GAN Generated Images for Facial Expression Recognition systems

Citation Author(s):
Simone
Porcu
DIEE, University of Cagliari, Italy
Alessandro
Floris
DIEE, University of Cagliari, Italy
Luigi
Atzori
DIEE, University of Cagliari, Italy
Submitted by:
Alessandro Floris
Last updated:
Fri, 03/29/2024 - 11:24
DOI:
10.21227/b7m1-rz14
Data Format:
Image files (.png)
Links:
Article related to this dataset
License:
Creative Commons Attribution
2081 Views
Categories:
Artificial Intelligence
Machine Learning
Image Processing
Keywords:
generative adversarial networks, Facial Expression Recognition, synthetic image database, data augmentation
0
0 ratings - Please login to submit your rating.
ACCESS DATASET CITE SHARE/EMBED

Abstract 

Most of Facial Expression Recognition (FER) systems rely on machine learning approaches that require large databases (DBs) for an effective training. As these are not easily available, a good solution is to augment the DBs with appropriate techniques, which are typically based on either geometric transformation or deep learning based technologies (e.g., Generative Adversarial Networks (GANs)). Whereas the first category of techniques have been fairly adopted in the past, studies that use GAN-based techniques are limited for FER systems. To advance in this respect, we evaluate the impact of the GAN techniques by creating a new DB containing the generated synthetic images. The face images contained in the KDEF DB are used as the base to create novel synthetic images using the facial features of 2 images selected from the YouTube-Faces DB. 

The published article is available here:

https://www.mdpi.com/2079-9292/9/11/1892

 

 

Instructions: 

The face images contained in the KDEF DB are used as the base to create novel synthetic images using the facial features of 2 images (i.e., Candie Kung and Cristina Saralegui) selected from the YouTube-Faces DB. The novel images differ between each other, in particular with respect to the eyes, the nose, and the mouth, whose characteristics are taken from the Candie and Cristina images.

The total number of novel synthetic images generated with the GAN is 980 (70 individuals from KDEF DB x 7 emotions x 2 subjects from YouTube-Faces DB).

The zip file "GAN_KDEF_Candie" contains the 490 images generated by combining the KDEF images with the Candie Kung image. The zip file "GAN_KDEF_Cristina" contains the 490 images generated by combining the KDEF images with the Cristina Saralegui image. The used image IDs are the same used for the KDEF DB. The synthetic generated images have a resolution of 562x762 pixels.

 

If you make use of this dataset, please consider citing the following publication:

Porcu, S., Floris, A., & Atzori, L. (2020). Evaluation of Data Augmentation Techniques for Facial Expression Recognition Systems. Electronics, 9, 1892.

BibTex format:

@article{porcu2020evaluation, title={Evaluation of Data Augmentation Techniques for Facial Expression Recognition Systems}, author={Porcu, Simone and Floris, Alessandro and Atzori, Luigi}, journal={Electronics}, volume={9}, pages={108781}, year={2020}, number = {11}, article-number = {1892}, publisher={MDPI}, doi={10.3390/electronics9111892} }

 

Dataset Files

LOGIN TO ACCESS DATASET FILES

 

QUESTIONS?