Face shape reconstruction from image sequence taken with monocular camera using shape database

Hideo Saito, Yosuke Ito, Masaaki Mochimaru

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

4 Citations (Scopus)

Abstract

We propose a method for reconstructing 3D face shape from a camera, which captures the object face from various viewing angles. In this method, we do not directly reconstruct the shape, but estimate a small number of parameters which represent the face shape. The parameter space is constructed with Principal Component Analysis of database of a large number of face shapes collected for different people. By the PCA, the parameter space can represent the shape difference for the faces of various persons. From the input image sequence that is captured by the moving camera, the parameters of the object face can be estimated based on optimization framework. The experiments based on the proposed method demonstrate that the proposed method can reconstruct the facial shape with the accuracy of 2.5mm averaged error.

Original languageEnglish
Title of host publicationProceedings - 14th International conference on Image Analysis and Processing, ICIAP 2007
Pages165-170
Number of pages6
DOIs
Publication statusPublished - 2007
Event14th Edition of the International Conference on Image Analysis and Processing, ICIAP 2007 - Modena, Italy
Duration: 2007 Sep 102007 Sep 14

Other

Other14th Edition of the International Conference on Image Analysis and Processing, ICIAP 2007
CountryItaly
CityModena
Period07/9/1007/9/14

Fingerprint

Cameras
Principal component analysis
Experiments

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Saito, H., Ito, Y., & Mochimaru, M. (2007). Face shape reconstruction from image sequence taken with monocular camera using shape database. In Proceedings - 14th International conference on Image Analysis and Processing, ICIAP 2007 (pp. 165-170). [4362774] https://doi.org/10.1109/ICIAP.2007.4362774

Face shape reconstruction from image sequence taken with monocular camera using shape database. / Saito, Hideo; Ito, Yosuke; Mochimaru, Masaaki.

Proceedings - 14th International conference on Image Analysis and Processing, ICIAP 2007. 2007. p. 165-170 4362774.

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

Saito, H, Ito, Y & Mochimaru, M 2007, Face shape reconstruction from image sequence taken with monocular camera using shape database. in Proceedings - 14th International conference on Image Analysis and Processing, ICIAP 2007., 4362774, pp. 165-170, 14th Edition of the International Conference on Image Analysis and Processing, ICIAP 2007, Modena, Italy, 07/9/10. https://doi.org/10.1109/ICIAP.2007.4362774
Saito H, Ito Y, Mochimaru M. Face shape reconstruction from image sequence taken with monocular camera using shape database. In Proceedings - 14th International conference on Image Analysis and Processing, ICIAP 2007. 2007. p. 165-170. 4362774 https://doi.org/10.1109/ICIAP.2007.4362774
Saito, Hideo ; Ito, Yosuke ; Mochimaru, Masaaki. / Face shape reconstruction from image sequence taken with monocular camera using shape database. Proceedings - 14th International conference on Image Analysis and Processing, ICIAP 2007. 2007. pp. 165-170
@inproceedings{b0ef59cb23d941d192b0a1429fcc7367,
title = "Face shape reconstruction from image sequence taken with monocular camera using shape database",
abstract = "We propose a method for reconstructing 3D face shape from a camera, which captures the object face from various viewing angles. In this method, we do not directly reconstruct the shape, but estimate a small number of parameters which represent the face shape. The parameter space is constructed with Principal Component Analysis of database of a large number of face shapes collected for different people. By the PCA, the parameter space can represent the shape difference for the faces of various persons. From the input image sequence that is captured by the moving camera, the parameters of the object face can be estimated based on optimization framework. The experiments based on the proposed method demonstrate that the proposed method can reconstruct the facial shape with the accuracy of 2.5mm averaged error.",
author = "Hideo Saito and Yosuke Ito and Masaaki Mochimaru",
year = "2007",
doi = "10.1109/ICIAP.2007.4362774",
language = "English",
isbn = "0769528775",
pages = "165--170",
booktitle = "Proceedings - 14th International conference on Image Analysis and Processing, ICIAP 2007",

}

TY - GEN

T1 - Face shape reconstruction from image sequence taken with monocular camera using shape database

AU - Saito, Hideo

AU - Ito, Yosuke

AU - Mochimaru, Masaaki

PY - 2007

Y1 - 2007

N2 - We propose a method for reconstructing 3D face shape from a camera, which captures the object face from various viewing angles. In this method, we do not directly reconstruct the shape, but estimate a small number of parameters which represent the face shape. The parameter space is constructed with Principal Component Analysis of database of a large number of face shapes collected for different people. By the PCA, the parameter space can represent the shape difference for the faces of various persons. From the input image sequence that is captured by the moving camera, the parameters of the object face can be estimated based on optimization framework. The experiments based on the proposed method demonstrate that the proposed method can reconstruct the facial shape with the accuracy of 2.5mm averaged error.

AB - We propose a method for reconstructing 3D face shape from a camera, which captures the object face from various viewing angles. In this method, we do not directly reconstruct the shape, but estimate a small number of parameters which represent the face shape. The parameter space is constructed with Principal Component Analysis of database of a large number of face shapes collected for different people. By the PCA, the parameter space can represent the shape difference for the faces of various persons. From the input image sequence that is captured by the moving camera, the parameters of the object face can be estimated based on optimization framework. The experiments based on the proposed method demonstrate that the proposed method can reconstruct the facial shape with the accuracy of 2.5mm averaged error.

UR - http://www.scopus.com/inward/record.url?scp=48149110949&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=48149110949&partnerID=8YFLogxK

U2 - 10.1109/ICIAP.2007.4362774

DO - 10.1109/ICIAP.2007.4362774

M3 - Conference contribution

AN - SCOPUS:48149110949

SN - 0769528775

SN - 9780769528779

SP - 165

EP - 170

BT - Proceedings - 14th International conference on Image Analysis and Processing, ICIAP 2007

ER -