Face Image Generation and Enhancement Using Conditional Generative Adversarial Network
Ainil Mardiah(1*), Sri Hartati(2), Agus Sihabuddin(3)
(1) Master Program in Computer Science, FMIPA UGM, Yogyakarta
(2) Department of Computer Science and Electronics, FMIPA UGM, Yogyakarta
(3) Department of Computer Science and Electronics, FMIPA UGM, Yogyakarta
(*) Corresponding Author
Abstract
The accuracy and speed of a single image super-resolution using a convolutional neural network is often a problem in improving finer texture details when using large enhancement factors. Some recent studies have focused on minimal mean square error, resulting in a high peak signal to noise ratio. Generally, although the peak signal to noise ratio has a high value, the output image is less detailed. This shows that the determination of super-resolution is not optimal. Conditional Generative Adversarial Network based on Boundary Equilibrium Generative Adversarial Network, by combining Mean Square Error Loss and GAN Loss as a loss function to optimize the super-resolution model and produce super-resolution images. Also, the generator network is designed with skip connection architecture to increase convergence speed and strengthen feature distribution.
Image quality value parameters used in this study are Peak Signal to Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The results showed the highest image quality values using dataset validation were 26.55 for PSNR values and 0.93 for SSIM values. The highest image quality values using the testing dataset are 24.56 for the PSNR value and 0.91 for the SSIM value.
Keywords
Full Text:
PDFReferences
E. Denton, A. Szlam, and R. Fergus, “Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks arXiv : 1506 . 05751v1 [ cs . CV ] 18 Jun 2015,” pp. 1–10, 2015.
I. Goodfellow, “NIPS 2016 Tutorial: Generative Adversarial Networks,” 2016, doi: 10.1001/jamainternmed.2016.8245.
C. Ledig et al., “Photo-realistic single image super-resolution using a generative adversarial network,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 105–114, 2017, doi: 10.1109/CVPR.2017.19.
J. Jiang, C. Chen, J. Ma, Z. Wang, Z. Wang, and R. Hu, “SRLSP: A Face Image Super-Resolution Algorithm Using Smooth Regression with Local Structure Prior,” IEEE Trans. Multimed., vol. 19, no. 1, pp. 27–40, 2017, doi: 10.1109/TMM.2016.2601020.
I. Goodfellow, J. Pouget-Abadie, and M. Mirza, “Generative Adversarial Networks,” arXiv Prepr. arXiv …, pp. 1–9, 2014, doi: 10.1017/CBO9781139058452.
S. Osindero, “Conditional Generative Adversarial Nets,” pp. 1–7, 2014.
P. Isola and A. A. Efros, “Image-to-Image Translation with Conditional Adversarial Networks,” 2017, doi: 10.1109/CVPR.2017.632.
D. Berthelot, T. Schumm, and L. Metz, “BEGAN: Boundary Equilibrium Generative Adversarial Networks,” pp. 1–10, 2017, doi: 1703.10717.
M. M. and Y. L. Junbo Zhao, “ENERGY-BASED GAN,” Neural Networks, vol. 61, no. 2014, pp. 32–48, 2015, doi: 10.1016/j.neunet.2014.10.001.
T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford, and X. Chen, “Improved Techniques for Training GANs,” pp. 1–10, 2016, doi: arXiv:1504.01391.
M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein GAN,” 2017, [Online]. Available: http://arxiv.org/abs/1701.07875.
B. Huang, W. Chen, X. Wu, and C. Lin, “High-quality face image generated with conditional boundary equilibrium generative adversarial networks,” Pattern Recognit. Lett., vol. 111, pp. 72–79, 2018, doi: 10.1016/j.patrec.2018.04.028.
W. Shi et al., “Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network,” pp. 1–10, 2016.
A. Radford, L. Metz, and S. Chintala, “UNSUPERVISED REPRESENTATION LEARNING WITH DEEP CONVOLUTIONAL,” pp. 1–16, 2016.
DOI: https://doi.org/10.22146/ijccs.58327
Article Metrics
Abstract views : 2630 | views : 2319Refbacks
- There are currently no refbacks.
Copyright (c) 2022 IJCCS (Indonesian Journal of Computing and Cybernetics Systems)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
View My Stats1