A compression perceptual image reconstruction method based on Generative Adversarial Networks based on generation antagonism network

Abstract

The invention discloses a compression perceptual image reconstruction method based on Generative Adversarial Networks. The method comprises the following steps: S1, according to a measurement vector obtained by original image sampling and a reconstruction image size, constructing a generation antagonism network model based on a neural network, and designing an objective function for optimizing thegeneration antagonism network model parameters; S2, presetting parameters when training the generated antagonistic network model; 3, alternately training a generator and a discriminator by adopting aback propagation algorithm accord to that objective function; 4, if that Generative Adversarial Network model converges, the train network can directly realize the compression sensing task, and the model output is the corresponding original image reconstructed by the measurement vector; Otherwise, return to Step S2-S4. The invention utilizes the powerful mapping ability of the generator to initially reconstruct the original image, and utilizes the confrontation training of the generator and the discriminator to make the pixel distribution of the image reconstructed by the generator closer tothe original image, thus achieving the purpose of accurately reconstructing the original image under the low sampling rate.

Description

technical field [0001] The present invention relates to the technical field of image information processing, in particular to a compressive sensing image reconstruction method and system based on generative confrontation networks. Background technique [0002] Compressed sensing (Compressed Sensing, CS) is a novel signal acquisition theory, which combines the traditional sampling and compression process, and can directly obtain measurement data much lower than the Nyquist sampling rate, which can reduce sampling costs, reduce storage resources, and compress The encoder side of the perceptual model only needs to perform linear random measurements, while the complex optimization process of reconstructing the signal is done at the decoder side. [0003] These imaging systems use iterative optimization algorithms to reconstruct images from a small number of observed measurements based on compressed sensing theory. However, these reconstruction algorithms require complex iterati...

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: In order to overcome the deficiencies of the prior art, the present invention provides a compressive sensing image reconstruction method based on generative confrontation network, which can solve the problems of long reconstruction time and poor reconstructed image quality. The present invention also provides A Compressed Sensing Image Reconstruction System Based on Generative Adversarial Networks

Images