Unsupervised Generation and Synthesis of Facial Images via an Auto-Encoder-Based Deep Generative Adversarial Network
School of Electrical Engineering, Korea University, Seoul 136-701, Korea
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(6), 1995; https://doi.org/10.3390/app10061995
Received: 26 December 2019 / Revised: 5 March 2020 / Accepted: 11 March 2020 / Published: 14 March 2020
(This article belongs to the Special Issue Intelligent Processing on Image and Optical Information)
The processing of facial images is an important task, because it is required for a large number of real-world applications. As deep-learning models evolve, they require a huge number of images for training. In reality, however, the number of images available is limited. Generative adversarial networks (GANs) have thus been utilized for database augmentation, but they suffer from unstable training, low visual quality, and a lack of diversity. In this paper, we propose an auto-encoder-based GAN with an enhanced network structure and training scheme for Database (DB) augmentation and image synthesis. Our generator and decoder are divided into two separate modules that each take input vectors for low-level and high-level features; these input vectors affect all layers within the generator and decoder. The effectiveness of the proposed method is demonstrated by comparing it with baseline methods. In addition, we introduce a new scheme that can combine two existing images without the need for extra networks based on the auto-encoder structure of the discriminator in our model. We add a novel double-constraint loss to make the encoded latent vectors equal to the input vectors.
View Full-Text
Keywords:
generative models; GAN (Generative adversarial networks); facial image; generation; database augmentation; synthesis
▼
Show Figures
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited
MDPI and ACS Style
Kwak, J.g.; Ko, H. Unsupervised Generation and Synthesis of Facial Images via an Auto-Encoder-Based Deep Generative Adversarial Network. Appl. Sci. 2020, 10, 1995.
AMA Style
Kwak Jg, Ko H. Unsupervised Generation and Synthesis of Facial Images via an Auto-Encoder-Based Deep Generative Adversarial Network. Applied Sciences. 2020; 10(6):1995.
Chicago/Turabian StyleKwak, Jeong g.; Ko, Hanseok. 2020. "Unsupervised Generation and Synthesis of Facial Images via an Auto-Encoder-Based Deep Generative Adversarial Network" Appl. Sci. 10, no. 6: 1995.
Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.
Search more from Scilit