Data Augmentation and Transfer Learning Approaches Applied to Facial Expressions Recognition
This work addresses the challenge of small datasets in facial expression recognition, an incremental improvement for applications in human-computer interaction and emotion analysis.
The paper tackled the problem of limited training data for facial expression recognition by proposing a novel data augmentation technique using geometrical transformations and GAN-generated synthetic images, which improved model performance to an average accuracy of 85% with the InceptionResNetV2 model.
The face expression is the first thing we pay attention to when we want to understand a person's state of mind. Thus, the ability to recognize facial expressions in an automatic way is a very interesting research field. In this paper, because the small size of available training datasets, we propose a novel data augmentation technique that improves the performances in the recognition task. We apply geometrical transformations and build from scratch GAN models able to generate new synthetic images for each emotion type. Thus, on the augmented datasets we fine tune pretrained convolutional neural networks with different architectures. To measure the generalization ability of the models, we apply extra-database protocol approach, namely we train models on the augmented versions of training dataset and test them on two different databases. The combination of these techniques allows to reach average accuracy values of the order of 85\% for the InceptionResNetV2 model.