Deep-learning-based optical scanning cryptography
Aimin Yan, XuSheng Zhuang, Lv Liu, Heming Tian · 2022
Optical scanning cryptography (OSC) is an optical image encryption method encrypting information incoherently based on two-pupil heterodyne scanning optical system. But numerical reconstruction of a 3-D volumetric image from an optical scanned hologram is a difficult task. The main problems are the intensive computational load, and the heavy blurring of each reconstructed section with the defocused noise from other sections.In this talk, we propose a deep-learning based reconstruction algorithm in optical scanning holography, which can generate reconstruction images in high quality. DNNs are created based on the U-net structure to learn the mapping between holograms and reconstruction images. Simulation and experimental results showed that the deep-learning based method is able to reconstruct the optical scanning hologram in real time for the removal of defocus noise.