Construction of realistic three dimensional facial images using video images

Hajime Sato; Jun Ohya; Nobuyoshi Terashima

doi:10.1109/ISSPA.2003.1224855

Construction of realistic three dimensional facial images using video images

Hajime Sato, Jun Ohya, Nobuyoshi Terashima

School of Creative Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

A method for constructing 3D human facial images which maintains the characteristics of video input image is proposed. First, a personalized 3D polygonal facial model is constructed from two orthogonal facial images. Video input frames are modified, and the movements of facial feature points are tracked and measured based on the contraction rule of facial muscles. The vertices of the 3D polygons are altered accordingly, and the modified input frame is texture mapped directly onto to the forementioned model. This method was implemented using an ordinary CCD camera and computer, and an experiment using one person's data showed that realistic facial images is reconstructed with high speed and precision.

Original language	English
Title of host publication	Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003
Publisher	IEEE Computer Society
Pages	227-230
Number of pages	4
ISBN (Print)	0780379462, 9780780379466
DOIs	https://doi.org/10.1109/ISSPA.2003.1224855
Publication status	Published - 2003 Jan 1
Event	7th International Symposium on Signal Processing and Its Applications, ISSPA 2003 - Paris, France Duration: 2003 Jul 1 → 2003 Jul 4

Publication series

Name	Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003
Volume	2

Conference

Conference	7th International Symposium on Signal Processing and Its Applications, ISSPA 2003
Country/Territory	France
City	Paris
Period	03/7/1 → 03/7/4

ASJC Scopus subject areas

Signal Processing

Access to Document

10.1109/ISSPA.2003.1224855

Cite this

Sato, H., Ohya, J., & Terashima, N. (2003). Construction of realistic three dimensional facial images using video images. In Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003 (pp. 227-230). [1224855] (Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003; Vol. 2). IEEE Computer Society. https://doi.org/10.1109/ISSPA.2003.1224855

Construction of realistic three dimensional facial images using video images. / Sato, Hajime; Ohya, Jun; Terashima, Nobuyoshi.
Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003. IEEE Computer Society, 2003. p. 227-230 1224855 (Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Sato, H, Ohya, J & Terashima, N 2003, Construction of realistic three dimensional facial images using video images. in Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003., 1224855, Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003, vol. 2, IEEE Computer Society, pp. 227-230, 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003, Paris, France, 03/7/1. https://doi.org/10.1109/ISSPA.2003.1224855

Sato H, Ohya J, Terashima N. Construction of realistic three dimensional facial images using video images. In Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003. IEEE Computer Society. 2003. p. 227-230. 1224855. (Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003). doi: 10.1109/ISSPA.2003.1224855

@inproceedings{1e36496e0d8e4dc3abc62cc554f62455,

title = "Construction of realistic three dimensional facial images using video images",

abstract = "A method for constructing 3D human facial images which maintains the characteristics of video input image is proposed. First, a personalized 3D polygonal facial model is constructed from two orthogonal facial images. Video input frames are modified, and the movements of facial feature points are tracked and measured based on the contraction rule of facial muscles. The vertices of the 3D polygons are altered accordingly, and the modified input frame is texture mapped directly onto to the forementioned model. This method was implemented using an ordinary CCD camera and computer, and an experiment using one person's data showed that realistic facial images is reconstructed with high speed and precision.",

author = "Hajime Sato and Jun Ohya and Nobuyoshi Terashima",

year = "2003",

month = jan,

day = "1",

doi = "10.1109/ISSPA.2003.1224855",

language = "English",

isbn = "0780379462",

series = "Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003",

publisher = "IEEE Computer Society",

pages = "227--230",

booktitle = "Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003",

note = "7th International Symposium on Signal Processing and Its Applications, ISSPA 2003 ; Conference date: 01-07-2003 Through 04-07-2003",

}

TY - GEN

T1 - Construction of realistic three dimensional facial images using video images

AU - Sato, Hajime

AU - Ohya, Jun

AU - Terashima, Nobuyoshi

PY - 2003/1/1

Y1 - 2003/1/1

N2 - A method for constructing 3D human facial images which maintains the characteristics of video input image is proposed. First, a personalized 3D polygonal facial model is constructed from two orthogonal facial images. Video input frames are modified, and the movements of facial feature points are tracked and measured based on the contraction rule of facial muscles. The vertices of the 3D polygons are altered accordingly, and the modified input frame is texture mapped directly onto to the forementioned model. This method was implemented using an ordinary CCD camera and computer, and an experiment using one person's data showed that realistic facial images is reconstructed with high speed and precision.

AB - A method for constructing 3D human facial images which maintains the characteristics of video input image is proposed. First, a personalized 3D polygonal facial model is constructed from two orthogonal facial images. Video input frames are modified, and the movements of facial feature points are tracked and measured based on the contraction rule of facial muscles. The vertices of the 3D polygons are altered accordingly, and the modified input frame is texture mapped directly onto to the forementioned model. This method was implemented using an ordinary CCD camera and computer, and an experiment using one person's data showed that realistic facial images is reconstructed with high speed and precision.

UR - http://www.scopus.com/inward/record.url?scp=84904282859&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84904282859&partnerID=8YFLogxK

U2 - 10.1109/ISSPA.2003.1224855

DO - 10.1109/ISSPA.2003.1224855

M3 - Conference contribution

AN - SCOPUS:84904282859

SN - 0780379462

SN - 9780780379466

T3 - Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003

SP - 227

EP - 230

BT - Proceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003

PB - IEEE Computer Society

T2 - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003

Y2 - 1 July 2003 through 4 July 2003

ER -

Construction of realistic three dimensional facial images using video images

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this