Deep-learning-based optical image hiding

TL;DR

This paper introduces a deep learning framework for optical image hiding that enables high-quality image reconstruction from interferograms, improving practicality and robustness against noise and phase shifts.

Contribution

It presents a novel end-to-end deep learning approach using GANs for optical image hiding, eliminating the need for optical inverse diffraction parameters.

Findings

High-quality image reconstruction from interferograms.

Robustness against phase shifts deviation and noise.

Feasibility demonstrated through optical experiments.

Abstract

A novel framework of optical image hiding based on deep learning (DL) is proposed in this paper, and hidden information can be reconstructed from an interferogram by using an end to end network with high-quality. By using the prior data between the hidden image and the object image, a generative adversarial network was trained so that it can learn the hiding model, which resulting in only an interferogram needs to be transmitted and recorded to reconstruct image. Moreover, reconstruction process can be obtained without the parameters in optical inverse diffraction and the reconstruction result will not be affected by the phase shifts deviation and noise, which is convenient for practical application. The feasibility and security of the proposed method are demonstrated by the optical experiment results.