Reconstruction of partially damaged face images based on a morphable face model

Bon Woo Hwang; Seong Whan Lee

doi:10.1109/TPAMI.2003.1182099

Reconstruction of partially damaged face images based on a morphable face model

Bon Woo Hwang, Seong Whan Lee

Department of Artificial Intelligence

Research output: Contribution to journal › Article › peer-review

98 Citations (Scopus)

Abstract

This paper proposes a method for reconstructing partially damaged faces based on a morphable face model. Faces are modeled by linear combinations of prototypes of shape and texture. With the shape and texture information from an undamaged region only, we can estimate optimal coefficients for linear combinations of prototypes of shape and texture by simple projection for least-square minimization (LSM). Our experimental results show that reconstructed faces are very natural and plausible like real photos.

Original language	English
Pages (from-to)	365-372
Number of pages	8
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	25
Issue number	3
DOIs	https://doi.org/10.1109/TPAMI.2003.1182099
Publication status	Published - 2003 Mar

Keywords

Damaged face
Face reconstruction
Face synthesis
Least-square minimization
Morphable face model

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Computational Theory and Mathematics
Artificial Intelligence
Applied Mathematics

Access to Document

10.1109/TPAMI.2003.1182099

Cite this

@article{cd742293ae0a43c0a4a9f8da5dbbbba4,

title = "Reconstruction of partially damaged face images based on a morphable face model",

abstract = "This paper proposes a method for reconstructing partially damaged faces based on a morphable face model. Faces are modeled by linear combinations of prototypes of shape and texture. With the shape and texture information from an undamaged region only, we can estimate optimal coefficients for linear combinations of prototypes of shape and texture by simple projection for least-square minimization (LSM). Our experimental results show that reconstructed faces are very natural and plausible like real photos.",

keywords = "Damaged face, Face reconstruction, Face synthesis, Least-square minimization, Morphable face model",

author = "Hwang, {Bon Woo} and Lee, {Seong Whan}",

note = "Funding Information: This research was supported by Creative Research Initiatives of the Ministry of Science and Technology, Korea. The authors would like to thank Dr. Volker Blanz and Dr. Thomas Vetter for helpful discussions and advice. In addition, they thank the Max-Planck-Institute for providing the MPI Face Database.",

year = "2003",

month = mar,

doi = "10.1109/TPAMI.2003.1182099",

language = "English",

volume = "25",

pages = "365--372",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "3",

}

TY - JOUR

T1 - Reconstruction of partially damaged face images based on a morphable face model

AU - Hwang, Bon Woo

AU - Lee, Seong Whan

N1 - Funding Information: This research was supported by Creative Research Initiatives of the Ministry of Science and Technology, Korea. The authors would like to thank Dr. Volker Blanz and Dr. Thomas Vetter for helpful discussions and advice. In addition, they thank the Max-Planck-Institute for providing the MPI Face Database.

PY - 2003/3

Y1 - 2003/3

N2 - This paper proposes a method for reconstructing partially damaged faces based on a morphable face model. Faces are modeled by linear combinations of prototypes of shape and texture. With the shape and texture information from an undamaged region only, we can estimate optimal coefficients for linear combinations of prototypes of shape and texture by simple projection for least-square minimization (LSM). Our experimental results show that reconstructed faces are very natural and plausible like real photos.

AB - This paper proposes a method for reconstructing partially damaged faces based on a morphable face model. Faces are modeled by linear combinations of prototypes of shape and texture. With the shape and texture information from an undamaged region only, we can estimate optimal coefficients for linear combinations of prototypes of shape and texture by simple projection for least-square minimization (LSM). Our experimental results show that reconstructed faces are very natural and plausible like real photos.

KW - Damaged face

KW - Face reconstruction

KW - Face synthesis

KW - Least-square minimization

KW - Morphable face model

UR - http://www.scopus.com/inward/record.url?scp=0037341419&partnerID=8YFLogxK

U2 - 10.1109/TPAMI.2003.1182099

DO - 10.1109/TPAMI.2003.1182099

M3 - Article

AN - SCOPUS:0037341419

SN - 0162-8828

VL - 25

SP - 365

EP - 372

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 3

ER -

Reconstruction of partially damaged face images based on a morphable face model

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this