The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
May. 27, 2025

Filed:

Jan. 18, 2025
Applicant:

Nanchang Hangkong University, Nanchang, CN;

Inventors:

Congxuan Zhang, Nanchang, CN;

Shijie Zhang, Nanchang, CN;

Leqi Jiang, Nanchang, CN;

Liyue Ge, Nanchang, CN;

Zige Wang, Nanchang, CN;

Zhen Chen, Nanchang, CN;

Chengzhong Wu, Nanchang, CN;

Yaonan Wang, Nanchang, CN;

Assignee:
Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06T 11/00 (2006.01); G06T 7/00 (2017.01); G06V 10/77 (2022.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 10/778 (2022.01); G06V 10/82 (2022.01); G06V 10/52 (2022.01);
U.S. Cl.
CPC ...
G06V 10/774 (2022.01); G06T 7/001 (2013.01); G06T 11/00 (2013.01); G06V 10/7715 (2022.01); G06V 10/776 (2022.01); G06V 10/7792 (2022.01); G06V 10/82 (2022.01); G06T 2207/20016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30108 (2013.01); G06V 10/52 (2022.01); G06V 2201/06 (2022.01);
Abstract

A method for generating an industrial defect image, a device, a medium, and a product are provided, relating to the field of image processing. The method includes: acquiring an industrial defect-free image; and generating an industrial defect image based on the industrial defect-free image by using a defect image generation model. The defect image generation model is constructed based on a cyclic Generative Adversarial Network (GAN); the defect image generation model includes two generators and two discriminators, with each generator including an encoder, a transformer, and a decoder connected in sequence; the encoder uses convolution operations to extract features from an input image, the transformer uses a self-attention-based residual network to transform an image output by the encoder, and the decoder uses a skip connection mechanism and deconvolution operations to decode an image output by the transformer to obtain a generated image.


Find Patent Forward Citations

Loading…