Next Article in Journal
Detection of Self-Healing Discharge in Metallized Film Capacitors Using an Ultrasonic Method
Previous Article in Journal
Distributed Genetic Algorithms for Low-Power, Low-Cost and Small-Sized Memory Devices
Article

Evaluation of Data Augmentation Techniques for Facial Expression Recognition Systems

1
Department of Electrical and Electronic Engineering, University of Cagliari, 09123 Cagliari, Italy
2
CNIT, University of Cagliari, 09123 Cagliari, Italy
*
Author to whom correspondence should be addressed.
Electronics 2020, 9(11), 1892; https://doi.org/10.3390/electronics9111892
Received: 16 October 2020 / Revised: 5 November 2020 / Accepted: 9 November 2020 / Published: 11 November 2020
(This article belongs to the Section Computer Science & Engineering)
Most Facial Expression Recognition (FER) systems rely on machine learning approaches that require large databases for an effective training. As these are not easily available, a good solution is to augment the databases with appropriate data augmentation (DA) techniques, which are typically based on either geometric transformation or oversampling augmentations (e.g., generative adversarial networks (GANs)). However, it is not always easy to understand which DA technique may be more convenient for FER systems because most state-of-the-art experiments use different settings which makes the impact of DA techniques not comparable. To advance in this respect, in this paper, we evaluate and compare the impact of using well-established DA techniques on the emotion recognition accuracy of a FER system based on the well-known VGG16 convolutional neural network (CNN). In particular, we consider both geometric transformations and GAN to increase the amount of training images. We performed cross-database evaluations: training with the "augmented" KDEF database and testing with two different databases (CK+ and ExpW). The best results were obtained combining horizontal reflection, translation and GAN, bringing an accuracy increase of approximately 30%. This outperforms alternative approaches, except for the one technique that could however rely on a quite bigger database. View Full-Text
Keywords: facial expression recognition; machine learning; generative adversarial network; data augmentation; convolutional neural network; synthetic image database facial expression recognition; machine learning; generative adversarial network; data augmentation; convolutional neural network; synthetic image database
Show Figures

Figure 1

MDPI and ACS Style

Porcu, S.; Floris, A.; Atzori, L. Evaluation of Data Augmentation Techniques for Facial Expression Recognition Systems. Electronics 2020, 9, 1892. https://doi.org/10.3390/electronics9111892

AMA Style

Porcu S, Floris A, Atzori L. Evaluation of Data Augmentation Techniques for Facial Expression Recognition Systems. Electronics. 2020; 9(11):1892. https://doi.org/10.3390/electronics9111892

Chicago/Turabian Style

Porcu, Simone, Alessandro Floris, and Luigi Atzori. 2020. "Evaluation of Data Augmentation Techniques for Facial Expression Recognition Systems" Electronics 9, no. 11: 1892. https://doi.org/10.3390/electronics9111892

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop