Single-pixel compressive optical image hiding based on conditional generative adversarial network
Authors:
- Jiaosheng LiJLJiaosheng Li
- Yuhui LiYLYuhui Li
- Qinnan ZhangQZQinnan Zhang
- Jun LiJLJun Li
- 17 July 2020
- journal article
- research article
- Published by Optica Publishing Group in Optics Express
- Vol. 28 (15) , 22992-23002
Abstract
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.Keywords
Funding Information
- China Postdoctoral Science Foundation (2018M643114)
- National Natural Science Foundation of China (61805086)
This publication has 27 references indexed in Scilit:
- Multi-key privacy-preserving deep learning in cloud computingFuture Generation Computer Systems, 2017
- A one-time pad encryption method combining full-phase image encryption and hidingJournal of Optics, 2017
- Optical image hiding based on dual-channel simultaneous phase-shifting interferometry and compressive sensingApplied Physics B, 2016
- Compressive Optical Image EncryptionScientific Reports, 2015
- Advances in optical security systemsAdvances in Optics and Photonics, 2014
- Optical image hiding with a modified Mach–Zehnder interferometerOptics and Lasers in Engineering, 2013
- Digital image encryption and watermarking by phase-shifting interferometryApplied Optics, 2004
- Information hiding-a surveyProceedings of the IEEE, 1999
- Optical image encryption based on input plane and Fourier plane random encodingOptics Letters, 1995
- An Inconsistent Maximum Likelihood EstimateJournal of the American Statistical Association, 1982