How to Distinguish Posed from Spontaneous Smiles using Geometric Features

UTSePress Research/Manakin Repository

Search UTSePress Research


Advanced Search

Browse

My Account

Show simple item record

dc.contributor.author Valstar, Michel en_US
dc.contributor.author Gunes, Hatice en_US
dc.contributor.author Pantic, Maja en_US
dc.contributor.editor Kenji Mase, Dominic Massaro, Kazuya Takeda, Deb Roy and Alexandros Potamianos en_US
dc.date.accessioned 2010-05-18T06:51:06Z
dc.date.available 2010-05-18T06:51:06Z
dc.date.issued 2007 en_US
dc.identifier 2006014553 en_US
dc.identifier.citation Valstar Michel, Gunes Hatice, and Pantic Maja 2007, 'How to Distinguish Posed from Spontaneous Smiles using Geometric Features', ACM, New York, USA, pp. 38-45. en_US
dc.identifier.issn 978-1-59593-817-6 en_US
dc.identifier.other E1 en_US
dc.identifier.uri http://hdl.handle.net/10453/7295
dc.description.abstract Automatic distinction between posed and spontaneous expressions is an unsolved problem. Previously cognitive sciencesa?? studies indicated that the automatic separation of posed from spontaneous expressions is possible using the face modality alone. However, little is known about the information contained in head and shoulder motion. In this work, we propose to (i) distinguish between posed and spontaneous smiles by fusing the head, face, and shoulder modalities, (ii) investigate which modalities carry important information and how the information of the modalities relate to each other, and (iii) to which extent the temporal dynamics of these signals attribute to solving the problem. We use a cylindrical head tracker to track the head movements and two particle filtering techniques to track the facial and shoulder movements. Classification is performed by kernel methods combined with ensemble learning techniques. We investigated two aspects of multimodal fusion: the level of abstraction (i.e., early, mid-level, and late fusion) and the fusion rule used (i.e., sum, product and weight criteria). Experimental results from 100 videos displaying posed smiles and 102 videos displaying spontaneous smiles are presented. Best results were obtained with late fusion of all modalities when 94.0% of the videos were classified correctly. en_US
dc.publisher ACM en_US
dc.relation.isbasedon http://dx.doi.org/10.1145/1322192.1322202 en_US
dc.title How to Distinguish Posed from Spontaneous Smiles using Geometric Features en_US
dc.parent Proceedings of the ACM Ninth International Conference on Multimodal Interfaces en_US
dc.journal.volume en_US
dc.journal.number en_US
dc.publocation New York, USA en_US
dc.identifier.startpage 38 en_US
dc.identifier.endpage 45 en_US
dc.cauo.name FEIT.School of Systems, Management and Leadership en_US
dc.conference en_US
dc.conference Verified OK en_US
dc.conference.location Nagoya, Japan en_US
dc.for 080600 en_US
dc.personcode 0000035314 en_US
dc.personcode 034144 en_US
dc.personcode 0000035315 en_US
dc.percentage 100 en_US
dc.classification.name Information Systems en_US
dc.classification.type FOR-08 en_US
dc.custom International Conference on Multimodal Interfaces en_US
dc.date.activity 20071112 en_US
dc.location.activity Nagoya, Japan en_US
dc.description.keywords Human information processing, Deception detection, Multi- modal video processing en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record