Next Article in Journal
Ground State Representations of Some Non-Rational Conformal Nets
Next Article in Special Issue
Face Liveness Detection Using Thermal Face-CNN with External Knowledge
Previous Article in Journal
On Fitting Ideals of Kahler Differential Module
Previous Article in Special Issue
Accurate Age Estimation Using Multi-Task Siamese Network-Based Deep Metric Learning for Frontal Face Images
Article

Emotion Classification Using a Tensorflow Generative Adversarial Network Implementation

Department of Control Engineering and Industrial Informatics, University Politehnica of Bucharest, 060042 Bucharest, Romania
*
Author to whom correspondence should be addressed.
Symmetry 2018, 10(9), 414; https://doi.org/10.3390/sym10090414
Received: 11 July 2018 / Revised: 4 September 2018 / Accepted: 17 September 2018 / Published: 19 September 2018
(This article belongs to the Special Issue Deep Learning for Facial Informatics)
The detection of human emotions has applicability in various domains such as assisted living, health monitoring, domestic appliance control, crowd behavior tracking real time, and emotional security. The paper proposes a new system for emotion classification based on a generative adversarial network (GAN) classifier. The generative adversarial networks have been widely used for generating realistic images, but the classification capabilities have been vaguely exploited. One of the main advantages is that by using the generator, we can extend our testing dataset and add more variety to each of the seven emotion classes we try to identify. Thus, the novelty of our study consists in increasing the number of classes from N to 2N (in the learning phase) by considering real and fake emotions. Facial key points are obtained from real and generated facial images, and vectors connecting them with the facial center of gravity are used by the discriminator to classify the image as one of the 14 classes of interest (real and fake for seven emotions). As another contribution, real images from different emotional classes are used in the generation process unlike the classical GAN approach which generates images from simple noise arrays. By using the proposed method, our system can classify emotions in facial images regardless of gender, race, ethnicity, age and face rotation. An accuracy of 75.2% was obtained on 7000 real images (14,000, also considering the generated images) from multiple combined facial datasets. View Full-Text
Keywords: generative adversarial network; emotion classification; facial key point detection; facial images processing; convolutional neural networks generative adversarial network; emotion classification; facial key point detection; facial images processing; convolutional neural networks
Show Figures

Figure 1

MDPI and ACS Style

Caramihale, T.; Popescu, D.; Ichim, L. Emotion Classification Using a Tensorflow Generative Adversarial Network Implementation. Symmetry 2018, 10, 414. https://doi.org/10.3390/sym10090414

AMA Style

Caramihale T, Popescu D, Ichim L. Emotion Classification Using a Tensorflow Generative Adversarial Network Implementation. Symmetry. 2018; 10(9):414. https://doi.org/10.3390/sym10090414

Chicago/Turabian Style

Caramihale, Traian, Dan Popescu, and Loretta Ichim. 2018. "Emotion Classification Using a Tensorflow Generative Adversarial Network Implementation" Symmetry 10, no. 9: 414. https://doi.org/10.3390/sym10090414

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