3D face expression estimation and generation from 2D image based on a physically constraint model

Takahiro Ishikawa, Shigeo Morishima, Demetri Terzopoulos

Research output: Contribution to journalArticle

8 Citations (Scopus)

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.

Original languageEnglish
Pages (from-to)251-258
Number of pages8
JournalIEICE Transactions on Information and Systems
VolumeE83-D
Issue number2
Publication statusPublished - 2000
Externally publishedYes

Fingerprint

Muscle
Tissue
Physics
Cameras
Neural networks

Keywords

  • Facial image reconstruction
  • Facial muscle model
  • Muscle parameter
  • Neural network

ASJC Scopus subject areas

  • Information Systems
  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

3D face expression estimation and generation from 2D image based on a physically constraint model. / Ishikawa, Takahiro; Morishima, Shigeo; Terzopoulos, Demetri.

In: IEICE Transactions on Information and Systems, Vol. E83-D, No. 2, 2000, p. 251-258.

Research output: Contribution to journalArticle

@article{6f042bab3d3c45f3b3302acae5179fc5,
title = "3D face expression estimation and generation from 2D image based on a physically constraint model",
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 = "Facial image reconstruction, Facial muscle model, Muscle parameter, Neural network",
author = "Takahiro Ishikawa and Shigeo Morishima and Demetri Terzopoulos",
year = "2000",
language = "English",
volume = "E83-D",
pages = "251--258",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "2",

}

TY - JOUR

T1 - 3D face expression estimation and generation from 2D image based on a physically constraint model

AU - Ishikawa, Takahiro

AU - Morishima, Shigeo

AU - Terzopoulos, Demetri

PY - 2000

Y1 - 2000

N2 - 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.

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.

KW - Facial image reconstruction

KW - Facial muscle model

KW - Muscle parameter

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=0033897551&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033897551&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0033897551

VL - E83-D

SP - 251

EP - 258

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 2

ER -