Adaptation of facial feature extraction and rule generation in emotion-analysis systems

Ioannou, S; Raouzaiou, A; Karpouzis, K; Kollias, S

dc.contributor.author	Ioannou, S	en
dc.contributor.author	Raouzaiou, A	en
dc.contributor.author	Karpouzis, K	en
dc.contributor.author	Kollias, S	en
dc.date.accessioned	2014-03-01T02:42:26Z
dc.date.available	2014-03-01T02:42:26Z
dc.date.issued	2004	en
dc.identifier.issn	10987576	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31005
dc.subject	Emotion Recognition	en
dc.subject	Environmental Conditions	en
dc.subject	Facial Expression	en
dc.subject	Facial Feature Extraction	en
dc.subject	Facial Features	en
dc.subject	Human Computer Interaction	en
dc.subject	neuro-fuzzy system	en
dc.subject	Rule Extraction	en
dc.subject.other	Animation	en
dc.subject.other	Database systems	en
dc.subject.other	Human computer interaction	en
dc.subject.other	Linguistics	en
dc.subject.other	Motion pictures	en
dc.subject.other	Optimization	en
dc.subject.other	Project management	en
dc.subject.other	Psychophysiology	en
dc.subject.other	Synchronization	en
dc.subject.other	Face and Body Animation (FBA)	en
dc.subject.other	Facial Animation Parameters (FAP)	en
dc.subject.other	Facial Definition Parameters (FDP)	en
dc.subject.other	Feature points (FP)	en
dc.subject.other	Feature extraction	en
dc.title	Adaptation of facial feature extraction and rule generation in emotion-analysis systems	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/IJCNN.2004.1379962	en
heal.identifier.secondary	http://dx.doi.org/10.1109/IJCNN.2004.1379962	en
heal.publicationDate	2004	en
heal.abstract	The paper addresses the problem of emotion recognition in faces through an intelligent neuro-fuzzy system, where the extraction of facial features follows the MPEG-4 standard and is adapted to particular environmental conditions and specific persons. These features are associated to symbolic fuzzy predicates providing the classification of facial images according to the underlying emotional states. For this classification we use rules extracted from psychological studies and expression databases including extreme expressions such as those illustrated in Ekman's database. The rules are then refined in realistic conditions, taking into account the extracted features. The experimental results, based both in extreme and naturalistic databases developed in the frameworks of IST ERMIS and NoE HUMAINE, illustrate the capability of the developed system to analyse and recognise facial expressions in human computer interaction applications.	en
heal.journalName	IEEE International Conference on Neural Networks - Conference Proceedings	en
dc.identifier.doi	10.1109/IJCNN.2004.1379962	en
dc.identifier.volume	1	en
dc.identifier.spage	513	en
dc.identifier.epage	518	en