An approach for automatically measuring facial activity in depressed subjects

Gordon McIntyre; Roland Göcke; Matthew Hyett; Melissa Green; Michael Breakspear

doi:10.1109/ACII.2009.5349593

An approach for automatically measuring facial activity in depressed subjects

Gordon McIntyre^*, Roland Göcke, Matthew Hyett, Melissa Green, Michael Breakspear

^*Corresponding author for this work

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

49 Citations (Scopus)

Abstract

This paper is motivated by Ellgring's work in non-verbal communication in depression to measure and compare the levels of facial activity, before and after treatment, of endogenous and neurotic depressives. Similar to that work, we loosely associate the measurements with Action Units (AU) groups from the Facial Action Coding System (FACS). However, we use the neologism Region Units (RU) to describe regions of the face that encapsulate AUs. In contrast to Ellgring's approach, we automatically generate the measurements and provide both prototypical expression recognition and RU-specific activity measurements. Latency between expressions is also measured and the system is conducive to comparison across groups and individual subjects. By using Active Appearance Models (AAM) to locate the fiduciary facial points, and MultiBoost to classify prototypical expressions and the RUs, we can provide a simple, objective, flexible and cost-effective means of automatically measuring facial activity.

Original language	English
Title of host publication	Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009
DOIs	https://doi.org/10.1109/ACII.2009.5349593
Publication status	Published - 2009
Event	2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009 - Amsterdam, Netherlands Duration: 10 Sept 2009 → 12 Sept 2009

Publication series

Name	Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009

Conference

Conference	2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009
Country/Territory	Netherlands
City	Amsterdam
Period	10/09/09 → 12/09/09

Access to Document

10.1109/ACII.2009.5349593

Cite this

McIntyre, G., Göcke, R., Hyett, M., Green, M., & Breakspear, M. (2009). An approach for automatically measuring facial activity in depressed subjects. In Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009 Article 5349593 (Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009). https://doi.org/10.1109/ACII.2009.5349593

McIntyre, Gordon ; Göcke, Roland ; Hyett, Matthew et al. / An approach for automatically measuring facial activity in depressed subjects. Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009. 2009. (Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009).

@inproceedings{0a7a074118f0464eb8ed0fa87e82d641,

title = "An approach for automatically measuring facial activity in depressed subjects",

abstract = "This paper is motivated by Ellgring's work in non-verbal communication in depression to measure and compare the levels of facial activity, before and after treatment, of endogenous and neurotic depressives. Similar to that work, we loosely associate the measurements with Action Units (AU) groups from the Facial Action Coding System (FACS). However, we use the neologism Region Units (RU) to describe regions of the face that encapsulate AUs. In contrast to Ellgring's approach, we automatically generate the measurements and provide both prototypical expression recognition and RU-specific activity measurements. Latency between expressions is also measured and the system is conducive to comparison across groups and individual subjects. By using Active Appearance Models (AAM) to locate the fiduciary facial points, and MultiBoost to classify prototypical expressions and the RUs, we can provide a simple, objective, flexible and cost-effective means of automatically measuring facial activity.",

author = "Gordon McIntyre and Roland G{\"o}cke and Matthew Hyett and Melissa Green and Michael Breakspear",

year = "2009",

doi = "10.1109/ACII.2009.5349593",

language = "English",

isbn = "9781424447992",

series = "Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009",

booktitle = "Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009",

note = "2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009 ; Conference date: 10-09-2009 Through 12-09-2009",

}

McIntyre, G, Göcke, R, Hyett, M, Green, M & Breakspear, M 2009, An approach for automatically measuring facial activity in depressed subjects. in Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009., 5349593, Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009, 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009, Amsterdam, Netherlands, 10/09/09. https://doi.org/10.1109/ACII.2009.5349593

An approach for automatically measuring facial activity in depressed subjects. / McIntyre, Gordon; Göcke, Roland; Hyett, Matthew et al.
Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009. 2009. 5349593 (Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009).

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

TY - GEN

T1 - An approach for automatically measuring facial activity in depressed subjects

AU - McIntyre, Gordon

AU - Göcke, Roland

AU - Hyett, Matthew

AU - Green, Melissa

AU - Breakspear, Michael

PY - 2009

Y1 - 2009

N2 - This paper is motivated by Ellgring's work in non-verbal communication in depression to measure and compare the levels of facial activity, before and after treatment, of endogenous and neurotic depressives. Similar to that work, we loosely associate the measurements with Action Units (AU) groups from the Facial Action Coding System (FACS). However, we use the neologism Region Units (RU) to describe regions of the face that encapsulate AUs. In contrast to Ellgring's approach, we automatically generate the measurements and provide both prototypical expression recognition and RU-specific activity measurements. Latency between expressions is also measured and the system is conducive to comparison across groups and individual subjects. By using Active Appearance Models (AAM) to locate the fiduciary facial points, and MultiBoost to classify prototypical expressions and the RUs, we can provide a simple, objective, flexible and cost-effective means of automatically measuring facial activity.

AB - This paper is motivated by Ellgring's work in non-verbal communication in depression to measure and compare the levels of facial activity, before and after treatment, of endogenous and neurotic depressives. Similar to that work, we loosely associate the measurements with Action Units (AU) groups from the Facial Action Coding System (FACS). However, we use the neologism Region Units (RU) to describe regions of the face that encapsulate AUs. In contrast to Ellgring's approach, we automatically generate the measurements and provide both prototypical expression recognition and RU-specific activity measurements. Latency between expressions is also measured and the system is conducive to comparison across groups and individual subjects. By using Active Appearance Models (AAM) to locate the fiduciary facial points, and MultiBoost to classify prototypical expressions and the RUs, we can provide a simple, objective, flexible and cost-effective means of automatically measuring facial activity.

UR - http://www.scopus.com/inward/record.url?scp=77949375429&partnerID=8YFLogxK

U2 - 10.1109/ACII.2009.5349593

DO - 10.1109/ACII.2009.5349593

M3 - Conference contribution

SN - 9781424447992

T3 - Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009

BT - Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009

T2 - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009

Y2 - 10 September 2009 through 12 September 2009

ER -

McIntyre G, Göcke R, Hyett M, Green M, Breakspear M. An approach for automatically measuring facial activity in depressed subjects. In Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009. 2009. 5349593. (Proceedings - 2009 3rd International Conference on Affective Computing and Intelligent Interaction and Workshops, ACII 2009). doi: 10.1109/ACII.2009.5349593

An approach for automatically measuring facial activity in depressed subjects

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this