By the same authors

From the same journal

Estimating facial albedo from a single image

Research output: Contribution to journalArticle

Standard

Estimating facial albedo from a single image. / Smith, William A. P.; Hancock, Edwin R.

In: INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, Vol. 20, No. 6, 09.2006, p. 955-970.

Research output: Contribution to journalArticle

Harvard

Smith, WAP & Hancock, ER 2006, 'Estimating facial albedo from a single image', INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, vol. 20, no. 6, pp. 955-970.

APA

Smith, W. A. P., & Hancock, E. R. (2006). Estimating facial albedo from a single image. INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 20(6), 955-970.

Vancouver

Smith WAP, Hancock ER. Estimating facial albedo from a single image. INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE. 2006 Sep;20(6):955-970.

Author

Smith, William A. P. ; Hancock, Edwin R. / Estimating facial albedo from a single image. In: INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE. 2006 ; Vol. 20, No. 6. pp. 955-970.

Bibtex - Download

@article{dd75639e62d04ffa9fcabda651845217,
title = "Estimating facial albedo from a single image",
abstract = "This paper describes how a facial albedo map can be recovered from a single image using a statistical model that captures variations in surface normal direction. We fit the model to intensity data using constraints on the surface normal direction provided by Lambert's law and then use the differences between observed and reconstructed image brightness to estimate the albedo. We show that this process is stable under varying illumination. We then show how eigenfaces trained on albedo maps may provide a better representation for illumination insensitive recognition than those trained on raw image intensity.",
keywords = "albedo estimation, shape-from-shading, face recognition, SHAPE, ILLUMINATION",
author = "Smith, {William A. P.} and Hancock, {Edwin R.}",
note = "1st International Symposium on Brain, Vision, and Artificial Intelligence, Naples, ITALY, OCT 19-21, 2005",
year = "2006",
month = "9",
language = "English",
volume = "20",
pages = "955--970",
journal = "INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE",
issn = "0218-0014",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "6",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Estimating facial albedo from a single image

AU - Smith, William A. P.

AU - Hancock, Edwin R.

N1 - 1st International Symposium on Brain, Vision, and Artificial Intelligence, Naples, ITALY, OCT 19-21, 2005

PY - 2006/9

Y1 - 2006/9

N2 - This paper describes how a facial albedo map can be recovered from a single image using a statistical model that captures variations in surface normal direction. We fit the model to intensity data using constraints on the surface normal direction provided by Lambert's law and then use the differences between observed and reconstructed image brightness to estimate the albedo. We show that this process is stable under varying illumination. We then show how eigenfaces trained on albedo maps may provide a better representation for illumination insensitive recognition than those trained on raw image intensity.

AB - This paper describes how a facial albedo map can be recovered from a single image using a statistical model that captures variations in surface normal direction. We fit the model to intensity data using constraints on the surface normal direction provided by Lambert's law and then use the differences between observed and reconstructed image brightness to estimate the albedo. We show that this process is stable under varying illumination. We then show how eigenfaces trained on albedo maps may provide a better representation for illumination insensitive recognition than those trained on raw image intensity.

KW - albedo estimation

KW - shape-from-shading

KW - face recognition

KW - SHAPE

KW - ILLUMINATION

M3 - Article

VL - 20

SP - 955

EP - 970

JO - INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE

JF - INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE

SN - 0218-0014

IS - 6

ER -