Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/53047
Registo completo
Campo DC | Valor | Idioma |
---|---|---|
dc.contributor.author | Silva, Vinicius Corrêa Alves | por |
dc.contributor.author | Soares, Filomena | por |
dc.contributor.author | Esteves, João Sena | por |
dc.contributor.author | Figueiredo, Joana Sofia Campos | por |
dc.contributor.author | Leão, Celina Pinto | por |
dc.contributor.author | Santos, Cristina | por |
dc.contributor.author | Pereira, Ana Paula da Silva | por |
dc.date.accessioned | 2018-03-21T11:26:26Z | - |
dc.date.issued | 2016 | - |
dc.identifier.isbn | 978-1-4673-8817-7 | - |
dc.identifier.issn | 2157-0221 | por |
dc.identifier.uri | https://hdl.handle.net/1822/53047 | - |
dc.description.abstract | This paper presents the experimental setup and methodology for a real-time emotions recognition system, based on the recent Intel RealSense 3D sensor, to identify six emotions: happiness, sadness, anger, surprise, fear, and neutral. The process includes the database construction, with 43 participants, based on facial features extraction and a multiclass Support Vector Machine classifier. The system was first tested offline using Linear kernel and Radial Basis Function (RBF) kernel. In the offline evaluation, the system performance was quantified in terms of confusion matrix, accuracy, sensitivity, specificity, Area Under the Curve, and Mathews Correlation Coefficient metrics. The RBF kernel achieved the best performance, with an average accuracy of 93.6%. Then, the real-time system was evaluated in a laboratorial setup, achieving an overall accuracy of 88%. The time required for the system to perform facial expression recognition efficiently is 1-3ms. The results, obtained by simulation and experimentally, point out that the present system can recognize facial expressions accurately. | por |
dc.description.sponsorship | - Research supported by COMPETE: POCI-01-0145-FEDER-007043 and FCT - Fundacao para a Ciencia e Tecnologia within the Project Scope: UID/CEC/00319/2013. | por |
dc.language.iso | eng | por |
dc.publisher | IEEE | por |
dc.relation | POCI-01-0145-FEDER-007043 | por |
dc.relation | info:eu-repo/grantAgreement/FCT/5876/147280/PT | por |
dc.rights | closedAccess | por |
dc.subject | Emotions Recognition | por |
dc.subject | Intel RealSense | por |
dc.subject | SVM classifier | por |
dc.title | Real-time emotions recognition system | por |
dc.type | conferencePaper | por |
dc.peerreviewed | yes | por |
oaire.citationStartPage | 201 | por |
oaire.citationEndPage | 206 | por |
oaire.citationVolume | 2016-December | por |
dc.date.updated | 2018-03-21T01:54:50Z | - |
dc.identifier.doi | 10.1109/ICUMT.2016.7765357 | por |
dc.description.publicationversion | info:eu-repo/semantics/publishedVersion | por |
dc.subject.wos | Science & Technology | - |
sdum.export.identifier | 4607 | - |
sdum.journal | International Conference on Ultra Modern Telecommunications and Control Systems & Workshops | por |
sdum.conferencePublication | 8th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT) | por |
Aparece nas coleções: | CIEd - Textos em volumes de atas de encontros científicos nacionais e internacionais |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
p201-silva.pdf Acesso restrito! | 1,08 MB | Adobe PDF | Ver/Abrir |