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

Defect detection method based on ResNeXt network with shrinkage block

A defect detection and network technology, applied in the field of deep learning, can solve problems such as low accuracy rate, achieve the effect of improving accuracy rate and solving low accuracy rate

Pending Publication Date: 2022-01-21
GUILIN UNIV OF ELECTRONIC TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a defect detection method based on ResNeXt network with shrinkage blocks, aiming to solve the technical problem that the accuracy of the visual defect detection method in the prior art 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
  • Defect detection method based on ResNeXt network with shrinkage block
  • Defect detection method based on ResNeXt network with shrinkage block
  • Defect detection method based on ResNeXt network with shrinkage block

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0028] see figure 1 , the present invention proposes adopting a kind of ResNeXt network defect detection method based on having contraction block, comprises the following steps:

[0029] S1: import the data set, and expand the data set;

[0030] S2: Establish a ResNext network model;

[0031] S3: Establish a contraction module;

[0032] S4: merging the contraction module into the ResNext network model to construct a new network model;

[0033] S5: Train the new network model, and output the accuracy rates of various defects. ...

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 discloses a defect detection method based on a ResNeXt network with a contraction block. The method comprises the following steps: constructing a new network model through fusing a ResNext model and the contraction module, then importing an industrial defect data set to train the new network model, obtaining a trained network model, and carrying out the defect detection through employing the trained network model, thereby achieving the detection of defects. The fused model not only can improve the accuracy of defect detection, but also can eliminate redundant information in the network, so that the technical problem of low accuracy of a visual defect detection method in the prior art is solved.

Description

technical field [0001] The invention relates to the technical field of deep learning, in particular to a defect detection method based on a ResNeXt network with shrinkage blocks. Background technique [0002] The traditional visual defect detection method mainly draws conclusions by observing the product surface. This method relies too much on manual experience, the cost of detection is high, the efficiency is low, and it does not meet the requirements of real-time production. [0003] In recent years, with the development of machine vision technology, industrial inspection has begun to use machine vision technology. The existing machine vision technology is mainly a method of graphic processing and feature extraction. This method needs to be extracted for each defect and then identified. It is more troublesome. In addition, the method of classifier plus feature extraction is used for defect identification, and the automatic feature extraction cannot be performed. At the sam...

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 Applications(China)
IPC IPC(8): G06T7/00G06N3/04G06N3/08
CPCG06T7/0006G06N3/08G06T2207/10004G06N3/045
Inventor 蒋占四梁日强胡燕林滕制郑泽瀚程豪刘雪涛
Owner GUILIN UNIV OF ELECTRONIC TECH