Super-resolution reconstruction algorithm for terahertz imaging below diffraction limit

被引:1
作者
Wang, Ying [1 ,2 ,3 ,4 ,5 ]
Qi, Feng [2 ,3 ,4 ,5 ,6 ]
Zhang, Zi-Xu [7 ]
Wang, Jin-Kuan [1 ]
机构
[1] Northeastern Univ, Sch Commun Sci & Engn, Shenyang 110819, Peoples R China
[2] Chinese Acad Sci, Key Lab Optoelect Informat Proc, Shenyang 110016, Peoples R China
[3] Chinese Acad Sci, Shenyang Inst Automat, Shenyang 110016, Peoples R China
[4] Chinese Acad Sci, Inst Robot, Shenyang 110169, Peoples R China
[5] Chinese Acad Sci, Inst Intelligent Mfg, Shenyang 110169, Peoples R China
[6] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
[7] Univ Technol Sydney, Sydney, NSW 2007, Australia
关键词
terahertz; image processing; complex convolution neural network;
D O I
10.1088/1674-1056/aca9c7
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Terahertz (THz) imaging has drawn significant attention because THz wave has a unique capability to transient, ultra-wide 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.
引用
收藏
页数:5
相关论文
共 24 条
[1]   Quality control and authentication of packaged integrated circuits using enhanced-spatial-resolution terahertz time-domain spectroscopy and imaging [J].
Ahi, Kiarash ;
Shahbazmohamadi, Sina ;
Asadizanjani, Navid .
OPTICS AND LASERS IN ENGINEERING, 2018, 104 :274-284
[2]   Mathematical Modeling of THz Point Spread Function and Simulation of THz Imaging Systems [J].
Ahi, Kiarash .
IEEE TRANSACTIONS ON TERAHERTZ SCIENCE AND TECHNOLOGY, 2017, 7 (06) :747-754
[3]   The Diagnosis of Human Liver Cancer by using THz Fiber-Scanning Near-Field Imaging [J].
Chen Hua ;
Ma Shi-Hua ;
Yan Wen-Xing ;
Wu Xiu-Mei ;
Wang Xiao-Zhou .
CHINESE PHYSICS LETTERS, 2013, 30 (03)
[4]   Image Super-Resolution Using Deep Convolutional Networks [J].
Dong, Chao ;
Loy, Chen Change ;
He, Kaiming ;
Tang, Xiaoou .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (02) :295-307
[5]   In vivo terahertz reflection imaging of human scars during and after the healing process [J].
Fan, Shuting ;
Ung, Benjamin S. Y. ;
Parrott, Edward P. J. ;
Wallace, Vincent P. ;
Pickwell-MacPherson, Emma .
JOURNAL OF BIOPHOTONICS, 2017, 10 (09) :1143-1151
[6]   Terahertz Radome Inspection [J].
Friederich, Fabian ;
May, Karl Henrik ;
Baccouche, Bessem ;
Matheis, Carsten ;
Bauer, Maris ;
Jonuscheit, Joachim ;
Moor, Michael ;
Denman, David ;
Bramble, Jamie ;
Savage, Nick .
PHOTONICS, 2018, 5 (01)
[7]  
Han Z., 2020, 2020 CROSS STRAIT RA, P1
[8]   Deep Back-ProjectiNetworks for Single Image Super-Resolution [J].
Haris, Muhammad ;
Shakhnarovich, Greg ;
Ukita, Norimichi .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (12) :4323-4337
[9]   Inception learning super-resolution [J].
Haris, Muhammad ;
Widyanto, M. Rahmat ;
Nobuhara, Hajime .
APPLIED OPTICS, 2017, 56 (22) :6043-6048
[10]   Perceptual Losses for Real-Time Style Transfer and Super-Resolution [J].
Johnson, Justin ;
Alahi, Alexandre ;
Li Fei-Fei .
COMPUTER VISION - ECCV 2016, PT II, 2016, 9906 :694-711