3B yüzlerde i̇fade, poz ve örtmeye dayanikli nirengi noktasi bulma

Hamdi Dibeklioǧlu; Albert Ali Salah; Lale Akarun

doi:10.1109/SIU.2009.5136436

3B yüzlerde i̇fade, poz ve örtmeye dayanikli nirengi noktasi bulma

Translated title of the contribution: Expression, pose and occlusion resistant 3D facial landmarking

Hamdi Dibeklioǧlu^*, Albert Ali Salah, Lale Akarun

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

This paper contrasts two approaches to facial landmarking in 3D. The first approach is statistical in nature, and is based on modeling the shape of each feature with Gaussian mixtures. The advantage of this approach is the uniform treatment of landmarks. The second approach is a hybrid method to find the nose tip, which does not require learning, and is robust under adverse conditions. We demonstrate the accuracy and cross-database performance of these methods on FRGC and Bosphorus databases.

Translated title of the contribution	Expression, pose and occlusion resistant 3D facial landmarking
Original language	Undefined/Unknown
Title of host publication	2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009
Pages	476-479
Number of pages	4
DOIs	https://doi.org/10.1109/SIU.2009.5136436
Publication status	Published - 2009
Event	2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009 - Antalya, Turkey Duration: 9 Apr 2009 → 11 Apr 2009

Publication series

Name	2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009

Conference

Conference	2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009
Country/Territory	Turkey
City	Antalya
Period	9/04/09 → 11/04/09

Access to Document

10.1109/SIU.2009.5136436

Cite this

Dibeklioǧlu, H., Salah, A. A., & Akarun, L. (2009). 3B yüzlerde i̇fade, poz ve örtmeye dayanikli nirengi noktasi bulma. In 2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009 (pp. 476-479). Article 5136436 (2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009). https://doi.org/10.1109/SIU.2009.5136436

@inproceedings{3a2609f12d914722831b6869eeb8633c,

title = "3B y{\"u}zlerde {\.i}fade, poz ve {\"o}rtmeye dayanikli nirengi noktasi bulma",

abstract = "This paper contrasts two approaches to facial landmarking in 3D. The first approach is statistical in nature, and is based on modeling the shape of each feature with Gaussian mixtures. The advantage of this approach is the uniform treatment of landmarks. The second approach is a hybrid method to find the nose tip, which does not require learning, and is robust under adverse conditions. We demonstrate the accuracy and cross-database performance of these methods on FRGC and Bosphorus databases.",

author = "Hamdi Dibeklioǧlu and Salah, {Albert Ali} and Lale Akarun",

year = "2009",

doi = "10.1109/SIU.2009.5136436",

language = "Undefined/Unknown",

isbn = "9781424444366",

series = "2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009",

pages = "476--479",

booktitle = "2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009",

note = "2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009 ; Conference date: 09-04-2009 Through 11-04-2009",

}

Dibeklioǧlu, H, Salah, AA & Akarun, L 2009, 3B yüzlerde i̇fade, poz ve örtmeye dayanikli nirengi noktasi bulma. in 2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009., 5136436, 2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009, pp. 476-479, 2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009, Antalya, Turkey, 9/04/09. https://doi.org/10.1109/SIU.2009.5136436

3B yüzlerde i̇fade, poz ve örtmeye dayanikli nirengi noktasi bulma. / Dibeklioǧlu, Hamdi; Salah, Albert Ali; Akarun, Lale.
2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009. 2009. p. 476-479 5136436 (2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - 3B yüzlerde i̇fade, poz ve örtmeye dayanikli nirengi noktasi bulma

AU - Dibeklioǧlu, Hamdi

AU - Salah, Albert Ali

AU - Akarun, Lale

PY - 2009

Y1 - 2009

N2 - This paper contrasts two approaches to facial landmarking in 3D. The first approach is statistical in nature, and is based on modeling the shape of each feature with Gaussian mixtures. The advantage of this approach is the uniform treatment of landmarks. The second approach is a hybrid method to find the nose tip, which does not require learning, and is robust under adverse conditions. We demonstrate the accuracy and cross-database performance of these methods on FRGC and Bosphorus databases.

AB - This paper contrasts two approaches to facial landmarking in 3D. The first approach is statistical in nature, and is based on modeling the shape of each feature with Gaussian mixtures. The advantage of this approach is the uniform treatment of landmarks. The second approach is a hybrid method to find the nose tip, which does not require learning, and is robust under adverse conditions. We demonstrate the accuracy and cross-database performance of these methods on FRGC and Bosphorus databases.

UR - http://www.scopus.com/inward/record.url?scp=70350339505&partnerID=8YFLogxK

U2 - 10.1109/SIU.2009.5136436

DO - 10.1109/SIU.2009.5136436

M3 - Conference contribution

AN - SCOPUS:70350339505

SN - 9781424444366

T3 - 2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009

SP - 476

EP - 479

BT - 2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009

T2 - 2009 IEEE 17th Signal Processing and Communications Applications Conference, SIU 2009

Y2 - 9 April 2009 through 11 April 2009

ER -

3B yüzlerde i̇fade, poz ve örtmeye dayanikli nirengi noktasi bulma

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this