Computational ghost imaging with deep compressed sensing*

被引:14
|
作者
Zhang, Hao [1 ]
Xia, Yunjie [1 ,2 ]
Duan, Deyang [1 ,2 ]
机构
[1] Qufu Normal Univ, Sch Phys & Phys Engn, Qufu 273165, Shandong, Peoples R China
[2] Qufu Normal Univ, Res Inst Laser, Shandong Prov Key Lab Laser Polarizat & Informat, Qufu 273165, Shandong, Peoples R China
基金
中国国家自然科学基金;
关键词
computational ghost imaging; compressed sensing; deep convolution generative adversarial network;
D O I
10.1088/1674-1056/ac0042
中图分类号
O4 [物理学];
学科分类号
0702 ;
摘要
Computational ghost imaging (CGI) provides an elegant framework for indirect imaging, but its application has been restricted by low imaging performance. Herein, we propose a novel approach that significantly improves the imaging performance of CGI. In this scheme, we optimize the conventional CGI data processing algorithm by using a novel compressed sensing (CS) algorithm based on a deep convolution generative adversarial network (DCGAN). CS is used to process the data output by a conventional CGI device. The processed data are trained by a DCGAN to reconstruct the image. Qualitative and quantitative results show that this method significantly improves the quality of reconstructed images by jointly training a generator and the optimization process for reconstruction via meta-learning. Moreover, the background noise can be eliminated well by this method.
引用
收藏
页数:4
相关论文
共 50 条
  • [1] Computational ghost imaging with deep compressed sensing
    张浩
    夏云杰
    段德洋
    [J]. Chinese Physics B, 2021, (12) : 445 - 448
  • [2] Computational ghost imaging with compressed sensing based on a convolutional neural network
    张浩
    段德洋
    [J]. Chinese Optics Letters, 2021, 19 (10) : 19 - 22
  • [3] Computational ghost imaging with compressed sensing based on a convolutional neural network
    Zhang, Hao
    Duan, Deyang
    [J]. CHINESE OPTICS LETTERS, 2021, 19 (10)
  • [4] Compressive sensing computational ghost imaging
    Katkovnik, Vladimir
    Astola, Jaakko
    [J]. JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 2012, 29 (08) : 1556 - 1567
  • [5] Computational ghost imaging for remote sensing
    Erkmen, Baris I.
    [J]. JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 2012, 29 (05) : 782 - 789
  • [6] Computational ghost imaging using deep learning
    Shimobaba, Tomoyoshi
    Endo, Yutaka
    Nishitsuji, Takashi
    Takahashi, Takayuki
    Nagahama, Yuki
    Hasegawa, Satoki
    Sano, Marie
    Hirayama, Ryuji
    Kakue, Takashi
    Shiraki, Atsushi
    Ito, Tomoyoshi
    [J]. OPTICS COMMUNICATIONS, 2018, 413 : 147 - 151
  • [7] Hadamard Ghost Imaging Based on Compressed Sensing Reconstruction Algorithm
    Li Chang
    Gao Chao
    Shao Jiaqi
    Wang Xiaoqian
    Yao Zhihai
    [J]. LASER & OPTOELECTRONICS PROGRESS, 2021, 58 (10)
  • [8] Compressed-Sensing-based Gradient Reconstruction for Ghost Imaging
    Rong Zhu
    Guangshun Li
    Ying Guo
    [J]. International Journal of Theoretical Physics, 2019, 58 : 1215 - 1226
  • [9] Super-resolution filtered ghost imaging with compressed sensing*
    Meng, Shao-Ying
    Shi, Wei-Wei
    Ji, Jie
    Tao, Jun-Jie
    Fu, Qian
    Chen, Xi-Hao
    Wu, Ling-An
    [J]. CHINESE PHYSICS B, 2020, 29 (12)
  • [10] Super-resolution ghost imaging via compressed sensing
    Li Long-Zhen
    Yao Xu-Ri
    Liu Xue-Feng
    Yu Wen-Kai
    Zhai Guang-Jie
    [J]. ACTA PHYSICA SINICA, 2014, 63 (22)