Unlock instant, AI-driven research and patent intelligence for your innovation.

An Image Highlight Processing Method Based on Custom Fuzzy Logic and GAN

A technology of fuzzy logic and highlight processing, applied in image data processing, image enhancement, image analysis, etc., can solve problems such as low image quality and unsatisfactory image texture restoration effect, and achieve the effect of improving applicability

Active Publication Date: 2022-08-02
NORTHEAST FORESTRY UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods have achieved good results in the overall repair effect of image highlight overflow, but the texture repair effect of the image is not ideal, and the quality of the obtained image is not high.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An Image Highlight Processing Method Based on Custom Fuzzy Logic and GAN
  • An Image Highlight Processing Method Based on Custom Fuzzy Logic and GAN
  • An Image Highlight Processing Method Based on Custom Fuzzy Logic and GAN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention. figure 1 is the membership function curve diagram used by the fuzzy logic in the module of the present invention to divide the highlight area, and the function expression is In this formula, x represents the brightness value in the continuous reading channel, a, b, and c are the parameters of the function S, a, c are the value ranges of the brightness channel, b represents the transition point divided into brightness regions, a, The positions of b and c are as ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention proposes an image highlight restoration method based on fuzzy logic and generative confrontation network. In this method, fuzzy logic is used to judge the image highlight areas, and a generative adversarial network with dual discriminators is designed to inpaint the image highlight areas. In addition, the present invention adds a brightness parameter to the generator network to control the brightness range of the highlight area of ​​the generated image, and the brightness parameter is obtained by fuzzy logic. The invention is mainly divided into three parts. The first part divides the highlight area by fuzzy logic; The fusion technology processes the image generation part and the original image to further improve the repair effect of the highlight area. Compared with the traditional image processing, the present invention has been greatly improved in all aspects, especially in the aspect of image quality.

Description

Technical field: [0001] The invention relates to the technical field of image generation and processing, in particular to a method for detecting highlights on an image with highlights and regenerating and removing highlight regions based on a generative adversarial network based on a deep neural network. Background technique: [0002] In the process of image formation, light spots will be formed on the surface of the object because the object is illuminated or the surface curvature of the object is too large, and the part where the light spot appears is the part where the highlights overflow. Highlights have a great impact on image processing, such as image recognition, target detection, and scene analysis, which bring huge obstacles. Therefore, finding an effective method to de-highlight the highlight area is the research focus in the field of image processing. Deep learning is a new field in machine learning research. Its motivation is to establish and simulate the neural...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/00G06T7/10G06N3/04G06N3/08
CPCG06T7/10G06N3/084G06T2207/20221G06N3/048G06N3/045G06T5/77
Inventor 郭继峰李星马志强庞志奇朱泳
Owner NORTHEAST FORESTRY UNIVERSITY