Fresnel hologram frequency domain gating filtering method based on deep learning

Abstract

The invention discloses a Fresnel hologram frequency domain gating filtering method based on deep learning, and the method comprises the steps: employing a spectrogram generated after the Fourier transform of an off-axis Fresnel digital hologram generated through simulation as a sample needed by network training; enabling the feature extraction network to realize extraction of main reconstruction information of the holographic image by learning a relation between zero level and positive and negative level of holographic spectrograms at different angles; finally, filtering the part containing the effective information, performing Fourier inversion to obtain an interference-free hologram, performing hologram reconstruction to obtain a hologram only containing a negative level, and performing compression quality evaluation on analog data. According to the method, the hologram without zero order and other interferences can be generated, the hologram compression rate is improved, and the problems that real-time reconstruction of the hologram is difficult, the reconstruction effect is poor and the compression rate is insufficient are solved. The method has a wide application prospect in the fields of holographic three-dimensional display, holographic projection, information security, digital microscopic holography, intelligent transportation, medical treatment and the like.

Description

technical field [0001] The invention relates to a Fresnel hologram frequency-domain gating filtering method based on deep learning, which is applicable to fields such as holographic three-dimensional display, holographic projection, information security, digital micro-holography, intelligent transportation, and medical treatment. Background technique [0002] With the development of optical technology and the advent of the information age, holography has been widely used in different fields such as real-time three-dimensional display, holographic projection, information security, and digital micro-holography due to its high precision and fast imaging speed. In recent years, digital holography has been widely used in three-dimensional display technology, resulting in an exponential growth in the amount of data. The huge amount of data and complex calculations make real-time transmission and processing very difficult. How to save the storage space of holograms and reduce the t...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problems of insufficient compression rate of holograms, complex compression algorithms, difficulties in real-time transmission and storage, poor image reconstruction effect, and high requirements for the application of holograms in current true-color scenes, and propose a Fresnel based on deep learning. Frequency Domain Gating Filtering Method for Hologram

Images