Facial image reconstruction by estimated muscle parameter

Takahiro Ishikawa, Hajime Sera, Shigeo Morishima, Demetri Terzopoulos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

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 tissue 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 2D marker movements using neural network. This corresponds to the non-realtime 3D facial motion tracking from 2D image under the physics based condition.

Original languageEnglish
Title of host publicationProceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998
PublisherIEEE Computer Society
Pages342-347
Number of pages6
ISBN (Print)0818683449, 9780818683442
DOIs
Publication statusPublished - 1998
Externally publishedYes
Event3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998 - Nara
Duration: 1998 Apr 141998 Apr 16

Other

Other3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998
CityNara
Period98/4/1498/4/16

Fingerprint

Image reconstruction
Muscle
Tissue
Physics
Neural networks

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Ishikawa, T., Sera, H., Morishima, S., & Terzopoulos, D. (1998). Facial image reconstruction by estimated muscle parameter. In Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998 (pp. 342-347). [670972] IEEE Computer Society. https://doi.org/10.1109/AFGR.1998.670972

Facial image reconstruction by estimated muscle parameter. / Ishikawa, Takahiro; Sera, Hajime; Morishima, Shigeo; Terzopoulos, Demetri.

Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998. IEEE Computer Society, 1998. p. 342-347 670972.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ishikawa, T, Sera, H, Morishima, S & Terzopoulos, D 1998, Facial image reconstruction by estimated muscle parameter. in Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998., 670972, IEEE Computer Society, pp. 342-347, 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998, Nara, 98/4/14. https://doi.org/10.1109/AFGR.1998.670972
Ishikawa T, Sera H, Morishima S, Terzopoulos D. Facial image reconstruction by estimated muscle parameter. In Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998. IEEE Computer Society. 1998. p. 342-347. 670972 https://doi.org/10.1109/AFGR.1998.670972
Ishikawa, Takahiro ; Sera, Hajime ; Morishima, Shigeo ; Terzopoulos, Demetri. / Facial image reconstruction by estimated muscle parameter. Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998. IEEE Computer Society, 1998. pp. 342-347
@inproceedings{c1e11f15473a4622b418dcb7e89a170c,
title = "Facial image reconstruction by estimated muscle parameter",
abstract = "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 tissue 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 2D marker movements using neural network. This corresponds to the non-realtime 3D facial motion tracking from 2D image under the physics based condition.",
author = "Takahiro Ishikawa and Hajime Sera and Shigeo Morishima and Demetri Terzopoulos",
year = "1998",
doi = "10.1109/AFGR.1998.670972",
language = "English",
isbn = "0818683449",
pages = "342--347",
booktitle = "Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Facial image reconstruction by estimated muscle parameter

AU - Ishikawa, Takahiro

AU - Sera, Hajime

AU - Morishima, Shigeo

AU - Terzopoulos, Demetri

PY - 1998

Y1 - 1998

N2 - 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 tissue 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 2D marker movements using neural network. This corresponds to the non-realtime 3D facial motion tracking from 2D image under the physics based condition.

AB - 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 tissue 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 2D marker movements using neural network. This corresponds to the non-realtime 3D facial motion tracking from 2D image under the physics based condition.

UR - http://www.scopus.com/inward/record.url?scp=0142241581&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0142241581&partnerID=8YFLogxK

U2 - 10.1109/AFGR.1998.670972

DO - 10.1109/AFGR.1998.670972

M3 - Conference contribution

SN - 0818683449

SN - 9780818683442

SP - 342

EP - 347

BT - Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998

PB - IEEE Computer Society

ER -