Reconstruction of facial shape from freehand multi-viewpoint snapshots

Seiji Suzuki, Hideo Saito, Masaaki Mochimaru

Research output: Contribution to journalArticle

Abstract

We propose a method that can reconstruct both facial poses and the facial shape from freehand multi-viewpoint snapshots. This method is based on Active Shape Models (ASM), which is a technique that uses a facial shape database. Most ASM methods require image in which the facial pose is known, but our method does not require this information. First, we chose an initial shape by selecting the model from the database which is most similar to the input images. Then, we improve the model by morphing it to better fit the input images. Next, we estimate the pose of the face using the morphed model. Finally we repeat the process, improving both the facial shape and the facial pose until the error between the input and the computed result is minimized. Through experimentation, we show that our method reconstructs the facial shape within 3.5mm of the ground truth.

Original languageEnglish
Pages (from-to)506-515
Number of pages10
JournalKyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers
Volume63
Issue number4
DOIs
Publication statusPublished - 2009

Keywords

  • Active Shape Model
  • Principal component analysis

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Media Technology
  • Computer Science Applications

Cite this

Reconstruction of facial shape from freehand multi-viewpoint snapshots. / Suzuki, Seiji; Saito, Hideo; Mochimaru, Masaaki.

In: Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, Vol. 63, No. 4, 2009, p. 506-515.

Research output: Contribution to journalArticle

@article{e57da7253f9c4917ad43328db91cf655,
title = "Reconstruction of facial shape from freehand multi-viewpoint snapshots",
abstract = "We propose a method that can reconstruct both facial poses and the facial shape from freehand multi-viewpoint snapshots. This method is based on Active Shape Models (ASM), which is a technique that uses a facial shape database. Most ASM methods require image in which the facial pose is known, but our method does not require this information. First, we chose an initial shape by selecting the model from the database which is most similar to the input images. Then, we improve the model by morphing it to better fit the input images. Next, we estimate the pose of the face using the morphed model. Finally we repeat the process, improving both the facial shape and the facial pose until the error between the input and the computed result is minimized. Through experimentation, we show that our method reconstructs the facial shape within 3.5mm of the ground truth.",
keywords = "Active Shape Model, Principal component analysis",
author = "Seiji Suzuki and Hideo Saito and Masaaki Mochimaru",
year = "2009",
doi = "10.3169/itej.63.506",
language = "English",
volume = "63",
pages = "506--515",
journal = "Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers",
issn = "1342-6907",
publisher = "Institute of Image Information and Television Engineers",
number = "4",

}

TY - JOUR

T1 - Reconstruction of facial shape from freehand multi-viewpoint snapshots

AU - Suzuki, Seiji

AU - Saito, Hideo

AU - Mochimaru, Masaaki

PY - 2009

Y1 - 2009

N2 - We propose a method that can reconstruct both facial poses and the facial shape from freehand multi-viewpoint snapshots. This method is based on Active Shape Models (ASM), which is a technique that uses a facial shape database. Most ASM methods require image in which the facial pose is known, but our method does not require this information. First, we chose an initial shape by selecting the model from the database which is most similar to the input images. Then, we improve the model by morphing it to better fit the input images. Next, we estimate the pose of the face using the morphed model. Finally we repeat the process, improving both the facial shape and the facial pose until the error between the input and the computed result is minimized. Through experimentation, we show that our method reconstructs the facial shape within 3.5mm of the ground truth.

AB - We propose a method that can reconstruct both facial poses and the facial shape from freehand multi-viewpoint snapshots. This method is based on Active Shape Models (ASM), which is a technique that uses a facial shape database. Most ASM methods require image in which the facial pose is known, but our method does not require this information. First, we chose an initial shape by selecting the model from the database which is most similar to the input images. Then, we improve the model by morphing it to better fit the input images. Next, we estimate the pose of the face using the morphed model. Finally we repeat the process, improving both the facial shape and the facial pose until the error between the input and the computed result is minimized. Through experimentation, we show that our method reconstructs the facial shape within 3.5mm of the ground truth.

KW - Active Shape Model

KW - Principal component analysis

UR - http://www.scopus.com/inward/record.url?scp=67650082884&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650082884&partnerID=8YFLogxK

U2 - 10.3169/itej.63.506

DO - 10.3169/itej.63.506

M3 - Article

AN - SCOPUS:67650082884

VL - 63

SP - 506

EP - 515

JO - Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers

JF - Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers

SN - 1342-6907

IS - 4

ER -