Utilize este identificador para referenciar este registo: http://hdl.handle.net/1822/53047

TítuloReal-time emotions recognition system
Autor(es)Silva, Vinicius Corrêa Alves
Soares, Filomena
Esteves, João Sena
Figueiredo, Joana Sofia Campos
Leão, Celina Pinto
Santos, Cristina
Pereira, Ana Paula da Silva
Palavras-chaveEmotions Recognition
Intel RealSense
SVM classifier
Data2016
EditoraIEEE
RevistaInternational Conference on Ultra Modern Telecommunications and Control Systems & Workshops
Resumo(s)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.
TipoconferencePaper
URIhttp://hdl.handle.net/1822/53047
ISBN978-1-4673-8817-7
DOI10.1109/ICUMT.2016.7765357
ISSN2157-0221
Arbitragem científicayes
AcessoclosedAccess
Aparece nas coleções:CIEd - Textos em volumes de atas de encontros científicos nacionais e internacionais
CAlg - Artigos em livros de atas/Papers in proceedings

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
p201-silva.pdf1,08 MBAdobe PDFVer/Abrir  Solicitar cópia ao autor!

Partilhe no FacebookPartilhe no TwitterPartilhe no DeliciousPartilhe no LinkedInPartilhe no DiggAdicionar ao Google BookmarksPartilhe no MySpacePartilhe no Orkut
Exporte no formato BibTex mendeley Exporte no formato Endnote Adicione ao seu Currículo DeGóis