Super-resolution reconstruction algorithm for terahertz imaging below diffraction limit  

作　　者：王莹 祁峰 张子旭 汪晋宽 Ying Wang;Feng Qi;Zi-Xu Zhang;Jin-Kuan Wang(School of Communication Science and Engineering,Northeastern University,Shenyang 110819,China;Key Laboratory of Opto-Electronic Information Processing,Chinese Academy of Sciences,Shenyang 110016,China;Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,China;Institutes for Robotics and Intelligent Manufacturing,Chinese Academy of Sciences,Shenyang 110169,China;University of Chinese Academy of Sciences,Beijing 100049,China;University of Technology Sydney,NSW 2007,Australia)

机构地区：[1]School of Communication Science and Engineering,Northeastern University,Shenyang 110819,China [2]Key Laboratory of Opto-Electronic Information Processing,Chinese Academy of Sciences,Shenyang 110016,China [3]Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,China [4]Institutes for Robotics and Intelligent Manufacturing,Chinese Academy of Sciences,Shenyang 110169,China [5]University of Chinese Academy of Sciences,Beijing 100049,China [6]University of Technology Sydney,NSW 2007,Australia

出　　处：《Chinese Physics B》2023年第3期608-612,共5页中国物理B（英文版）

基　　金："XingLiaoYingCai"Talents of Liaoning Province,China(Grant No.XLYC2007074);Shenyang Young and Middle-aged Science and Technology Innovation Talent Support Program(Grant No.RC200512);Project supported by“XingLiaoYingCai"Talents of Liaoning Province,China(Grant No.XLYC2007074);Shenyang Young and Middle-aged Science and Technology Innovation Talent Support Program(Grant No.RC200512),。

摘　　要：Terahertz(THz)imaging has drawn significant attention because THz wave has a unique capability to transient,ultrawide spectrum and low photon energy.However,the low resolution has always been a problem due to its long wavelength,limiting their application of fields practical use.In this paper,we proposed a complex one-shot super-resolution(COSSR)framework based on a complex convolution neural network to restore superior THz images at 0.35 times wavelength by extracting features directly from a reference measured sample and groundtruth without the measured PSF.Compared with real convolution neural network-based approaches and complex zero-shot super-resolution(CZSSR),COSSR delivers at least 6.67,0.003,and 6.96%superior higher imaging efficacy in terms of peak signal to noise ratio(PSNR),mean square error(MSE),and structural similarity index measure(SSIM),respectively,for the analyzed data.Additionally,the proposed method is experimentally demonstrated to have a good generalization and to perform well on measured data.The COSSR provides a new pathway for THz imaging super-resolution(SR)reconstruction below the diffraction limit.

关 键 词：TERAHERTZ image processing complex convolution neural network 

分 类 号：O441.4[理学—电磁学] TP391.41[理学—物理]