BCGAN: Facial Expression Synthesis by Bottleneck-Layered Conditional Generative Adversarial Networks
- Resource Type
- Conference
- Authors
- Shin, Yeji; Bum, Junghyun; Son, Chang-Hwan; Choo, Hyunseung
- Source
- 2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM) Ubiquitous Information Management and Communication (IMCOM), 2021 15th International Conference on. :1-4 Jan, 2021
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Robotics and Control Systems
Signal Processing and Analysis
Training
Human computer interaction
Face recognition
Generative adversarial networks
Information management
Task analysis
Image reconstruction
Facial expression synthesis
generative adversarial networks
densely connected convolutional networks
- Language
Facial expression synthesis is widely applied to emotion prediction and face recognition for human-computer interaction. This task is challenging because it is difficult to reconstruct realistic and accurate facial expressions. Early deep learning methods focus only on pixel-level manipulation and are not suitable for generating realistic facial expressions. In this paper, we propose a bottleneck-layered conditional generative adversarial networks (BCGAN) for more realistic and accurate facial expression synthesis. BCGAN adopts a bottleneck layer that uses channel-wise concatenation in the generator to train with meaningful features only. In addition, a dense connection that links all bottleneck layers is added to generate an image which preserves the facial details of the original image. Both quantitative and qualitative evaluations were performed using the Radboud Faces Database (RaFD). Experimental results showed that BCGAN had 2% higher classification accuracy (98.7%) on the generated images as well as faster training speed compared to state-of-the-art approach.