Single-pixel compressive optical image hiding based on conditional generative adversarial network.

We present a deep learning (DL) framework based on a conditional generative adversarial network (CGAN) to perform compressive optical image hiding (COIH) with a single-pixel detector. An end-to-end compressive sensing generative adversarial network (eCSGAN) is developed, achieving the approximate equivalent model of an inverse system of a nonlinear COIH model, to reconstruct two-dimensional secret images directly from real acquired one-dimensional compressive sampling signals without the need of any security keys of the COIH system such as the sequence of illumination patterns, the host image, etc. Moreover, detailed comparisons between the image reconstructed using eCSGAN and compressive sensing (CS) shows that the proposed method can remarkably increase the quality in image reconstruction with a lower sampling rate. The feasibility and security of the proposed method are demonstrated by the numerical simulations and optical experiment results.

[1]  Shuming Jiao,et al.  Does deep learning always outperform simple linear regression in optical imaging? , 2020, Optics express.

[2]  Yunfei Zhou,et al.  Optical image hiding based on dual-channel simultaneous phase-shifting interferometry and compressive sensing , 2016 .

[3]  Wenqi He,et al.  Cryptanalysis of random-phase-encoding-based optical cryptosystem via deep learning. , 2019, Optics express.

[4]  Dawei Zhang,et al.  Optical image compression and encryption transmission-based ondeep learning and ghost imaging , 2020 .

[5]  Qing Liu,et al.  Digital image encryption and watermarking by phase-shifting interferometry. , 2004, Applied optics.

[6]  Xia Li,et al.  Review on Optical Image Hiding and Watermarking Techniques , 2018, Optics & Laser Technology.

[7]  Jun Li,et al.  A one-time pad encryption method combining full-phase image encryption and hiding , 2017 .

[8]  Fei Wang,et al.  Learning from simulation: An end-to-end deep-learning approach for computational ghost imaging. , 2019, Optics express.

[9]  Wen Chen,et al.  Machine-learning attacks on interference-based optical encryption: experimental demonstration. , 2019, Optics express.

[10]  L. Deng,et al.  The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web] , 2012, IEEE Signal Processing Magazine.

[11]  C. Brosseau,et al.  Optical image encryption method based on incoherent imaging and polarized light encoding , 2018 .

[12]  Françoise Peyrin,et al.  Deep neural networks for single-pixel compressive video reconstruction , 2020 .

[13]  Yi Qin,et al.  Learning-based chosen-plaintext attack on diffractive-imaging-based encryption scheme , 2020 .

[14]  Bahram Javidi,et al.  Advances in optical security systems , 2014 .

[15]  Shumeet Baluja,et al.  Hiding Images within Images , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Yibo Zhang,et al.  Phase recovery and holographic image reconstruction using deep learning in neural networks , 2017, Light: Science & Applications.

[17]  B Javidi,et al.  Optical image encryption based on input plane and Fourier plane random encoding. , 1995, Optics letters.

[18]  Markus G. Kuhn,et al.  Information hiding-a survey , 1999, Proc. IEEE.

[19]  Shuai Li,et al.  Lensless computational imaging through deep learning , 2017, ArXiv.

[20]  Guohai Situ,et al.  Deep-learning-based ghost imaging , 2017, Scientific Reports.

[21]  Jun Li,et al.  Compressive Optical Image Encryption , 2015, Scientific Reports.

[22]  Zhilong Jiang,et al.  Single-shot optical multiple-image encryption by jointly using wavelength multiplexing and position multiplexing. , 2020, Applied optics.

[23]  Siu-Ming Yiu,et al.  Multi-key privacy-preserving deep learning in cloud computing , 2017, Future Gener. Comput. Syst..

[24]  Rong Li,et al.  Optical image hiding with a modified Mach–Zehnder interferometer , 2014 .

[25]  Guohai Situ,et al.  eHoloNet: a learning-based end-to-end approach for in-line digital holographic reconstruction. , 2018, Optics express.

[26]  Qun Hao,et al.  Improving Imaging Quality of Real-time Fourier Single-pixel Imaging via Deep Learning , 2019, Sensors.

[27]  T. Ferguson.  An Inconsistent Maximum Likelihood Estimate , 1982 .