An Active Illumination and Appearance (AIA) Model for Face Alignment

Fatih Kahraman; Muhittin Gokmen; Sune Darkner; Rasmus Larsen

doi:10.1109/CVPR.2007.383399

An Active Illumination and Appearance (AIA) Model for Face Alignment

Fatih Kahraman, Muhittin Gokmen, Sune Darkner, Rasmus Larsen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

Face recognition systems are typically required to work under highly varying illumination conditions. This leads to complex effects imposed on the acquired face image that pertains little to the actual identity. Consequently, illumination normalization is required to reach acceptable recognition rates in face recognition systems. In this paper, we propose an approach that integrates the face identity and illumination models under the widely used Active Appearance Model framework as an extension to the texture model in order to obtain illumination-invariant face localization

Original language	English
Title of host publication	Proceedings of the CVPR 2007, IEEE Computer Society Workshop on Biometrics
Publisher	IEEE Computer Society Press
Publication date	2007
ISBN (Print)	1-4244-1180-7
DOIs	https://doi.org/10.1109/CVPR.2007.383399
Publication status	Published - 2007
Event	2007 IEEE Conference on Computer Vision and Pattern Recognition - Minneapolis, United States Duration: 17 Jun 2007 → 22 Jun 2007 https://ieeexplore.ieee.org/xpl/conhome/4269955/proceeding

Conference

Conference	2007 IEEE Conference on Computer Vision and Pattern Recognition
Country/Territory	United States
City	Minneapolis
Period	17/06/2007 → 22/06/2007
Internet address	https://ieeexplore.ieee.org/xpl/conhome/4269955/proceeding

Keywords

faces
texture
shape
illumination
aam

Access to Document

10.1109/CVPR.2007.383399

OpenUrl availability

Full text

Cite this

@inproceedings{84b47204461b4ef6b23746f6dc26d35b,

title = "An Active Illumination and Appearance (AIA) Model for Face Alignment",

abstract = "Face recognition systems are typically required to work under highly varying illumination conditions. This leads to complex effects imposed on the acquired face image that pertains little to the actual identity. Consequently, illumination normalization is required to reach acceptable recognition rates in face recognition systems. In this paper, we propose an approach that integrates the face identity and illumination models under the widely used Active Appearance Model framework as an extension to the texture model in order to obtain illumination-invariant face localization",

keywords = "faces, texture, shape, illumination, aam",

author = "Fatih Kahraman and Muhittin Gokmen and Sune Darkner and Rasmus Larsen",

year = "2007",

doi = "10.1109/CVPR.2007.383399",

language = "English",

isbn = "1-4244-1180-7",

booktitle = "Proceedings of the CVPR 2007, IEEE Computer Society Workshop on Biometrics",

publisher = "IEEE Computer Society Press",

note = "2007 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2007 ; Conference date: 17-06-2007 Through 22-06-2007",

url = "https://ieeexplore.ieee.org/xpl/conhome/4269955/proceeding",

}

Kahraman, F, Gokmen, M, Darkner, S & Larsen, R 2007, An Active Illumination and Appearance (AIA) Model for Face Alignment. in Proceedings of the CVPR 2007, IEEE Computer Society Workshop on Biometrics. IEEE Computer Society Press, 2007 IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, Minnesota, United States, 17/06/2007. https://doi.org/10.1109/CVPR.2007.383399

TY - GEN

T1 - An Active Illumination and Appearance (AIA) Model for Face Alignment

AU - Kahraman, Fatih

AU - Gokmen, Muhittin

AU - Darkner, Sune

AU - Larsen, Rasmus

PY - 2007

Y1 - 2007

N2 - Face recognition systems are typically required to work under highly varying illumination conditions. This leads to complex effects imposed on the acquired face image that pertains little to the actual identity. Consequently, illumination normalization is required to reach acceptable recognition rates in face recognition systems. In this paper, we propose an approach that integrates the face identity and illumination models under the widely used Active Appearance Model framework as an extension to the texture model in order to obtain illumination-invariant face localization

AB - Face recognition systems are typically required to work under highly varying illumination conditions. This leads to complex effects imposed on the acquired face image that pertains little to the actual identity. Consequently, illumination normalization is required to reach acceptable recognition rates in face recognition systems. In this paper, we propose an approach that integrates the face identity and illumination models under the widely used Active Appearance Model framework as an extension to the texture model in order to obtain illumination-invariant face localization

KW - faces

KW - texture

KW - shape

KW - illumination

KW - aam

U2 - 10.1109/CVPR.2007.383399

DO - 10.1109/CVPR.2007.383399

M3 - Article in proceedings

SN - 1-4244-1180-7

BT - Proceedings of the CVPR 2007, IEEE Computer Society Workshop on Biometrics

PB - IEEE Computer Society Press

T2 - 2007 IEEE Conference on Computer Vision and Pattern Recognition

Y2 - 17 June 2007 through 22 June 2007

ER -

An Active Illumination and Appearance (AIA) Model for Face Alignment

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this