Facial landmark configuration for improved detection

C. Huang; B. A. Efraty; U. Kurkure; M. Papadakis; S. K. Shah; I. A. Kakadiaris

doi:10.1109/WIFS.2012.6412618

Facial landmark configuration for improved detection

C. Huang, B. A. Efraty, U. Kurkure, M. Papadakis, S. K. Shah, I. A. Kakadiaris

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Scopus citations

Abstract

In this paper, we present two methods to improve the performance of landmark detection algorithms that are designed to detect individual landmarks. We focus on the landmark configuration module that takes the output of the individual landmark detectors and searches for a configuration of optimal landmark locations based on appropriate shape constraints. We design two configuration search approaches: (i) a multivariate conditional Gaussian-based model, and (ii) a MRF-based formulation with higher-order potentials. We evaluated the performance of our proposed methods using several state-of-the-art detectors, and consistently obtained improved performance.

Original language	English (US)
Title of host publication	WIFS 2012 - Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security
Pages	13-18
Number of pages	6
DOIs	https://doi.org/10.1109/WIFS.2012.6412618
State	Published - 2012
Event	2012 IEEE International Workshop on Information Forensics and Security, WIFS 2012 - Tenerife, Spain Duration: Dec 2 2012 → Dec 5 2012

Publication series

Name	WIFS 2012 - Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security

Conference

Conference	2012 IEEE International Workshop on Information Forensics and Security, WIFS 2012
Country/Territory	Spain
City	Tenerife
Period	12/2/12 → 12/5/12

ASJC Scopus subject areas

Computer Science Applications
Information Systems

Access to Document

10.1109/WIFS.2012.6412618

Cite this

Huang, C., Efraty, B. A., Kurkure, U., Papadakis, M., Shah, S. K., & Kakadiaris, I. A. (2012). Facial landmark configuration for improved detection. In WIFS 2012 - Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security (pp. 13-18). [6412618] (WIFS 2012 - Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security). https://doi.org/10.1109/WIFS.2012.6412618

Facial landmark configuration for improved detection. / Huang, C.; Efraty, B. A.; Kurkure, U. et al.

WIFS 2012 - Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security. 2012. p. 13-18 6412618 (WIFS 2012 - Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Huang, C, Efraty, BA, Kurkure, U, Papadakis, M, Shah, SK & Kakadiaris, IA 2012, Facial landmark configuration for improved detection. in WIFS 2012 - Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security., 6412618, WIFS 2012 - Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security, pp. 13-18, 2012 IEEE International Workshop on Information Forensics and Security, WIFS 2012, Tenerife, Spain, 12/2/12. https://doi.org/10.1109/WIFS.2012.6412618

Huang C, Efraty BA, Kurkure U, Papadakis M, Shah SK, Kakadiaris IA. Facial landmark configuration for improved detection. In WIFS 2012 - Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security. 2012. p. 13-18. 6412618. (WIFS 2012 - Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security). https://doi.org/10.1109/WIFS.2012.6412618

@inproceedings{3be48d6e40884ac291bf1a546f8e66c6,

title = "Facial landmark configuration for improved detection",

abstract = "In this paper, we present two methods to improve the performance of landmark detection algorithms that are designed to detect individual landmarks. We focus on the landmark configuration module that takes the output of the individual landmark detectors and searches for a configuration of optimal landmark locations based on appropriate shape constraints. We design two configuration search approaches: (i) a multivariate conditional Gaussian-based model, and (ii) a MRF-based formulation with higher-order potentials. We evaluated the performance of our proposed methods using several state-of-the-art detectors, and consistently obtained improved performance.",

author = "C. Huang and Efraty, {B. A.} and U. Kurkure and M. Papadakis and Shah, {S. K.} and Kakadiaris, {I. A.}",

year = "2012",

doi = "10.1109/WIFS.2012.6412618",

language = "English (US)",

isbn = "9781467322874",

series = "WIFS 2012 - Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security",

pages = "13--18",

booktitle = "WIFS 2012 - Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security",

note = "2012 IEEE International Workshop on Information Forensics and Security, WIFS 2012 ; Conference date: 02-12-2012 Through 05-12-2012",

}

TY - GEN

T1 - Facial landmark configuration for improved detection

AU - Huang, C.

AU - Efraty, B. A.

AU - Kurkure, U.

AU - Papadakis, M.

AU - Shah, S. K.

AU - Kakadiaris, I. A.

PY - 2012

Y1 - 2012

N2 - In this paper, we present two methods to improve the performance of landmark detection algorithms that are designed to detect individual landmarks. We focus on the landmark configuration module that takes the output of the individual landmark detectors and searches for a configuration of optimal landmark locations based on appropriate shape constraints. We design two configuration search approaches: (i) a multivariate conditional Gaussian-based model, and (ii) a MRF-based formulation with higher-order potentials. We evaluated the performance of our proposed methods using several state-of-the-art detectors, and consistently obtained improved performance.

AB - In this paper, we present two methods to improve the performance of landmark detection algorithms that are designed to detect individual landmarks. We focus on the landmark configuration module that takes the output of the individual landmark detectors and searches for a configuration of optimal landmark locations based on appropriate shape constraints. We design two configuration search approaches: (i) a multivariate conditional Gaussian-based model, and (ii) a MRF-based formulation with higher-order potentials. We evaluated the performance of our proposed methods using several state-of-the-art detectors, and consistently obtained improved performance.

UR - http://www.scopus.com/inward/record.url?scp=84874032341&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874032341&partnerID=8YFLogxK

U2 - 10.1109/WIFS.2012.6412618

DO - 10.1109/WIFS.2012.6412618

M3 - Conference contribution

AN - SCOPUS:84874032341

SN - 9781467322874

T3 - WIFS 2012 - Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security

SP - 13

EP - 18

BT - WIFS 2012 - Proceedings of the 2012 IEEE International Workshop on Information Forensics and Security

T2 - 2012 IEEE International Workshop on Information Forensics and Security, WIFS 2012

Y2 - 2 December 2012 through 5 December 2012

ER -

Facial landmark configuration for improved detection

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this