Open AccessEmotion Recognition using AutoEncoders and Convolutional Neural Networks
Author(s) -
Luis Antonio Beltrán Prieto,
Zuzana Komínková Oplatková
Publication year - 2018
Publication title -
mendel ... (brno. on-line)/mendel ...
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.221
H-Index - 13
eISSN - 1803-3822
pISSN - 1803-3814
DOI - 10.13164/mendel.2018.1.113
Subject(s) - autoencoder , convolutional neural network , computer science , artificial intelligence , deep learning , facial expression , emotion recognition , pattern recognition (psychology) , emotion classification , speech recognition , machine learning
Emotions demonstrate people's reactions to certain stimuli. Facial expression analysis is often used to identify the emotion expressed. Machine learning algorithms combined with artificial intelligence techniques have been developed in order to detect expressions found in multimedia elements, including videos and pictures. Advanced methods to achieve this include the usage of Deep Learning algorithms. The aim of this paper is to analyze the performance of a Convolutional Neural Network which uses AutoEncoder Units for emotion-recognition in human faces. The combination of two Deep Learning techniques boosts the performance of the classification system. 8000 facial expressions from the Radboud Faces Database were used during this research for both training and testing. The outcome showed that five of the eight analyzed emotions presented higher accuracy rates, higher than 90%.