KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

An Edge Detection Technique for Performance Improvement of eGAN

eGAN 모델의 성능개선을 위한 에지 검출 기법

  • 이초연 (한국방송통신대학원 정보과학과) ;
  • 박지수 (전주대학교 컴퓨터공학과) ;
  • 손진곤 (한국방송통신대학원 컴퓨터과학과)
  • Received : 2020.12.23
  • Accepted : 2021.01.13
  • Published : 2021.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

GAN(Generative Adversarial Network) is an image generation model, which is composed of a generator network and a discriminator network, and generates an image similar to a real image. Since the image generated by the GAN should be similar to the actual image, a loss function is used to minimize the loss error of the generated image. However, there is a problem that the loss function of GAN degrades the quality of the image by making the learning to generate the image unstable. To solve this problem, this paper analyzes GAN-related studies and proposes an edge GAN(eGAN) using edge detection. As a result of the experiment, the eGAN model has improved performance over the existing GAN model.

GAN(Generative Adversarial Network, 생성적 적대 신경망)은 이미지 생성모델로서 생성기 네트워크와 판별기 네트워크로 구성되며 실제 같은 이미지를 생성한다. GAN에 의해 생성된 이미지는 실제 이미지와 유사해야 하므로 생성된 이미지와 실제 이미지의 손실 오차를 최소화하는 손실함수(loss function)를 사용한다. 그러나 GAN의 손실함수는 이미지를 생성하는 학습을 불안정하게 만들어 이미지의 품질을 떨어뜨린다는 문제점이 있다. 이러한 문제를 해결하기 위해 본 논문에서는 GAN 관련 연구를 분석하고 에지 검출(edge detection)을 이용한 eGAN(edge GAN)을 제안한다. 실험 결과 eGAN 모델이 기존의 GAN 모델보다 성능이 개선되었다.

Keywords

References

  1. Y. J. Choi, "Deep Learning Approach for Generating Photorealistic Facial Images," Department of Media Engineering, Sogang University Graduate School of Media Studies. Doctoral dissertation, 2017.
  2. I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozairy, A. Courville, and Y. Bengioz, "Generative Adversarial Nets," Advances in neural Information Processing Systems, pp.2672-2680, 2014.
  3. Y. J. Cao, L. L. Jia, Y. X. Chen, N. Lin, C. Yang, and B. Zhang, "Recent Advances of Generative Adversarial Networks in Computer Vision," IEEE Access, Vol.7, pp.14985-15006, 2018. https://doi.org/10.1109/access.2018.2886814
  4. M. Mirza and S. Osindero, "Conditional generative adversarial nets," https://arxiv.org/abs/1411.1784 2019.
  5. Patterson, J. Zhao, M. Mathieu, and Y. Lecun, "Energy-based generative adversarial network," https://arxiv.org/pdf/1609.03126, 2019.
  6. D. Berthelot, T. Schumm, and L. Metz, "BEGAN: Boundary Equilibrium Generative Adversarial Networks," arXiv: 1703.10717, 2019.
  7. J. Dong, R. Yin, X. Sun, Q. Li, Y. Yang, and X. Qin, "Inpainting of Remote Sensing SST Images With Deep Convolutional Generative Adversarial Network," IEEE Geoscience and Remote Sensing Letters, Vol.16, No.2, pp.173-177, 2019. https://doi.org/10.1109/lgrs.2018.2870880
  8. M. Arjovsky, S. Chintala, and L. Bottou. "Wasserstein GAN," https://arxiv.org/abs/1701.07875 2019
  9. I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. Courville, "Improved training of Wasserstein GANs," https://arxiv.org/pdf/1606.0349 2019.
  10. X. Mao, Q. Li, H. Xie, RYK. Lau, Z. Wang, and S. P. Smolley, "Least Squares Generative Adversarial Networks," The IEEE International Conference on Computer Vision (ICCV), pp.2794-2802, 2017.
  11. J. canny, "A Computational Approach to Edge Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.PAMI-8, Iss.6, pp.679-697, 1986. https://doi.org/10.1109/TPAMI.1986.4767851