3D facial surface reconstruction using integrated orthographic models to approximate perspective projection model

Research output: Contribution to journalArticle

Abstract

This study develops a 3D facial reconstruction system in which the perspective projection model is approximated by applying a factorization method to the piecewise orthographic projection model. The proposed system comprises five modules. The first and second modules reconstruct the 3D facial surface using a factorization method based on an orthographic projection model. However, the facial video is taken based on the perspective projection model rather than an orthographic projection model. Thus, to compensate for the difference between the two models, the third module is developed to approximate the perspective projection model by dividing the 3D facial surface into small groups and then reconstructs each group in orthographic projection module. These reconstructed results are then integrated to form a complete 3D facial surface, which is almost as accurate as the reconstruction result using a perspective projection model. The fourth module implements a novel smoothing process for the 3D facial surface by interpolating additional vertices from the vectors of the existing 3D vertices. Finally, the fifth module utilizes a new solution to overcome the missing point problem, which is caused by occlusion at high pan rotation angles, commonly arising in 3D reconstruction applications. The experimental results show that the proposed system achieves a promising result within a relatively short time.

Original languageEnglish
Pages (from-to)807-825
Number of pages19
JournalInternational Journal of Innovative Computing, Information and Control
Volume8
Issue number1 B
Publication statusPublished - 2012 Jan 1

Fingerprint

Surface Reconstruction
Surface reconstruction
Integrated Model
Projection
Module
Factorization Method
Factorization
Model
3D Reconstruction
Occlusion
Smoothing
Angle
Experimental Results

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Information Systems
  • Computational Theory and Mathematics

Cite this

@article{d361442c84734837a22e419f9cd1d926,
title = "3D facial surface reconstruction using integrated orthographic models to approximate perspective projection model",
abstract = "This study develops a 3D facial reconstruction system in which the perspective projection model is approximated by applying a factorization method to the piecewise orthographic projection model. The proposed system comprises five modules. The first and second modules reconstruct the 3D facial surface using a factorization method based on an orthographic projection model. However, the facial video is taken based on the perspective projection model rather than an orthographic projection model. Thus, to compensate for the difference between the two models, the third module is developed to approximate the perspective projection model by dividing the 3D facial surface into small groups and then reconstructs each group in orthographic projection module. These reconstructed results are then integrated to form a complete 3D facial surface, which is almost as accurate as the reconstruction result using a perspective projection model. The fourth module implements a novel smoothing process for the 3D facial surface by interpolating additional vertices from the vectors of the existing 3D vertices. Finally, the fifth module utilizes a new solution to overcome the missing point problem, which is caused by occlusion at high pan rotation angles, commonly arising in 3D reconstruction applications. The experimental results show that the proposed system achieves a promising result within a relatively short time.",
author = "Wu, {Jin Yi} and Lien, {James Jenn-Jier}",
year = "2012",
month = "1",
day = "1",
language = "English",
volume = "8",
pages = "807--825",
journal = "International Journal of Innovative Computing, Information and Control",
issn = "1349-4198",
publisher = "IJICIC Editorial Office",
number = "1 B",

}

TY - JOUR

T1 - 3D facial surface reconstruction using integrated orthographic models to approximate perspective projection model

AU - Wu, Jin Yi

AU - Lien, James Jenn-Jier

PY - 2012/1/1

Y1 - 2012/1/1

N2 - This study develops a 3D facial reconstruction system in which the perspective projection model is approximated by applying a factorization method to the piecewise orthographic projection model. The proposed system comprises five modules. The first and second modules reconstruct the 3D facial surface using a factorization method based on an orthographic projection model. However, the facial video is taken based on the perspective projection model rather than an orthographic projection model. Thus, to compensate for the difference between the two models, the third module is developed to approximate the perspective projection model by dividing the 3D facial surface into small groups and then reconstructs each group in orthographic projection module. These reconstructed results are then integrated to form a complete 3D facial surface, which is almost as accurate as the reconstruction result using a perspective projection model. The fourth module implements a novel smoothing process for the 3D facial surface by interpolating additional vertices from the vectors of the existing 3D vertices. Finally, the fifth module utilizes a new solution to overcome the missing point problem, which is caused by occlusion at high pan rotation angles, commonly arising in 3D reconstruction applications. The experimental results show that the proposed system achieves a promising result within a relatively short time.

AB - This study develops a 3D facial reconstruction system in which the perspective projection model is approximated by applying a factorization method to the piecewise orthographic projection model. The proposed system comprises five modules. The first and second modules reconstruct the 3D facial surface using a factorization method based on an orthographic projection model. However, the facial video is taken based on the perspective projection model rather than an orthographic projection model. Thus, to compensate for the difference between the two models, the third module is developed to approximate the perspective projection model by dividing the 3D facial surface into small groups and then reconstructs each group in orthographic projection module. These reconstructed results are then integrated to form a complete 3D facial surface, which is almost as accurate as the reconstruction result using a perspective projection model. The fourth module implements a novel smoothing process for the 3D facial surface by interpolating additional vertices from the vectors of the existing 3D vertices. Finally, the fifth module utilizes a new solution to overcome the missing point problem, which is caused by occlusion at high pan rotation angles, commonly arising in 3D reconstruction applications. The experimental results show that the proposed system achieves a promising result within a relatively short time.

UR - http://www.scopus.com/inward/record.url?scp=84863039244&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863039244&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84863039244

VL - 8

SP - 807

EP - 825

JO - International Journal of Innovative Computing, Information and Control

JF - International Journal of Innovative Computing, Information and Control

SN - 1349-4198

IS - 1 B

ER -