%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2017/09.04.14.38
%2 sid.inpe.br/sibgrapi/2017/09.04.14.38.55
%T Reconhecimento de expressões faciais aplicada à análise de vídeos com reações espontâneas usando SVM com resposta probabilística
%D 2017
%A Paixão, Wdnei Ribeiro da,
%A Pereira, Flávio Garcia,
%A Komati, Karin Satie,
%@affiliation Instituto Federal do Espirito Santo - Campus Serra
%@affiliation Instituto Federal do Espirito Santo - Campus Serra
%@affiliation Instituto Federal do Espirito Santo - Campus Serra
%E Torchelsen, Rafael Piccin,
%E Nascimento, Erickson Rangel do,
%E Panozzo, Daniele,
%E Liu, Zicheng,
%E Farias, Mylène,
%E Viera, Thales,
%E Sacht, Leonardo,
%E Ferreira, Nivan,
%E Comba, João Luiz Dihl,
%E Hirata, Nina,
%E Schiavon Porto, Marcelo,
%E Vital, Creto,
%E Pagot, Christian Azambuja,
%E Petronetto, Fabiano,
%E Clua, Esteban,
%E Cardeal, Flávio,
%B Conference on Graphics, Patterns and Images, 30 (SIBGRAPI)
%C Niterói, RJ, Brazil
%8 17-20 Oct. 2017
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K reconhecimento de expressões faciais, reações espontâneas, análise de vídeos, machine learning, HoG, SVM.
%X This work defines an initial proposal of a system for automated facial emotion classification applied to video that contains recordings of spontaneous reactions of spectators. The proposed approach uses a variation of the classifier Support Vector Machines (SVM) with outputs in a posteriori probability value and the Histogram of Oriented Gradients (HoG) as a feature descriptor. For the training, the Radboud Face Database (RaFD) was used. The results presented show the viability of the use in the mass media to assess the mood of the audience in quantitative terms of probability with respect to time.
%@language pt
%3 7_wip.pdf