Method of training image decomposition model, method of decomposing image, electronic device, and storage medium

Patent metadata

Field	Value
Publication number	US-12561872-B2
Application number	US-202318225060-A
Country	US
Kind code	B2
Filing date	Jul 21, 2023
Priority date	Jul 22, 2022
Publication date	Feb 24, 2026
Grant date	Feb 24, 2026

Abstract

A method of training an image decomposition model, a method of decomposing an image, an electronic device, and a storage medium are provided. The method of training the image decomposition model includes: acquiring a training set; inputting first and second training images into first and second adversarial neural networks respectively, so as to determine a first loss function value; inputting a third training image into the first and second adversarial neural networks respectively, so as to determine a second loss function value; determining a third loss function value according to a comparison result between an acquired fusion image and the third training image, where the fusion image is generated by fusing generated images of the first and second adversarial neural networks, and adjusting a parameter of the image decomposition model according to at least one of the first to third loss function values.

First claim

What is claimed is:

1 . A method of training an image decomposition model, wherein the image decomposition model comprises a first adversarial neural network and a second adversarial neural network, the first adversarial neural network comprises a first generation network and a first discrimination network, and the second adversarial neural network comprises a second generation network and a second discrimination network;
the training method comprising: acquiring a training set, wherein the training set comprises a first training image, a second training image and a third training image, and the third training image is generated by fusing the first training image with the second training image; inputting the first training image into the first adversarial neural network and inputting the second training image into the second adversarial neural network, so as to determine a first loss function value of the first adversarial neural network and a first loss function value of the second adversarial neural network respectively; inputting the third training image into the first adversarial neural network and the second adversarial neural network respectively, so as to determine a second loss function value of the first adversarial neural network and a second loss function value of the second adversarial neural network respectively; determining a third loss function value according to a comparison result between an acquired fusion image and the third training image, wherein the fusion image is generated by fusing a generated image of the first adversarial neural network with a generated image of the second adversarial neural network; and adjusting a parameter of the image decomposition model by means of back propagation according to at least one of the first loss function value, the second loss function value, or the third loss function value, until a predetermined training end condition is met, wherein the first loss function value is calculated based on a first loss function, the second loss function value is calculated based on a second loss function, and the third loss function value is calculated based on a third loss function; and wherein the first loss function, the second loss function and the third loss function meet a predetermined weight relationship.

2 . The method according to claim 1 , wherein the inputting the first training image into the first adversarial neural network to determine a first loss function value of the first adversarial neural network comprises:
inputting the first training image into the first generation network of the first adversarial neural network to obtain a first generated image; inputting the first training image and the first generated image into the first discrimination network of the first adversarial neural network to obtain a first image recognition result; and determining the first loss function value of the first adversarial neural network according to the first image recognition result.

3 . The method according to claim 1 , wherein the inputting the second training image into the second adversarial neural network to determine a first loss function value of the second adversarial neural network comprises:
inputting the second training image into the second generation network of the second adversarial neural network to obtain a second generated image; inputting the second training image and the second generated image into the second discrimination network of the second adversarial neural network to obtain a second image recognition result; and determining the first loss function value of the second adversarial neural network according to the second image recognition result.

4 . The method according to claim 1 , wherein the inputting the third training image into the first adversarial neural network and the second adversarial neural network respectively to determine a second loss function value of the first adversarial neural network and a second loss function value of the second adversarial neural network respectively comprises:
inputting the third training image into the first generation network of the first adversarial neural network to obtain a third generated image; inputting the third generated image and the first training image associated with the third training image into the first discrimination network of the first adversarial neural network to obtain a third image recognition result; determining the second loss function value of the first adversarial neural network according to the third image recognition result; inputting the third training image into the second generation network of the second adversarial neural network to obtain a fourth generated image; inputting the fourth generated image and the second training image associated with the third training image into the second discrimination network of the second adversarial neural network to obtain a fourth image recognition result; and determining the second loss function value of the second adversarial neural network according to the fourth image recognition result.

5 . The method according to claim 4 , wherein the determining a third loss function value according to an acquired comparison result between an acquired fusion image and the third training image comprises:
fusing the third generated image with the fourth generated image according to an image fusion algorithm, so as to generate a fusion image; comparing the fusion image with the third training image to generate a comparison result; and determining the third loss function value according to the comparison result.

6 . The method according to claim 1 , wherein the second loss function comprises a generator loss function and a discriminator loss function; and
wherein the second loss function value comprises a generator loss function value and a discriminator loss function value.

7 . The method according to claim 6 , wherein the generator loss function in the second loss function has a predetermined weight greater than weights of other loss functions.

8 . The method according to claim 1 , wherein a training image in the training set is obtained by performing a negative logarithm processing on an X-ray image.

9 . The method according to claim 6 , wherein the adjusting a parameter of the image decomposition model by means of hack propagation according to the second loss function value comprises:
adjusting a parameter of the first generation network of the first adversarial neural network and a parameter of the second generation network of the second adversarial neural network according to the generator loss function value in the second loss function value; and adjusting a parameter of the first discrimination network or the first adversarial neural network and a parameter of the second discrimination network of the second adversarial neural network according to the discriminator loss function value in the second loss function value.

10 . A method of decomposing an image, applicable to a decomposition of an X-ray image, comprising:
performing a negative logarithmic transformation on an acquired X-ray image to generate an image to be decomposed; processing the image to be decomposed by a first generation network in an image decomposition model, so as to generate a first decomposed image; processing the image to be decomposed by a second generation network in the image decomposition model, so as to generate a second decomposed image; and performing a negative logarithmic inverse operation transformation on the first decomposed image and the second decomposed image to generate an image decomposition result; wherein the image decomposition model comprises a first adversarial neural network and a second adversari

Assignees

• Nuctech Co Ltd

Inventors

• Zhang Li
• Sun Yunda
• Hu Zheng
• Fu Gang
• Li Qiang

Classifications

• G06T2207/20221

  Image fusion; Image merging · CPC title

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T2207/20081

  Training; Learning · CPC title

• G06T5/50

  using two or more images, e.g. averaging or subtraction · CPC title

• G01V5/22

  Active interrogation, i.e. by irradiating objects or goods using external radiation sources, e.g. using gamma rays or cosmic rays · CPC title