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

Convolutional neural network image restoration method for reflective metal visual detection

A convolutional neural network and visual inspection technology, applied in neural learning methods, biological neural network models, image enhancement, etc., can solve problems such as poor application effect of image restoration technology, improve image restoration quality, and save cumbersome links Effect

Active Publication Date: 2019-08-06
SOUTH CHINA UNIV OF TECH
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It can be seen that the image restoration technology based on the linear degradation model is not effective in the application of reflective metal visual inspection, and the convolutional neural network image restoration technology is the future trend in this field

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
  • Convolutional neural network image restoration method for reflective metal visual detection
  • Convolutional neural network image restoration method for reflective metal visual detection
  • Convolutional neural network image restoration method for reflective metal visual detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The present invention will be further described in detail below in conjunction with the embodiments and accompanying drawings.

[0015] The present invention is a convolutional neural network image restoration method for reflective metal visual detection, such as figure 1 As shown, the method includes the following steps:

[0016] Step 10, introducing slack variables to decouple the maximum a posteriori probability image restoration model;

[0017] Maximum Posteriori Probability Image Restoration Model argmax x p(x|k,y)∝p(yk,x)p(x) by introducing slack variables Likelihood with the prior term Where y, k, and x represent blurred image, blurred kernel, and clear image respectively, and the constraints are

[0018] Step 20, constructing the principal component of the logarithmic likelihood item based on the Poisson distribution, introducing a nonlinear degradation model, and eliminating pixels saturated with reflective metal;

[0019] Construct log-likelihood te...

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 provides a convolutional neural network image restoration method for reflective metal visual detection, and the method comprises the steps: introducing a relaxation variable, and decoupling a maximum posteriori probability image restoration model; constructing a logarithmic likelihood item principal component based on Poisson distribution, introducing a nonlinear degradation model, and removing reflective metal saturated pixels; constructing a logarithm prior item principal component based on the convolutional neural network, and constraining an image restoration solution space;and alternately updating the likelihood item and the prior item, and optimizing the final restored image through multi-stage connection. According to the method, the advantages of the convolutional neural network are utilized, the tedious link of manual design of priori items is omitted, the image restoration quality is improved based on the nonlinear degradation model, and the application of theimage restoration technology in reflective metal visual detection is facilitated.

Description

technical field [0001] The invention relates to the field of image restoration, in particular to a convolutional neural network image restoration method for reflective metal visual detection. Background technique [0002] Visual inspection technology has been widely used due to its high accuracy, non-contact and good applicability. Visual inspection under dynamic imaging conditions is prone to motion blur, which reduces the reliability of inspection results. Image restoration technology is an important auxiliary tool for visual inspection technology to obtain potential clear images from observed blurred images. There are many kinds of visual inspection targets, among which metal targets are difficult to avoid reflection phenomenon, especially under dynamic imaging conditions. Reflections cause oversaturated areas of the image, known as saturated pixels. Saturated pixels do not conform to the assumptions of image linear degradation models, and image restoration techniques ...

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
IPC IPC(8): G06T5/00G06N3/02G06N3/08
CPCG06T2207/20084G06T2207/20081G06T5/77
Inventor 刘桂雄王博帝
Owner SOUTH CHINA UNIV OF TECH
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com