Automatic landmark location with a combined active shape model

Dianle Zhou; Dijana Petrovska-Delacrétaz; Bernadette Dorizzi

doi:10.1109/BTAS.2009.5339037

Automatic landmark location with a combined active shape model

Dianle Zhou
, Dijana Petrovska-Delacrétaz
, Bernadette Dorizzi

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collection › Contribution à une conférence › Revue par des pairs

Résumé

Automatic facial landmark location is a difficult challenge for realistic face recognition applications, where the face is recorded under variable illumination conditions including indoor and outdoor recordings and also with some pose and scale variability. Moreover, the image distortion and complex background also bring some difficulty both for landmark location and face recognition. The proposed landmark detection method, called Combined Active Shape Models, is robust to illumination, translation, and rotation. It exploits the Scale Invariant Feature Transform (SIFT) [1] and the Active Shape Model (ASM) [2]. In order to have a better representation of face images, the landmarks on the face region and the face contour are modeled and processed separately. The performance of the proposed Combined-ASM algorithm is tested on the BioID and FRGCv2.0 face image databases.

langue originale	Anglais
titre	IEEE 3rd International Conference on Biometrics
Sous-titre	Theory, Applications and Systems, BTAS 2009
Editeur	IEEE Computer Society
ISBN (imprimé)	9781424450206
Les DOIs	https://doi.org/10.1109/BTAS.2009.5339037
état	Publié - 1 janv. 2009
Evénement	3rd IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009 - Washington, DC, États-Unis Durée: 28 sept. 2009 → 30 sept. 2009

Série de publications

Nom	IEEE 3rd International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009

Une conférence

Une conférence	3rd IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009
Pays/Territoire	États-Unis
La ville	Washington, DC
période	28/09/09 → 30/09/09

Accès au document

10.1109/BTAS.2009.5339037

Contient cette citation

Zhou, D., Petrovska-Delacrétaz, D., & Dorizzi, B. (2009). Automatic landmark location with a combined active shape model. Dans IEEE 3rd International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009 Article 5339037 (IEEE 3rd International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009). IEEE Computer Society. https://doi.org/10.1109/BTAS.2009.5339037

@inproceedings{f1de11d4c5254384a360ad3bd2fc8020,

title = "Automatic landmark location with a combined active shape model",

abstract = "Automatic facial landmark location is a difficult challenge for realistic face recognition applications, where the face is recorded under variable illumination conditions including indoor and outdoor recordings and also with some pose and scale variability. Moreover, the image distortion and complex background also bring some difficulty both for landmark location and face recognition. The proposed landmark detection method, called Combined Active Shape Models, is robust to illumination, translation, and rotation. It exploits the Scale Invariant Feature Transform (SIFT) [1] and the Active Shape Model (ASM) [2]. In order to have a better representation of face images, the landmarks on the face region and the face contour are modeled and processed separately. The performance of the proposed Combined-ASM algorithm is tested on the BioID and FRGCv2.0 face image databases.",

author = "Dianle Zhou and Dijana Petrovska-Delacr{\'e}taz and Bernadette Dorizzi",

year = "2009",

month = jan,

day = "1",

doi = "10.1109/BTAS.2009.5339037",

language = "English",

isbn = "9781424450206",

series = "IEEE 3rd International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009",

publisher = "IEEE Computer Society",

booktitle = "IEEE 3rd International Conference on Biometrics",

note = "3rd IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009 ; Conference date: 28-09-2009 Through 30-09-2009",

}

Zhou, D, Petrovska-Delacrétaz, D & Dorizzi, B 2009, Automatic landmark location with a combined active shape model. Dans IEEE 3rd International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009., 5339037, IEEE 3rd International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009, IEEE Computer Society, 3rd IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009, Washington, DC, États-Unis, 28/09/09. https://doi.org/10.1109/BTAS.2009.5339037

Automatic landmark location with a combined active shape model. / Zhou, Dianle; Petrovska-Delacrétaz, Dijana; Dorizzi, Bernadette.
IEEE 3rd International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009. IEEE Computer Society, 2009. 5339037 (IEEE 3rd International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009).

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collection › Contribution à une conférence › Revue par des pairs

TY - GEN

T1 - Automatic landmark location with a combined active shape model

AU - Zhou, Dianle

AU - Petrovska-Delacrétaz, Dijana

AU - Dorizzi, Bernadette

PY - 2009/1/1

Y1 - 2009/1/1

N2 - Automatic facial landmark location is a difficult challenge for realistic face recognition applications, where the face is recorded under variable illumination conditions including indoor and outdoor recordings and also with some pose and scale variability. Moreover, the image distortion and complex background also bring some difficulty both for landmark location and face recognition. The proposed landmark detection method, called Combined Active Shape Models, is robust to illumination, translation, and rotation. It exploits the Scale Invariant Feature Transform (SIFT) [1] and the Active Shape Model (ASM) [2]. In order to have a better representation of face images, the landmarks on the face region and the face contour are modeled and processed separately. The performance of the proposed Combined-ASM algorithm is tested on the BioID and FRGCv2.0 face image databases.

AB - Automatic facial landmark location is a difficult challenge for realistic face recognition applications, where the face is recorded under variable illumination conditions including indoor and outdoor recordings and also with some pose and scale variability. Moreover, the image distortion and complex background also bring some difficulty both for landmark location and face recognition. The proposed landmark detection method, called Combined Active Shape Models, is robust to illumination, translation, and rotation. It exploits the Scale Invariant Feature Transform (SIFT) [1] and the Active Shape Model (ASM) [2]. In order to have a better representation of face images, the landmarks on the face region and the face contour are modeled and processed separately. The performance of the proposed Combined-ASM algorithm is tested on the BioID and FRGCv2.0 face image databases.

U2 - 10.1109/BTAS.2009.5339037

DO - 10.1109/BTAS.2009.5339037

M3 - Conference contribution

AN - SCOPUS:71749098189

SN - 9781424450206

T3 - IEEE 3rd International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009

BT - IEEE 3rd International Conference on Biometrics

PB - IEEE Computer Society

T2 - 3rd IEEE International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009

Y2 - 28 September 2009 through 30 September 2009

ER -

Zhou D, Petrovska-Delacrétaz D, Dorizzi B. Automatic landmark location with a combined active shape model. Dans IEEE 3rd International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009. IEEE Computer Society. 2009. 5339037. (IEEE 3rd International Conference on Biometrics: Theory, Applications and Systems, BTAS 2009). doi: 10.1109/BTAS.2009.5339037

Automatic landmark location with a combined active shape model

Résumé

Série de publications

Une conférence

Accès au document

Empreinte digitale

Contient cette citation