Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A super-resolution deblurring method with generative adversarial networks

A super-resolution and deblurring technology, applied in the field of pattern recognition, can solve the problems of low intelligence and poor adaptability, and achieve the effect of improving ability, reducing impact and improving training speed.

Active Publication Date: 2022-03-18
STATE GRID INTELLIGENCE TECH CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a super-resolution deblurring method of a generative adversarial network, which aims to solve the problems of low intelligence and poor adaptability of the existing deblurring algorithms, and realize the improvement of training speed and deblurring speed. Reducing the Influence of Expertise and Experience on the Design of Deblurring Algorithms

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
  • A super-resolution deblurring method with generative adversarial networks
  • A super-resolution deblurring method with generative adversarial networks
  • A super-resolution deblurring method with generative adversarial networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] In order to clearly illustrate the technical features of the present solution, the present invention will be described in detail below through specific implementation methods and in conjunction with the accompanying drawings. The following disclosure provides many different embodiments or examples for implementing different structures of the present invention. To simplify the disclosure of the present invention, components and arrangements of specific examples are described below. Furthermore, the present invention may repeat reference numerals and / or letters in different instances. This repetition is for simplicity and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. It should be noted that components illustrated in the figures are not necessarily drawn to scale. Descriptions of well-known components and processing techniques and processes are omitted herein to avoid unnecessarily limiting the prese...

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 present invention provides a super-resolution defuzzification method of a generative confrontation network, comprising: S1, using the DRCN network structure to form a super-resolution deep convolution network, and establishing a confrontation network model; S2, combining the SRGAN network cost function, improving Confrontation network performance; S3, select a clear picture, add Gaussian noise and motion blur to realize training. The present invention analyzes the characteristics of the motion blur, designs the artificial noise of the sample, adds the defocus blur kernel and the multi-directional motion blur kernel, realizes the super-resolution motion blur removal processing of double-magnification of the blur image, and shoots the UAV Experimental analysis of blurred images can greatly reduce the influence of professional knowledge and experience on the design of deblurring algorithms.

Description

technical field [0001] The invention relates to the technical field of pattern recognition, in particular to a super-resolution defuzzification method of a generative confrontation network. Background technique [0002] With the rapid development of the economy, the demand for power transmission and transformation in my country continues to increase, the scale of the power system continues to expand, and the safety and stability of the power system are becoming increasingly prominent, which puts forward higher requirements for the reliability of power transmission and transformation technology. The main function of power transmission and transformation technology is to meet people's power needs. At the same time, the skilled application of power technology is also the basis for ensuring stable power supply of the power grid. At the same time, it can effectively prevent accidents during the power supply process and promote the construction and development of my country's power...

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): G06T5/00G06N3/04
CPCG06T5/003G06N3/045
Inventor 刘广秀许玮王万国李建祥郭锐赵金龙王振利张旭刘越李振宇刘斌许荣浩白万建李勇杨波孙晓斌
Owner STATE GRID INTELLIGENCE TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products