Abstract
The feed-forward architectures of recently proposed generative adversarial network can learn the non-linear mapping from low-resolution output to high-resolution output. However, this approach does not fully address the mutual dependencies of different resolution images. By analyzing the zero-sum game, the paper proposes an image enhancement algorithm by using conditional generative adversarial networks based on improved non-saturating game. Firstly, the enhancement image obtained by the GAN model is adopted as a condition against the network object image, making the original image learning the network structure of the object image with dim-small. Our proposed generative adversarial networks can obtain a clearer image through improved non-saturating game, and it can still get a large gradient and sufficient learning, which makes up for the deficiencies in the mini-maximum game. In addition, the loss function of the network adds the loss of discriminator to guide discriminator to generate high quality images. We compared the proposed method (SRG) with other methods including SC, SRCNN, VESPCN and ESPCN, and the proposed method resulted in obvious improvements in the peak signal-to-noise ratio (PSNR) by 2.348 dB and in structural similarity index measurement (SSIM) by 1.89% to enhance the visual effects of nature images.






Similar content being viewed by others
References
Caballero J, Ledig C, Aitken A, et al (2017) Real-Time Video Super-Resolution with Spatio-Temporal Networks and Motion Compensation[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE Computer Society, p 172-181
Chong F, Chaoyun W, Grand L et al (2017) Projections onto convex sets super-resolution reconstruction based on point spread function estimation of low-resolution remote sensing images[J]. Sensors 17(2):362
Chong F, Xushuai C, Lei Z et al (2017) Improved Wallis dodging algorithm for large-scale super-resolution reconstruction remote sensing images[J]. Sensors 17(3):623
Creswell A, White T, Dumoulin V et al (2017) Generative adversarial networks: an overview[J]. IEEE Signal Process Mag 35(1):53–65
Culley S, Albrecht D, Jacobs C et al (2018) Quantitative mapping and minimization of super-resolution optical imaging artifacts[J]. Nat Methods, 15(4):263–266
Culley S, Albrecht D, Jacobs C et al (2018) NanoJ-SQUIRREL: quantitative mapping and minimisation of super-resolution optical imaging artefacts[J]. Nat Methods 15(4):263–266
Darren P, Rasim L, Jon P et al (2018) Landsat super-resolution enhancement using convolution neural networks and Sentinel-2 for training[J]. Remote Sens 10(3):394
Elad M, Datsenko D (2008) Example-based regularization deployed to super-resolution reconstruction of a single image[J]. Comput J 52(1):15–30
Graf BL, Rojo LE, Delatorre-Herrera J (2017) ChromoTrace reconstruction of 3D chromosome configurations by super-resolution microscopy[J]. Food Chem 131(2):387–396
Huang DT, Huang WQ, Gu PT et al (2017) Image super-resolution reconstruction based on regularization technique and guided filter[J]. Infrared Phys Technol 83:103–113
Huang B, Chen W, Wu X et al (2018) High-quality face image generated with conditional boundary equilibrium generative adversarial networks[J]. Pattern Recogn Lett 111:72–79
Jinsheng X, Enyu L, Li Z et al (2017) Improved image super-resolution algorithm based on convolutional neural network[J]. Acta Opt Sin 32(7):872–890
Ledig C, Theis L, Huszar F, et al (2016) Photo-realistic single image super-resolution using a generative adversarial network[J]. computer vision and pattern recognition 105–114
Ledig C, Theis L, Huszar F, et al (2017) Photo-realistic single image super-resolution using a generative adversarial network[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE
Lei J, Li L, Yue H et al (2017) Depth map super-resolution considering view synthesis quality[J]. IEEE Trans Image Process 26(4):1732–1745
Li D, Wang Z (2017) Face video super-resolution with identity guided generative adversarial networks[C]// Ccf Chinese Conference on Computer Vision. Springer, Singapore
Lucas A, Tapia SL, Molina R, et al (2018) Generative adversarial networks and perceptual losses for video super-resolution[J]. international conference on image processing 2018:51–55
Mahapatra D, Bozorgtabar B (2017) Retinal vasculature segmentation using local saliency maps and generative adversarial networks for image super resolution[J]
Mahapatra D, Bozorgtabar B, Hewavitharanage S, et al (2017) Image super resolution using generative adversarial networks and local saliency maps for retinal image analysis[C]// International Conference on Medical Image Computing & Computer-assisted Intervention. Springer, Cham
Okanovic M, Hillig B, Breuer F et al (2018) Time-of-flight MR-angiography with a helical trajectory and slice-super-resolution reconstruction[J]. Magn Reson Med
Sanchez I, Vilaplana V (2018) Brain MRI super-resolution using 3D generative adversarial networks[J]. Computer Vision and Pattern Recognition 2018:1–8
Shi W, Caballero J, Huszár, F, et al (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[J]. 12(2):722-739
Shi Y, Li Q, Zhu XX (2018) Building footprint generation using improved generative adversarial networks[J]. IEEE Geosci Remote Sens Lett
Wang X, Yu K, Wu S, et al (2018) ESRGAN: enhanced super-resolution generative adversarial networks[J]. european conference on computer vision 2018:63–79
Ying C, Zhao P, Li Y (2018) Low-light-level image super-resolution reconstruction based on iterative projection photon localization algorithm[J]. J Electron Imaging 27(1):1
Yisheng L, Yuanyuan C, Li L, et al (2018) Generative adversarial networks for parallel transportation systems[J]. IEEE Intell Transp Syst Mag 1-1
Yuan Y, Liu S, Zhang J, et al (2018) Unsupervised image super-resolution using cycle-in-cycle generative adversarial networks[J]. computer vision and pattern recognition 701–710.
Zhang D, He J (2017) Hybrid sparse-representation-based approach to image super-resolution reconstruction[J]. J Electron Imaging 26(2):023008
Zhang DX, Lu L, Li CH et al (2014) Super-resolution image reconstruction algorithm based on sub-pixel shift[J]. Acta Automat Sin 40(12):2851–2861
Zhang D, Shao J, Hu G, et al (2017) Sharp and real image super-resolution using generative adversarial network[C]// International Conference on Neural Information Processing 217–226
Zhang M, Hu X, Zhao L et al (2017) Translation-aware semantic segmentation via conditional Least Square generative adversarial networks[J]. J Appl Remote Sens (4):11
Zhao L, Bai H, Liang J, et al (2017) Simultaneously color-depth super-resolution with conditional generative adversarial network[J]. Pattern Recogn 356–369
Acknowledgments
This work was financially supported by the Natural Science Foundation of Zhejiang Province, China (No. LGF18F020015).
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xu, C., Cui, Y., Zhang, Y. et al. Image enhancement algorithm based on generative adversarial network in combination of improved game adversarial loss mechanism. Multimed Tools Appl 79, 9435–9450 (2020). https://doi.org/10.1007/s11042-019-07776-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-019-07776-x