Research on Cyclic Generation Countermeasure Network Based Super-resolution Image Reconstruction Algorithm

CAI Wenyu; ZHANG Meiyan; WU Yan; GUO Jiahao

doi:10.11999/JEIT201046

Volume 44 Issue 1

Jan. 2022

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2022 > 44(1): 178-186

CAI Wenyu, ZHANG Meiyan, WU Yan, GUO Jiahao. Research on Cyclic Generation Countermeasure Network Based Super-resolution Image Reconstruction Algorithm[J]. Journal of Electronics & Information Technology, 2022, 44(1): 178-186. doi: 10.11999/JEIT201046

Citation:

CAI Wenyu, ZHANG Meiyan, WU Yan, GUO Jiahao. Research on Cyclic Generation Countermeasure Network Based Super-resolution Image Reconstruction Algorithm[J]. Journal of Electronics & Information Technology, 2022, 44(1): 178-186. doi: 10.11999/JEIT201046

Citation:

PDF( 5013 KB)

Research on Cyclic Generation Countermeasure Network Based Super-resolution Image Reconstruction Algorithm

doi: 10.11999/JEIT201046

1.
College of Electronics and Information, Hangzhou Dianzi University, Hangzhou 310018, China
2.
College of Electrical Engineering, Zhejiang University of Water Resources and Electric Power, Hangzhou 310018, China

Funds: The National Natural Science Foundation of China (61801431), The Fundamental Research Funds for the Provincial Universities of Zhejiang (GK209907299001-001)

Received Date: 2020-12-14
Rev Recd Date: 2021-10-18

Available Online: 2021-11-15

Publish Date: 2022-01-10

Abstract

Abstract

In order to improve the effect of image super-resolution reconstruction, the attention mechanism is introduced into Multi-level Residual Attention Network (MRAN) as the improved reconstruction network of Cycle Generation Countermeasure Network (CycleGAN) in this paper. A super-resolution reconstruction model MRA-GAN based on CycleGAN is proposed. The designed reconstruction network in MRA-GAN model is responsible for mapping from Low Resolution (LR) image to High Resolution (HR) image and the designed degradation network is responsible for reconstructing HR image to LR image. The LR discriminator is used to identify the real LR image which is obtained through the degraded network. The HR discriminator is used to identify the real HR image which is reconstructed by the reconstructed network. Moreover, the original discriminator and loss function of CycleGAN is improved. Experimental results verify that MRA-GAN model can obtain better Peak Signal to Noise Ratio (PSNR) and Structural SIMilarity (SSIM) than the existing deep learning based super-resolution algorithms.
- Image Super resolution Reconstruction (SR),
- Multi-level attention mechanism,
- CycleGAN,
- Peak Signal to Noise Ratio(PSNR),
- Structural SIMilarity(SSIM)

FullText(HTML)

References(25)

References

[1]	陈嘉琪, 刘祥梅, 李宁, 等. 一种超分辨SAR图像水域分割算法及其应用[J]. 电子与信息学报, 2021, 43(3): 700–707. doi: 10.11999/JEIT200366 CHEN Jiaqi, LIU Xiangmei, LI Ning, et al. A high-precision water segmentation algorithm for SAR image and its application[J]. Journal of Electronics &Information Technology, 2021, 43(3): 700–707. doi: 10.11999/JEIT200366
[2]	TAO Huanjie and LU Xiaobo. Contour-based smoky vehicle detection from surveillance video for alarm systems[J]. Signal, Image and Video Processing, 2019, 13(2): 217–225. doi: 10.1007/s11760-018-1348-z
[3]	王钢, 周若飞, 邹昳琨. 基于压缩感知理论的图像优化技术[J]. 电子与信息学报, 2020, 42(1): 222–233. doi: 10.11999/JEIT190669 WANG Gang, ZHOU Ruofei, and ZOU Yikun. Research on image optimization technology based on compressed sensing[J]. Journal of Electronics &Information Technology, 2020, 42(1): 222–233. doi: 10.11999/JEIT190669
[4]	陈书贞, 曹世鹏, 崔美玥, 等. 基于深度多级小波变换的图像盲去模糊算法[J]. 电子与信息学报, 2021, 43(1): 154–161. doi: 10.11999/JEIT190947 CHEN Shuzhen, CAO Shipeng, CUI Meiyue, et al. Image blind deblurring algorithm based on deep multi-level wavelet transform[J]. Journal of Electronics &Information Technology, 2021, 43(1): 154–161. doi: 10.11999/JEIT190947
[5]	YANG Chenxue, YE Mao, TANG Song, et al. Semi-supervised low-rank representation for image classification[J]. Signal, Image and Video Processing, 2017, 11(1): 73–80. doi: 10.1007/s11760-016-0895-4
[6]	DING Chunhui, BAO Tianlong, KARMOSHI S, et al. Single sample per person face recognition with KPCANet and a weighted voting scheme[J]. Signal, Image and Video Processing, 2017, 11(7): 1213–1220. doi: 10.1007/s11760-017-1077-8
[7]	ZHANG Kai, ZUO Wangmeng, and ZHANG Lei. Learning a single convolutional super-resolution network for multiple degradations[C]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 3262–3271.
[8]	HE Chao, CHEN Zhenxue, and LIU Chengyun. Salient object detection via images frequency domain analyzing[J]. Signal, Image and Video Processing, 2016, 10(7): 1295–1302. doi: 10.1007/s11760-016-0954-x
[9]	HOU H and ANDREWS H. Cubic splines for image interpolation and digital filtering[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1978, 26(6): 508–517. doi: 10.1109/TASSP.1978.1163154
[10]	SCHULTZ R R and STEVENSON R L. A Bayesian approach to image expansion for improved definition[J]. IEEE Transactions on Image Processing, 1994, 3(3): 233–242. doi: 10.1109/83.287017
[11]	LI Xin and ORCHARD M T. New edge-directed interpolation[J]. IEEE Transactions on Image Processing, 2001, 10(10): 1521–1527. doi: 10.1109/83.951537
[12]	IRANI M and PELEG S. Improving resolution by image registration[J]. CVGIP:Graphical Models and Image Processing, 1991, 53(3): 231–239. doi: 10.1016/1049-9652(91)90045-L
[13]	STARK H and OSKOUI P. High-resolution image recovery from image-plane arrays, using convex projections[J]. Journal of the Optical Society of America A, 1989, 6(11): 1715–1726. doi: 10.1364/JOSAA.6.001715
[14]	SCHULTZ R R and STEVENSON R L. Extraction of high-resolution frames from video sequences[J]. IEEE Transactions on Image Processing, 1996, 5(6): 996–1011. doi: 10.1109/83.503915
[15]	DONG Chao, LOY C C, HE Kaiming, et al. Learning a deep convolutional network for image super-resolution[C]. 13th European Conference on Computer Vision, Zurich, Switzerland, 2014: 184–199.
[16]	DONG Chao, LOY C C, and TANG Xiaoou. Accelerating the super-resolution convolutional neural network[C]. 14th European Conference on Computer Vision, Amsterdam, The Netherlands, 2016: 391–407.
[17]	KIM J, LEE J K, and LEE K M. Accurate image super-resolution using very deep convolutional networks[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 1646–1654.
[18]	SHI Wenzhe, CABALLERO J, HUSZÁR F, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 2016: 1874–1883. doi: 10.1109/CVPR.2016.207.
[19]	GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]. Proceedings of the 27th International Conference on Neural Information Processing Systems, Montreal, Canada, 2014: 2672–2680.
[20]	LEDIG C, THEIS L, HUSZÁR F, et al. Photo-realistic single image super-resolution using a generative adversarial network[C]. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 105–114.
[21]	LIM B, SON S, KIM H, et al. Enhanced deep residual networks for single image super-resolution[C]. IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, USA, 2017: 1132–1140.
[22]	ZHANG Yulun, LI Kunpeng, LI Kai, et al. Image super-resolution using very deep residual channel attention networks[C]. Proceedings of the 15th European Conference on Computer Vision (ECCV), Munich, Germany, 2018: 294–310.
[23]	SHOCHER A, COHEN N, and IRANI M. Zero-Shot super-resolution using deep internal learning[C]. 2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, 2018: 3118–3126.
[24]	HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 2016: 770–778.
[25]	RADFORD A, METZ L, and CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[EB/OL]. https://arxiv.org/pdf/1511.06434.pdf, 2016.