NURBS-based facial expression modeling for anthropomorphic interface agent

Santi Saeyor, Hiroshi Dohi, Mitsuru Ishizuka

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

1 Citation (Scopus)

Abstract

Facial images play an important role in friendly human-computer interactions as well as in human-human communications. To date, more than 500 polygon patches have been commonly used to generate a human 3D face model. It is not easy, however, to control the vertices of these patches in designing the facial forms and their expressions. This paper discusses algorithms for the manipulation of NURBS (non-uniform rational B-Spline) parameters to yield realistic 3D facial models and their expressions. Then it presents a new method which uses a single NURBS patch in constructing a 3D facial model with several expressions. This allows to design and modify the facial model easily. A real human image can be texture-mapped onto this model. A prototype software shows that the quality and the synthesis speed of the image are satisfactory level.

Original languageEnglish
Title of host publicationRobot and Human Communication - Proceedings of the IEEE International Workshop
Editors Anon
Place of PublicationPiscataway, NJ, United States
PublisherIEEE
Pages395-400
Number of pages6
Publication statusPublished - 1996
Externally publishedYes
EventProceedings of the 1996 5th IEEE International Workshop on Robot and Human Communication, RO-MAN - Tsukuba, Jpn
Duration: 1996 Nov 111996 Nov 14

Other

OtherProceedings of the 1996 5th IEEE International Workshop on Robot and Human Communication, RO-MAN
CityTsukuba, Jpn
Period96/11/1196/11/14

Fingerprint

Splines
Human computer interaction
Textures
Communication

ASJC Scopus subject areas

  • Hardware and Architecture
  • Software

Cite this

Saeyor, S., Dohi, H., & Ishizuka, M. (1996). NURBS-based facial expression modeling for anthropomorphic interface agent. In Anon (Ed.), Robot and Human Communication - Proceedings of the IEEE International Workshop (pp. 395-400). Piscataway, NJ, United States: IEEE.

NURBS-based facial expression modeling for anthropomorphic interface agent. / Saeyor, Santi; Dohi, Hiroshi; Ishizuka, Mitsuru.

Robot and Human Communication - Proceedings of the IEEE International Workshop. ed. / Anon. Piscataway, NJ, United States : IEEE, 1996. p. 395-400.

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

Saeyor, S, Dohi, H & Ishizuka, M 1996, NURBS-based facial expression modeling for anthropomorphic interface agent. in Anon (ed.), Robot and Human Communication - Proceedings of the IEEE International Workshop. IEEE, Piscataway, NJ, United States, pp. 395-400, Proceedings of the 1996 5th IEEE International Workshop on Robot and Human Communication, RO-MAN, Tsukuba, Jpn, 96/11/11.
Saeyor S, Dohi H, Ishizuka M. NURBS-based facial expression modeling for anthropomorphic interface agent. In Anon, editor, Robot and Human Communication - Proceedings of the IEEE International Workshop. Piscataway, NJ, United States: IEEE. 1996. p. 395-400
Saeyor, Santi ; Dohi, Hiroshi ; Ishizuka, Mitsuru. / NURBS-based facial expression modeling for anthropomorphic interface agent. Robot and Human Communication - Proceedings of the IEEE International Workshop. editor / Anon. Piscataway, NJ, United States : IEEE, 1996. pp. 395-400
@inproceedings{249ff6d4c767402c938f7f0e215affd2,
title = "NURBS-based facial expression modeling for anthropomorphic interface agent",
abstract = "Facial images play an important role in friendly human-computer interactions as well as in human-human communications. To date, more than 500 polygon patches have been commonly used to generate a human 3D face model. It is not easy, however, to control the vertices of these patches in designing the facial forms and their expressions. This paper discusses algorithms for the manipulation of NURBS (non-uniform rational B-Spline) parameters to yield realistic 3D facial models and their expressions. Then it presents a new method which uses a single NURBS patch in constructing a 3D facial model with several expressions. This allows to design and modify the facial model easily. A real human image can be texture-mapped onto this model. A prototype software shows that the quality and the synthesis speed of the image are satisfactory level.",
author = "Santi Saeyor and Hiroshi Dohi and Mitsuru Ishizuka",
year = "1996",
language = "English",
pages = "395--400",
editor = "Anon",
booktitle = "Robot and Human Communication - Proceedings of the IEEE International Workshop",
publisher = "IEEE",

}

TY - GEN

T1 - NURBS-based facial expression modeling for anthropomorphic interface agent

AU - Saeyor, Santi

AU - Dohi, Hiroshi

AU - Ishizuka, Mitsuru

PY - 1996

Y1 - 1996

N2 - Facial images play an important role in friendly human-computer interactions as well as in human-human communications. To date, more than 500 polygon patches have been commonly used to generate a human 3D face model. It is not easy, however, to control the vertices of these patches in designing the facial forms and their expressions. This paper discusses algorithms for the manipulation of NURBS (non-uniform rational B-Spline) parameters to yield realistic 3D facial models and their expressions. Then it presents a new method which uses a single NURBS patch in constructing a 3D facial model with several expressions. This allows to design and modify the facial model easily. A real human image can be texture-mapped onto this model. A prototype software shows that the quality and the synthesis speed of the image are satisfactory level.

AB - Facial images play an important role in friendly human-computer interactions as well as in human-human communications. To date, more than 500 polygon patches have been commonly used to generate a human 3D face model. It is not easy, however, to control the vertices of these patches in designing the facial forms and their expressions. This paper discusses algorithms for the manipulation of NURBS (non-uniform rational B-Spline) parameters to yield realistic 3D facial models and their expressions. Then it presents a new method which uses a single NURBS patch in constructing a 3D facial model with several expressions. This allows to design and modify the facial model easily. A real human image can be texture-mapped onto this model. A prototype software shows that the quality and the synthesis speed of the image are satisfactory level.

UR - http://www.scopus.com/inward/record.url?scp=0030405984&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030405984&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030405984

SP - 395

EP - 400

BT - Robot and Human Communication - Proceedings of the IEEE International Workshop

A2 - Anon, null

PB - IEEE

CY - Piscataway, NJ, United States

ER -