Multi-image Blending Holographic Encryption System Based on Multi-Source Coherent Diffraction and Frequency-Domain Attention Learning

The multi-image encryption method has the advantage of large information encryption capacity, which is conducive to the development of high-throughput cryptosystems. However, for multi-image encryption, the low PSNR caused by the crosstalk between images restricts the development of multi-image encryption methods. In our method, a novel optical multi-image encryption method based on multi-image coherent diffraction and frequency-domain attention learning is proposed. For encrypting, random aberrations brought about by diffraction are used instead of random phase masks to encrypt multiple source images into a single holographic ciphertext image based on holography and coherent diffraction imaging. A specially designed deep learning decryption network based on physical prior is proposed, which is used to resolve the source images of each channel respectively. Highlights and advantages include lower computational cost algorithm, higher real-time performance and better decryption quality. The feasibility, noise immunity, security and robustness of the proposed method are investigated through simulations and experiments. It is believed that the method we propose here can promote the further development of multi-optical image encryption systems.