Face recognition under varying poses

The role of texture and shape

Nikolaus F. Troje, Heinrich Bulthoff

Research output: Contribution to journalArticle

301 Citations (Scopus)

Abstract

Although remarkably robust, face recognition is not perfectly invariant to pose and viewpoint changes. It has long been known that both profile and full-face views result in poorer recognition performance than a 3/4 view. However, little data exist which investigate this phenomenon in detail. The present work provides such data using a high angular resolution and a large range of poses. Since there are inconsistencies in the literature concerning these issues, we emphasize the different roles of the learning view and the testing view in the recognition experiment. We also emphasize the roles of information contained in the texture and in the shape of a face. Our stimuli were generated from laser-scanned head models and contained either the natural texture or only Lambertian shading and no texture. The results of our same/different face recognition experiments are: (1) only the learning view but not the testing view affects recognition performance. (2) For textured faces the optimal learning view is closer to the full-face view than for the shaded faces. (3) For shaded faces, we find a significantly better recognition performance for the symmetric view. The results can be interpreted in terms of different strategies to recover invariants from texture and from shading.

Original languageEnglish
Pages (from-to)1761-1771
Number of pages11
JournalVision Research
Volume36
Issue number12
DOIs
Publication statusPublished - 1996 Jun 1
Externally publishedYes

Fingerprint

Learning
Facial Recognition
Lasers
Head
Recognition (Psychology)

Keywords

  • Face recognition
  • Shading
  • Symmetry
  • Texture
  • Viewpoint invariance

ASJC Scopus subject areas

  • Ophthalmology
  • Sensory Systems

Cite this

Face recognition under varying poses : The role of texture and shape. / Troje, Nikolaus F.; Bulthoff, Heinrich.

In: Vision Research, Vol. 36, No. 12, 01.06.1996, p. 1761-1771.

Research output: Contribution to journalArticle

@article{3b4fd7c3db494e5da9e19d5ddb1a28e3,
title = "Face recognition under varying poses: The role of texture and shape",
abstract = "Although remarkably robust, face recognition is not perfectly invariant to pose and viewpoint changes. It has long been known that both profile and full-face views result in poorer recognition performance than a 3/4 view. However, little data exist which investigate this phenomenon in detail. The present work provides such data using a high angular resolution and a large range of poses. Since there are inconsistencies in the literature concerning these issues, we emphasize the different roles of the learning view and the testing view in the recognition experiment. We also emphasize the roles of information contained in the texture and in the shape of a face. Our stimuli were generated from laser-scanned head models and contained either the natural texture or only Lambertian shading and no texture. The results of our same/different face recognition experiments are: (1) only the learning view but not the testing view affects recognition performance. (2) For textured faces the optimal learning view is closer to the full-face view than for the shaded faces. (3) For shaded faces, we find a significantly better recognition performance for the symmetric view. The results can be interpreted in terms of different strategies to recover invariants from texture and from shading.",
keywords = "Face recognition, Shading, Symmetry, Texture, Viewpoint invariance",
author = "Troje, {Nikolaus F.} and Heinrich Bulthoff",
year = "1996",
month = "6",
day = "1",
doi = "10.1016/0042-6989(95)00230-8",
language = "English",
volume = "36",
pages = "1761--1771",
journal = "Vision Research",
issn = "0042-6989",
publisher = "Elsevier Limited",
number = "12",

}

TY - JOUR

T1 - Face recognition under varying poses

T2 - The role of texture and shape

AU - Troje, Nikolaus F.

AU - Bulthoff, Heinrich

PY - 1996/6/1

Y1 - 1996/6/1

N2 - Although remarkably robust, face recognition is not perfectly invariant to pose and viewpoint changes. It has long been known that both profile and full-face views result in poorer recognition performance than a 3/4 view. However, little data exist which investigate this phenomenon in detail. The present work provides such data using a high angular resolution and a large range of poses. Since there are inconsistencies in the literature concerning these issues, we emphasize the different roles of the learning view and the testing view in the recognition experiment. We also emphasize the roles of information contained in the texture and in the shape of a face. Our stimuli were generated from laser-scanned head models and contained either the natural texture or only Lambertian shading and no texture. The results of our same/different face recognition experiments are: (1) only the learning view but not the testing view affects recognition performance. (2) For textured faces the optimal learning view is closer to the full-face view than for the shaded faces. (3) For shaded faces, we find a significantly better recognition performance for the symmetric view. The results can be interpreted in terms of different strategies to recover invariants from texture and from shading.

AB - Although remarkably robust, face recognition is not perfectly invariant to pose and viewpoint changes. It has long been known that both profile and full-face views result in poorer recognition performance than a 3/4 view. However, little data exist which investigate this phenomenon in detail. The present work provides such data using a high angular resolution and a large range of poses. Since there are inconsistencies in the literature concerning these issues, we emphasize the different roles of the learning view and the testing view in the recognition experiment. We also emphasize the roles of information contained in the texture and in the shape of a face. Our stimuli were generated from laser-scanned head models and contained either the natural texture or only Lambertian shading and no texture. The results of our same/different face recognition experiments are: (1) only the learning view but not the testing view affects recognition performance. (2) For textured faces the optimal learning view is closer to the full-face view than for the shaded faces. (3) For shaded faces, we find a significantly better recognition performance for the symmetric view. The results can be interpreted in terms of different strategies to recover invariants from texture and from shading.

KW - Face recognition

KW - Shading

KW - Symmetry

KW - Texture

KW - Viewpoint invariance

UR - http://www.scopus.com/inward/record.url?scp=0342561506&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0342561506&partnerID=8YFLogxK

U2 - 10.1016/0042-6989(95)00230-8

DO - 10.1016/0042-6989(95)00230-8

M3 - Article

VL - 36

SP - 1761

EP - 1771

JO - Vision Research

JF - Vision Research

SN - 0042-6989

IS - 12

ER -