A Quadratic Deformation Model for Facial Expression Recognition

Mohammad Obaid; null Mukundan; Roland Goecke; null Billinghurst; null Seichter

doi:10.1109/DICTA.2009.51

A Quadratic Deformation Model for Facial Expression Recognition

Mohammad Obaid, Mukundan, Roland Goecke, Billinghurst, Seichter

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

1 Citation (Scopus)

46 Downloads (Pure)

Abstract

In this paper, we propose a novel approach for recognizing facial expressions based on using an active appearance model facial feature tracking system with the quadratic deformation model representations of facial expressions. Thirty seven facial feature points are tracked based on the MPEG-4 facial animation parameters layout. The proposed approach relies on the Euclidean distance measures between the tracked feature points and the reference deformed facial feature points of the six main expressions (smile, sad, fear, disgust, surprise, and anger). An evaluation of 30 model subjects, selected randomly from the Cohn-Kanade database, was carried out. Results show that the main six facial expressions can successfully be recognized with an overall recognition accuracy of 89%. The proposed approach yields to promising recognition rates and can be used in real time applications

Original language	English
Title of host publication	Proceedings of the 2009 Digital Image Computing: Techniques and Applications
Editors	Hao Shi, Yanchun Zhang, Murk J Bottema, Brian C Lovell, Anthony J Maeder
Place of Publication	Australia
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	264-270
Number of pages	7
Volume	1
ISBN (Print)	9781424452972
DOIs	https://doi.org/10.1109/DICTA.2009.51
Publication status	Published - 2009
Event	2009 Digital Image Computing: Techniques and Applications, DICTA 2009 - Melbourne, Australia Duration: 1 Dec 2009 → 3 Dec 2009

Conference

Conference	2009 Digital Image Computing: Techniques and Applications, DICTA 2009
Country/Territory	Australia
City	Melbourne
Period	1/12/09 → 3/12/09

Access to Document

10.1109/DICTA.2009.51

PaperFinal published version, 924 KB

Cite this

Obaid, M., Mukundan, Goecke, R., Billinghurst, & Seichter (2009). A Quadratic Deformation Model for Facial Expression Recognition. In H. Shi, Y. Zhang, M. J. Bottema, B. C. Lovell, & A. J. Maeder (Eds.), Proceedings of the 2009 Digital Image Computing: Techniques and Applications (Vol. 1, pp. 264-270). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/DICTA.2009.51

Obaid, Mohammad ; Mukundan ; Goecke, Roland et al. / A Quadratic Deformation Model for Facial Expression Recognition. Proceedings of the 2009 Digital Image Computing: Techniques and Applications. editor / Hao Shi ; Yanchun Zhang ; Murk J Bottema ; Brian C Lovell ; Anthony J Maeder. Vol. 1 Australia : IEEE, Institute of Electrical and Electronics Engineers, 2009. pp. 264-270

@inproceedings{542521dd7d104cef9fc2b57d2135bb9b,

title = "A Quadratic Deformation Model for Facial Expression Recognition",

abstract = "In this paper, we propose a novel approach for recognizing facial expressions based on using an active appearance model facial feature tracking system with the quadratic deformation model representations of facial expressions. Thirty seven facial feature points are tracked based on the MPEG-4 facial animation parameters layout. The proposed approach relies on the Euclidean distance measures between the tracked feature points and the reference deformed facial feature points of the six main expressions (smile, sad, fear, disgust, surprise, and anger). An evaluation of 30 model subjects, selected randomly from the Cohn-Kanade database, was carried out. Results show that the main six facial expressions can successfully be recognized with an overall recognition accuracy of 89%. The proposed approach yields to promising recognition rates and can be used in real time applications",

author = "Mohammad Obaid and Mukundan and Roland Goecke and Billinghurst and Seichter",

year = "2009",

doi = "10.1109/DICTA.2009.51",

language = "English",

isbn = "9781424452972",

volume = "1",

pages = "264--270",

editor = "Hao Shi and Yanchun Zhang and Bottema, {Murk J} and Lovell, {Brian C} and Maeder, {Anthony J}",

booktitle = "Proceedings of the 2009 Digital Image Computing: Techniques and Applications",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

note = "2009 Digital Image Computing: Techniques and Applications, DICTA 2009 ; Conference date: 01-12-2009 Through 03-12-2009",

}

Obaid, M, Mukundan, Goecke, R, Billinghurst & Seichter 2009, A Quadratic Deformation Model for Facial Expression Recognition. in H Shi, Y Zhang, MJ Bottema, BC Lovell & AJ Maeder (eds), Proceedings of the 2009 Digital Image Computing: Techniques and Applications. vol. 1, IEEE, Institute of Electrical and Electronics Engineers, Australia, pp. 264-270, 2009 Digital Image Computing: Techniques and Applications, DICTA 2009, Melbourne, Australia, 1/12/09. https://doi.org/10.1109/DICTA.2009.51

A Quadratic Deformation Model for Facial Expression Recognition. / Obaid, Mohammad; Mukundan; Goecke, Roland et al.
Proceedings of the 2009 Digital Image Computing: Techniques and Applications. ed. / Hao Shi; Yanchun Zhang; Murk J Bottema; Brian C Lovell; Anthony J Maeder. Vol. 1 Australia: IEEE, Institute of Electrical and Electronics Engineers, 2009. p. 264-270.

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

TY - GEN

T1 - A Quadratic Deformation Model for Facial Expression Recognition

AU - Obaid, Mohammad

AU - Mukundan, null

AU - Goecke, Roland

AU - Billinghurst, null

AU - Seichter, null

PY - 2009

Y1 - 2009

N2 - In this paper, we propose a novel approach for recognizing facial expressions based on using an active appearance model facial feature tracking system with the quadratic deformation model representations of facial expressions. Thirty seven facial feature points are tracked based on the MPEG-4 facial animation parameters layout. The proposed approach relies on the Euclidean distance measures between the tracked feature points and the reference deformed facial feature points of the six main expressions (smile, sad, fear, disgust, surprise, and anger). An evaluation of 30 model subjects, selected randomly from the Cohn-Kanade database, was carried out. Results show that the main six facial expressions can successfully be recognized with an overall recognition accuracy of 89%. The proposed approach yields to promising recognition rates and can be used in real time applications

AB - In this paper, we propose a novel approach for recognizing facial expressions based on using an active appearance model facial feature tracking system with the quadratic deformation model representations of facial expressions. Thirty seven facial feature points are tracked based on the MPEG-4 facial animation parameters layout. The proposed approach relies on the Euclidean distance measures between the tracked feature points and the reference deformed facial feature points of the six main expressions (smile, sad, fear, disgust, surprise, and anger). An evaluation of 30 model subjects, selected randomly from the Cohn-Kanade database, was carried out. Results show that the main six facial expressions can successfully be recognized with an overall recognition accuracy of 89%. The proposed approach yields to promising recognition rates and can be used in real time applications

U2 - 10.1109/DICTA.2009.51

DO - 10.1109/DICTA.2009.51

M3 - Conference contribution

SN - 9781424452972

VL - 1

SP - 264

EP - 270

BT - Proceedings of the 2009 Digital Image Computing: Techniques and Applications

A2 - Shi, Hao

A2 - Zhang, Yanchun

A2 - Bottema, Murk J

A2 - Lovell, Brian C

A2 - Maeder, Anthony J

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Australia

T2 - 2009 Digital Image Computing: Techniques and Applications, DICTA 2009

Y2 - 1 December 2009 through 3 December 2009

ER -

Obaid M, Mukundan, Goecke R, Billinghurst, Seichter. A Quadratic Deformation Model for Facial Expression Recognition. In Shi H, Zhang Y, Bottema MJ, Lovell BC, Maeder AJ, editors, Proceedings of the 2009 Digital Image Computing: Techniques and Applications. Vol. 1. Australia: IEEE, Institute of Electrical and Electronics Engineers. 2009. p. 264-270 doi: 10.1109/DICTA.2009.51