Army Academy of Armored Forces of Pla

Xinlei Liu

Xi Wang

Cheng Song

Tao Jing

Xingpeng Yan

Xiaoyu Jiang

Zhuo Chen

Junhui Liu

A method and system for optimizing first-diffraction-order reconstruction of holograms, a device, and a medium are provided. The method includes: acquiring a target image; determining a target image light field according to the target image; calculating a target diffraction field for the target image light field by performing backward propagation by a set distance; constructing a U-Net network model; and inputting the target diffraction field into a trained U-Net network model to acquire an optimized hologram. The trained U-Net network model is obtained by constructing a U-Net network model and training and optimizing the U-Net network model, thereby continuously improving the quality of the zero-diffraction-order reconstructed image of the initial hologram and finally achieving the effect of optimizing the first-diffraction-order reconstructed image of the hologram.

Method and system for optimizing first-diffraction-order reconstruction of holograms, device and medium

A method and system for generating a random graphic training dataset and a hologram is disclosed, which relates to the technical field of image processing. The method for generating a random graphic training dataset includes: randomly generating a plurality of graphic datasets, where each of the graphic datasets includes a square, a circle and an equilateral triangle; for any graphic dataset, performing gradual filling on each graphic in the graphic dataset to obtain a gradual graphic dataset; and performing translation transformation on each graphic in the gradual graphic dataset for a predetermined number of times to obtain random graphics corresponding to the graphic dataset, and determining random graphics corresponding to all graphic datasets as a random graphic training dataset. More comprehensive training data can be provided and a training effect of a model can be improved.

Method and system for generating random graphic training dataset and hologram

Growing community of inventors

Beijing, China

Xinlei Liu