Skip navigation
Skip navigation

Evaluating AAM Fitting Methods for Facial Expression Recognition

Asthana, Akshay; Saragih, Jason; Wagner, Michael; Goecke, Roland

Description

The human face is a rich source of information for the viewer and facial expressions are a major component in judging a person's affective state, intention and personality. Facial expressions are an important part of human-human interaction and have the potential to play an equally important part in human-computer interaction. This paper evaluates various Active Appearance Model (AAM) fitting methods, including both the original formulation as well as several state-of-the-art methods, for the...[Show more]

dc.contributor.authorAsthana, Akshay
dc.contributor.authorSaragih, Jason
dc.contributor.authorWagner, Michael
dc.contributor.authorGoecke, Roland
dc.coverage.spatialAmsterdam The Netherlands
dc.date.accessioned2015-12-10T22:32:31Z
dc.date.createdSeptember 10-12 2009
dc.identifier.isbn9781424447992
dc.identifier.urihttp://hdl.handle.net/1885/55800
dc.description.abstractThe human face is a rich source of information for the viewer and facial expressions are a major component in judging a person's affective state, intention and personality. Facial expressions are an important part of human-human interaction and have the potential to play an equally important part in human-computer interaction. This paper evaluates various Active Appearance Model (AAM) fitting methods, including both the original formulation as well as several state-of-the-art methods, for the task of automatic facial expression recognition. The AAM is a powerful statistical model for modelling and registering deformable objects. The results of the fitting process are used in a facial expression recognition task using a region-based intermediate representation related to Action Units, with the expression classification task realised using a Support Vector Machine. Experiments are performed for both persondependent and person-independent setups. Overall, the best facial expression recognition results were obtained by using the Iterative Error Bound Minimisation method, which consistently resulted in accurate face model alignment and facial expression recognition even when the initial face detection used to initialise the fitting procedure was poor.
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE Inc)
dc.relation.ispartofseriesInternational Conference on Affective Computing & Intelligent Interaction (ACII 2009)
dc.sourceAn Approach for Automatically Measuring Facial Activity in Depressed Subjects
dc.source.urihttp://doc.utwente.nl/68953
dc.subjectKeywords: Action Unit; Active appearance models; Affective state; Automatic facial expression recognition; Classification tasks; Deformable object; Face Detection; Face models; Facial expression recognition; Facial Expressions; Fitting method; Fitting procedure; Hu
dc.titleEvaluating AAM Fitting Methods for Facial Expression Recognition
dc.typeConference paper
local.description.notesImported from ARIES
local.description.refereedYes
dc.date.issued2009
local.identifier.absfor080602 - Computer-Human Interaction
local.identifier.ariespublicationu4334215xPUB340
local.type.statusPublished Version
local.contributor.affiliationAsthana, Akshay, College of Engineering and Computer Science, ANU
local.contributor.affiliationSaragih, Jason, Carnegie Mellon University
local.contributor.affiliationWagner, Michael, University of Canberra
local.contributor.affiliationGoecke, Roland, College of Engineering and Computer Science, ANU
local.description.embargo2037-12-31
local.bibliographicCitation.startpage598
local.bibliographicCitation.lastpage605
local.identifier.doi10.1109/ACII.2009.5349489
dc.date.updated2016-02-24T11:00:02Z
local.identifier.scopusID2-s2.0-77949392410
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Asthana_Evaluating_AAM_Fitting_Methods_2009.pdf279.19 kBAdobe PDFThumbnail


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator