Title :
Emotion classification using hidden layer outputs
Author :
Günler, Mine Altinay ; Tora, Hakan
Author_Institution :
EBIS, Data Commun. Dept., Vakiflar Bankasi T.A.O., Ankara, Turkey
Abstract :
Neural network (NN) with Multi-Layer Perceptron (MLP) is a supervised learning algorithm composed of artificial neurons. Multilayer NN is capable of solving nonlinear classification problems such as emotion identification by using facial expressions that is presented in this paper. Hidden layer outputs of NN provide useful information about facial appearance. This study addresses that without fully training NN hidden layer outputs can be used as feature. It is shown that an acceptable recognition rate is obtained by means of hidden layer outputs.
Keywords :
emotion recognition; face recognition; image classification; learning (artificial intelligence); multilayer perceptrons; MLP; artificial neurons; emotion classification; emotion identification; facial appearance; facial expressions; hidden layer outputs; multilayer NN; multilayer perceptron; neural network; nonlinear classification problems; supervised learning algorithm; Artificial neural networks; Databases; Face; Face recognition; Humans; Training; Multi layer neural network; facial expressions; image processing;
Conference_Titel :
Innovations in Intelligent Systems and Applications (INISTA), 2012 International Symposium on
Conference_Location :
Trabzon
Print_ISBN :
978-1-4673-1446-6
DOI :
10.1109/INISTA.2012.6247027
