Name: MARCUS VINÍCIUS ZAVARÊZ
Type: MSc dissertation
Publication date: 01/10/2018
Advisor:
Name |
Role |
|---|---|
| THIAGO OLIVEIRA DOS SANTOS | Advisor * |
Examining board:
| Name |
Role |
|---|---|
| ALBERTO FERREIRA DE SOUZA | Internal Examiner * |
| THIAGO OLIVEIRA DOS SANTOS | Advisor * |
Summary: "Facial expression recognition is a very important research field to understand human emotions. Many facial expression recognition systems have been proposed in the literature over the years. Some of these methods use neural network approaches with deep architectures to address the problem, since these networks have been increasingly used to learn discriminatory representations of faces.
Although it seems that the facial expression recognition problem has been solved, there is a large difference between the results achieved from laboratory-controlled to in-the-wild conditions and using the same database to train and test the network and the cross-database protocol.
In this work, we extensively investigate the performance influence of fine-tuning with cross-database approach and the use of Generative Adversarial Networks in facial expression recognition problem. In order to perform the study, the VGG-Face Deep Convolutional Network model (pre-trained for face recognition) was fine-tuned to recognize facial expressions considering different well-established databases in the literature: CK+, JAFFE, MMI, RaFD, KDEF, BU3DFE, and AR Face. The cross-database experiments were organized so that one of the databases was separated as test set and the others as training, and each experiment was ran multiple times to ensure the results.
% Moreover the generative adversarial network was used to generate more images to compose the study, using the same databases as used by classification network.
Our results show a significant improvement on the use of pre-trained models against randomly initialized Convolutional Neural Networks on the facial expression recognition problem, for example achieving 88.58\%, 67.03\%, 85.97\%, and 72.55\% average accuracy testing in the CK+, MMI, RaFD, and KDEF, respectively. Additionally, in absolute terms, the results show an improvement in the literature for cross-database facial expression recognition with the use of pre-trained models."
