Face reconstruction from a small number of feature points

Bon Woo Hwang, Volker Blanz, Thomas Vetter, Seong Whan Lee

Research output: Chapter in Book/Report/Conference proceedingChapter

20 Citations (Scopus)

Abstract

This paper proposes a method for face reconstruction that makes use of only a small set of feature points. Faces can be modeled by forming linear combinations of prototypes of shape and texture information. With the shape and texture information at the feature points alone, we can achieve only an approximation to the deformation required. In such an under-determined condition, we find an optimal solution using a simple least square minimization method. As experimental results, we show well-reconstructed 2D faces even from a small number of feature points.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages838-841
Number of pages4
Volume15
Edition2
Publication statusPublished - 2000

Fingerprint

Textures

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

Cite this

Hwang, B. W., Blanz, V., Vetter, T., & Lee, S. W. (2000). Face reconstruction from a small number of feature points. In Proceedings - International Conference on Pattern Recognition (2 ed., Vol. 15, pp. 838-841)

Face reconstruction from a small number of feature points. / Hwang, Bon Woo; Blanz, Volker; Vetter, Thomas; Lee, Seong Whan.

Proceedings - International Conference on Pattern Recognition. Vol. 15 2. ed. 2000. p. 838-841.

Research output: Chapter in Book/Report/Conference proceedingChapter

Hwang, BW, Blanz, V, Vetter, T & Lee, SW 2000, Face reconstruction from a small number of feature points. in Proceedings - International Conference on Pattern Recognition. 2 edn, vol. 15, pp. 838-841.
Hwang BW, Blanz V, Vetter T, Lee SW. Face reconstruction from a small number of feature points. In Proceedings - International Conference on Pattern Recognition. 2 ed. Vol. 15. 2000. p. 838-841
Hwang, Bon Woo ; Blanz, Volker ; Vetter, Thomas ; Lee, Seong Whan. / Face reconstruction from a small number of feature points. Proceedings - International Conference on Pattern Recognition. Vol. 15 2. ed. 2000. pp. 838-841
@inbook{2c510879ea4d427db95a8cef42856558,
title = "Face reconstruction from a small number of feature points",
abstract = "This paper proposes a method for face reconstruction that makes use of only a small set of feature points. Faces can be modeled by forming linear combinations of prototypes of shape and texture information. With the shape and texture information at the feature points alone, we can achieve only an approximation to the deformation required. In such an under-determined condition, we find an optimal solution using a simple least square minimization method. As experimental results, we show well-reconstructed 2D faces even from a small number of feature points.",
author = "Hwang, {Bon Woo} and Volker Blanz and Thomas Vetter and Lee, {Seong Whan}",
year = "2000",
language = "English",
volume = "15",
pages = "838--841",
booktitle = "Proceedings - International Conference on Pattern Recognition",
edition = "2",

}

TY - CHAP

T1 - Face reconstruction from a small number of feature points

AU - Hwang, Bon Woo

AU - Blanz, Volker

AU - Vetter, Thomas

AU - Lee, Seong Whan

PY - 2000

Y1 - 2000

N2 - This paper proposes a method for face reconstruction that makes use of only a small set of feature points. Faces can be modeled by forming linear combinations of prototypes of shape and texture information. With the shape and texture information at the feature points alone, we can achieve only an approximation to the deformation required. In such an under-determined condition, we find an optimal solution using a simple least square minimization method. As experimental results, we show well-reconstructed 2D faces even from a small number of feature points.

AB - This paper proposes a method for face reconstruction that makes use of only a small set of feature points. Faces can be modeled by forming linear combinations of prototypes of shape and texture information. With the shape and texture information at the feature points alone, we can achieve only an approximation to the deformation required. In such an under-determined condition, we find an optimal solution using a simple least square minimization method. As experimental results, we show well-reconstructed 2D faces even from a small number of feature points.

UR - http://www.scopus.com/inward/record.url?scp=34147108363&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34147108363&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:34147108363

VL - 15

SP - 838

EP - 841

BT - Proceedings - International Conference on Pattern Recognition

ER -