A Super Resolution Algorithm Based on Attention Mechanism and SRGAN Network

doi:10.1109/ACCESS.2021.3100069

CQUET-IR

	A Super Resolution Algorithm Based on Attention Mechanism and SRGAN Network
	Liu, Baozhong 1; Chen, Ji 2
	2021
发表期刊	IEEE Access
ISSN	2169-3536
EISSN	2169-3536
卷号	9 页码:139138-139145
摘要	Image super-resolution reconstruction uses a specific algorithm to restore the low resolution blurred image in the same scene to a high resolution image. In recent years, with the vigorous development of deep learning, this technology has been widely used in many fields. In the field of image super-resolution reconstruction, more and more methods based on deep learning have been studied. According to the principle of GAN, a pseudo high-resolution image is generated by the generator, and then the discriminator calculates the difference between the image and the real high-resolution image to measure the authenticity of the image. Based on SRGAN (super resolution general adverse network), this paper mainly makes three improvements. First, it introduces the attention channel mechanism, that is, it adds Ca (channel attention) module to SRGAN network, and increases the network depth to better express high frequency features; Second, delete the original BN (batch normalization) layer to improve the network performance; Third, modify the loss function to reduce the impact of noise on the image. The experimental results show that the proposed method is superior to the current methods in both quantitative and qualitative indicators, and promotes the recovery of high-frequency detail information. The experimental results show that the proposed method improves the artifact problem and improves the PSNR (peak signal-to-noise ratio) on set5, set10 and bsd100 test sets.
关键词	Superresolution Feature extraction Convolution Image reconstruction Training Image coding Signal resolution Super resolution GAN network attention mechanism Deep learning Image enhancement Optical resolving power Signal to noise ratio Attention mechanisms High frequency HF High resolution image Image super resolution reconstruction Impact of noise PSNR (peak signal to noise ratio) Super resolution algorithms
DOI	10.1109/ACCESS.2021.3100069
收录类别	SCIE ; EI
语种	英语
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:000707439900001
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
EI入藏号	20213210750762
EI分类号	716.1 Information Theory and Signal Processing ; 741.1 Light/Optics
原始文献类型	Article ; Journal article (JA)
出版地	PISCATAWAY
引用统计	被引频次：18[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	https://ir.cqcet.edu.cn/handle/39TD4454/3717
专题	重庆电子科技职业大学
作者单位	1.Chongqing Coll Elect Engn, Chongqing 401331, Peoples R China; 2.Chongqing Inst Engn, Chongqing 400056, Peoples R China
推荐引用方式 GB/T 7714	Liu, Baozhong,Chen, Ji. A Super Resolution Algorithm Based on Attention Mechanism and SRGAN Network[J]. IEEE Access,2021,9:139138-139145.
APA	Liu, Baozhong,&Chen, Ji.(2021).A Super Resolution Algorithm Based on Attention Mechanism and SRGAN Network.IEEE Access,9,139138-139145.
MLA	Liu, Baozhong,et al."A Super Resolution Algorithm Based on Attention Mechanism and SRGAN Network".IEEE Access 9(2021):139138-139145.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Liu-2021-A Super Res（6527KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载