Automatic emotional expression analysis from lip shapes using artificial neural networks

dc.contributor.authorAkkoç, Betül
dc.contributor.authorÜlker, Erkan
dc.contributor.authorArslan, Ahmet
dc.date.accessioned2020-03-26T18:44:34Z
dc.date.available2020-03-26T18:44:34Z
dc.date.issued2013
dc.departmentSelçuk Üniversitesien_US
dc.description2013 21st Signal Processing and Communications Applications Conference, SIU 2013 -- 24 April 2013 through 26 April 2013 -- Haspolat -- 98109en_US
dc.description.abstractIn this study, emotional expressions are automatically analyzed from lip form using artificial neural network. Firstly facial region and then mouth area were found for expressions analysis. After these steps, lip shape was found and the parameters that are used for the analysis were automatically obtained. Artificial neural network trained using these parameters. This network was used for expression analysis. Success rate of 86% is achieved for the seven classes mentioned (happiness, sadness, surprise, disgust, anger, fear and disdain) whereas a success rate of 97% is found when three classes (happiness, sadness and surprised) are used. © 2013 IEEE.en_US
dc.identifier.doi10.1109/SIU.2013.6531213en_US
dc.identifier.isbn9.78147E+12
dc.identifier.scopusqualityN/Aen_US
dc.identifier.urihttps://dx.doi.org/10.1109/SIU.2013.6531213
dc.identifier.urihttps://hdl.handle.net/20.500.12395/30017
dc.indekslendigikaynakScopusen_US
dc.language.isotren_US
dc.relation.ispartof2013 21st Signal Processing and Communications Applications Conference, SIU 2013en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.selcuk20240510_oaigen_US
dc.subjectArtificial neural networksen_US
dc.subjectEmotional expression analysisen_US
dc.subjectImage processingen_US
dc.titleAutomatic emotional expression analysis from lip shapes using artificial neural networksen_US
dc.title.alternativeYapay sinir ağlarıyla dudak şekillerinden otomatik duygusal ifade analizi
dc.typeConference Objecten_US

Dosyalar