Abstract
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.
Original language | English |
---|---|
Article number | 1995 |
Journal | Applied Sciences (Switzerland) |
Volume | 10 |
Issue number | 6 |
DOIs | |
Publication status | Published - 2020 Mar 1 |
Bibliographical note
Funding Information:This research was supported by a National Research Foundation (NRF) grant funded by the MSIP of Korea (number 2019R1A2C2009480).
Publisher Copyright:
© 2020 by the authors. Licensee MDPI, Basel, Switzerland.
Keywords
- Database augmentation
- Facial image
- GAN (Generative adversarial networks)
- Generation
- Generative models
- Synthesis
ASJC Scopus subject areas
- General Materials Science
- Instrumentation
- General Engineering
- Process Chemistry and Technology
- Computer Science Applications
- Fluid Flow and Transfer Processes