Deep learning for universal emotion recognition in still images

This work propose a methodology for still image facial expression. The proposed method contains a face detection and alignment module followed by a deep convolutional neural network (CNN) that outputs a seven emotions probability vector.

Detalles Bibliográficos
Autor: Rosa Ramos, Juan Luis
Tipo de recurso: tesis de maestría
Fecha de publicación:2018
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/119073
Acceso en línea:https://hdl.handle.net/2117/119073
Access Level:acceso abierto
Palabra clave:Neural networks (Computer science)
Machine learning
Human face recognition (Computer science)
facial expression recognition
convolutional neural networks
overfitting
face analysis dataset
Xarxes neuronals (Informàtica)
Aprenentatge automàtic
Reconeixement facial (Informàtica)
Àrees temàtiques de la UPC::Informàtica
Descripción
Sumario:This work propose a methodology for still image facial expression. The proposed method contains a face detection and alignment module followed by a deep convolutional neural network (CNN) that outputs a seven emotions probability vector.