation and Generation from 2D Image Based on a Physically Constraint Model
T2 - IEICE TRANSACTIONS on Information
SP - 251
EP - 258
AU - Takahiro ISHIKAWA
AU - Shigeo MORISHIMA
AU - Demetri TERZOPOULOS
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E83-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2000
AB - Muscle based face image synthesis is one of the most realistic approaches to the realization of a life-like agent in computers. A facial muscle model is composed of facial tissue elements and simulated muscles. In this model, forces are calculated effecting a facial tissue element by contraction of each muscle string, so the combination of each muscle contracting force decides a specific facial expression. This muscle parameter is determined on a trial and error basis by comparing the sample photograph and a 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 2D markers'movements located on a face using a neural network. This corresponds to the non-realtime 3D facial motion capturing from 2D camera image under the physics based condition.
ER -