Computational ghost imaging with deep compressed sensing

doi:10.1088/1674-1056/ac0042

中国物理B ›› 2021, Vol. 30 ›› Issue (12): 124209-124209.doi: 10.1088/1674-1056/ac0042

Computational ghost imaging with deep compressed sensing

Hao Zhang(张浩)¹, Yunjie Xia(夏云杰)^1,2,†, and Deyang Duan(段德洋)^1,2,‡

1 School of Physics and Physical Engineering, Qufu Normal University, Qufu 273165, China;
2 Shandong Provincial Key Laboratory of Laser Polarization and Information Technology, Research Institute of Laser, Qufu Normal University, Qufu 273165, China

收稿日期:2021-03-22 修回日期:2021-04-22 接受日期:2021-05-12 出版日期:2021-11-15 发布日期:2021-11-30
通讯作者: Yunjie Xia, Deyang Duan E-mail:yjxia@qfnu.edu.cn;duandy2015@qfnu.edu.cn
基金资助:
Project supported by the National Natural Science Foundation of China (Grant Nos. 11704221, 11574178, and 61675115) and the Taishan Scholar Project of Shandong Province, China (Grant No. tsqn201812059).

Computational ghost imaging with deep compressed sensing

Hao Zhang(张浩)¹, Yunjie Xia(夏云杰)^1,2,†, and Deyang Duan(段德洋)^1,2,‡

1 School of Physics and Physical Engineering, Qufu Normal University, Qufu 273165, China;
2 Shandong Provincial Key Laboratory of Laser Polarization and Information Technology, Research Institute of Laser, Qufu Normal University, Qufu 273165, China

Received:2021-03-22 Revised:2021-04-22 Accepted:2021-05-12 Online:2021-11-15 Published:2021-11-30
Contact: Yunjie Xia, Deyang Duan E-mail:yjxia@qfnu.edu.cn;duandy2015@qfnu.edu.cn
Supported by:
Project supported by the National Natural Science Foundation of China (Grant Nos. 11704221, 11574178, and 61675115) and the Taishan Scholar Project of Shandong Province, China (Grant No. tsqn201812059).

摘要/Abstract

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.

关键词: computational ghost imaging, compressed sensing, deep convolution generative adversarial network

Abstract: 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.

Key words: computational ghost imaging, compressed sensing, deep convolution generative adversarial network

中图分类号: (Image forming and processing)

42.30.Va

42.50.-p (Quantum optics)

Hao Zhang(张浩), Yunjie Xia(夏云杰), and Deyang Duan(段德洋). Computational ghost imaging with deep compressed sensing[J]. 中国物理B, 2021, 30(12): 124209-124209.

Hao Zhang(张浩), Yunjie Xia(夏云杰), and Deyang Duan(段德洋). Computational ghost imaging with deep compressed sensing[J]. Chin. Phys. B, 2021, 30(12): 124209-124209.

参考文献

[1] Pittman T B, Shih Y H, Strekalov D V and Sergienko A V 1995 Phys. Rev. A 52 R3429
[2] Shapiro J H and Boyd R W 2012 Quantum Inf. Process. 11 949
[3] Erkmen B I and Shapiro J H 2010 Adv. Opt. Photon. 2 405
[4] Meyers R E, Deacon K S and Shih Y 2011 App. Phys. Lett. 98 111115
[5] Li M F, Yan L, Yang R, Kou J and Liu S 2019 Acta Phys. Sin. 68 094204
[6] Pelliccia D, Rack A, Scheel M, Cantelli V and Paganin D M 2016 Phys. Rev. Lett. 117 113902
[7] Yu H, Lu R, Han S, Xie H, Du G, Xiao T and Zhu D 2016 Phys. Rev. Lett. 117 113901
[8] Zhang A X, He Y, Wu L A, Chen L and Wang B 2018 Optica 5 374
[9] Duan D Y, Zhang L and Xia Y J 2014 J. Opt. Soc. Am A 31 730
[10] Duan D Y and Xia Y J 2021 Opt. Express 29 4978
[11] Shapiro J H 2008 Phys. Rev. A 78 061802
[12] Wang C, Lan R J, Ren C and Cao D Z 2020 Phys. Rev A 101 033819
[13] Gong W L, Zhao C Q, Yu H, Chen M L, Xu W D and Han S S 2016 Sci. Rep. 6 26133
[14] Zhao C Q, Gong W L, Chen M L, Li E R, Wang H, Xu W D and Han S S 2012 Appl. Phys. Lett. 101 141123
[15] Erkmen B I 2012 J. Opt. Soc. A 29 782
[16] Duan D Y, Man Z X and Xia Y J 2019 Opt. Express 27 25187
[17] Katza O, Bromberg Y and Silberberg Y 2009 Appl. Phys. Lett. 95 131110
[18] Katkovnik V and Astola J 2012 J. Opt. Soc. Am. A 29 1556
[19] Yu W K, Li M F, Yao X R, Liu X F, Wu L A and Zhai G J 2014 Opt. Express 22 7133
[20] Chen Z, Shi J and Zeng G 2016 Appl. Opt. 55 8644
[21] Lyu M, Wang W, Wang H, Wang W, Li G, Chen N and Situ G H 2017 Sci. Rep. 7 17865
[22] He Y, Wang G, Dong G, Zhu S, Chen H, Zhang A and Xu Z 2018 Sci. Rep. 8 6469
[23] Shimobaba T, Endo Y, Nishitsuji T, Takahashi T, Nagahama Y, Hasegawa T, Sano M, Hirayama R, Kakue T, Shiraki A and Ito T 2018 Opt. Commun. 413 147
[24] Barbastathis G, Ozcan A and Situ G 2019 Optica 6 921
[25] Wu Y, Rosca M and Lillicrap T 2019 arXiv:1905.06723v2
[26] Bromberg Y, Katz O and Silberberg Y 2009 Phys. Rev. A 79 053840
[27] Jiang W J, Li X Y, Peng X L and Sun B Q 2020 Opt. Express 28 7889
[28] Huang X J 2020 Electron. Commer. R. A 4 21

Computational ghost imaging with deep compressed sensing

Computational ghost imaging with deep compressed sensing

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

Metrics

本文评价

推荐阅读 0

[1]	Shao-Ying Meng(孟少英), Mei-Yi Chen(陈美伊), Jie Ji(季杰), Wei-Wei Shi(史伟伟), Qiang Fu(付强), Qian-Qian Bao(鲍倩倩), Xi-Hao Chen(陈希浩), and Ling-An Wu(吴令安). Iterative filtered ghost imaging[J]. 中国物理B, 2022, 31(2): 28702-028702.
[2]	Yi-Yi Huang(黄祎祎), Chen Ou-Yang(欧阳琛), Ke Fang(方可), Yu-Feng Dong(董玉峰), Jie Zhang(张杰), Li-Ming Chen(陈黎明), and Ling-An Wu(吴令安). High speed ghost imaging based on a heuristic algorithm and deep learning[J]. 中国物理B, 2021, 30(6): 64202-064202.
[3]	郭媛, 陈炜, 敬世伟. An image compressed sensing algorithm based on adaptive nonlinear network[J]. 中国物理B, 2020, 29(5): 54203-054203.
[4]	王乐, 赵生妹. Compressed ghost imaging based on differential speckle patterns[J]. 中国物理B, 2020, 29(2): 24204-024204.
[5]	高超, 王晓茜, 蔡宏吉, 任捷, 刘籍元, 姚治海. Influence of random phase modulation on the imaging quality of computational ghost imaging[J]. 中国物理B, 2019, 28(2): 20201-020201.
[6]	张玉东, 赵生妹. Optical encryption scheme based on ghost imaging with disordered speckles[J]. 中国物理B, 2017, 26(5): 54205-054205.
[7]	曹蓓, 罗秀娟, 张羽, 刘辉, 陈明徕. Compressed sensing sparse reconstruction for coherent field imaging[J]. 中国物理B, 2016, 25(4): 40701-040701.