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

Aluminum Surface Defect Detection Method Based on Improved Cascade R-CNN

An improved technology for defect detection, applied in neural learning methods, biological neural network models, image enhancement, etc., can solve problems such as difficult detection of extreme aspect ratios, high false detection rate, etc., to alleviate the loss of precision and improve the detection rate , the effect of training step improvement

Active Publication Date: 2022-04-22
SOUTH CHINA UNIV OF TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The existing two-stage deep learning object detector has high accuracy and good versatility, but it is still difficult to detect extreme aspect ratio defects in the detection of aluminum surface defects, and normal pictures without defects cannot participate in model training, making mistakes High detection rate and other issues

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
  • Aluminum Surface Defect Detection Method Based on Improved Cascade R-CNN
  • Aluminum Surface Defect Detection Method Based on Improved Cascade R-CNN
  • Aluminum Surface Defect Detection Method Based on Improved Cascade R-CNN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further described below in conjunction with specific examples.

[0040] The example uses real collected aluminum surface picture data, including 10 kinds of defects such as non-conductivity, scratches, orange peel, and dirty spots, several normal pictures and marked defect pictures, and the picture size is 2560*1920.

[0041] like figure 1 and figure 2 As shown, the improved Cascade R-CNN-based aluminum surface defect detection method provided in this embodiment includes the following steps:

[0042] 1) Standardize the size of the aluminum surface picture set, and scale all the picture sizes to 1280*960. The pictures containing defects have corresponding defect labeling files, and the picture set is divided into a normal picture set and a defect picture set according to whether the picture contains a defect labeling file.

[0043] The aluminum surface picture set includes a defect picture set X containing defects, a normal picture set Y...

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 an aluminum material surface defect detection method based on an improved Cascade R-CNN, comprising the steps of: 1) standardizing the size of the aluminum material surface pictures, cutting and classifying; 2) normalizing the picture set and online Data enhancement and batch division; 3) use the improved Cascade R-CNN algorithm for iterative training of all batches of pictures; 4) repeat step 2) to step 3), iterative training to obtain aluminum surface defect detection model; 5 ) Input the surface picture of the aluminum material to be detected into the aluminum material surface defect detection model to obtain the detection result. The invention can effectively reduce the influence of conditions such as illumination, exposure and displacement on defect detection, improve the detection stability, and at the same time greatly increase the detection rate of defects with extreme aspect ratios and reduce the false detection rate.

Description

technical field [0001] The invention relates to the technical field of aluminum surface defect detection, in particular to an aluminum surface defect detection method based on an improved Cascade R-CNN. Background technique [0002] Defect detection is an important part of the production process, which guarantees the reliability of industrial products. The surface defect detection of aluminum needs to classify whether there are defects on the surface, and then accurately locate the position of the existing defects, and accurately classify the located defects, which is a combination of classification problems and target detection problems. Prior to this, the surface defect detection technology of aluminum usually used traditional machine vision technology to perform operations such as image grayscale binarization, edge contour extraction, and template matching. The disadvantage of this type is that it is very sensitive to changes in the illumination and displacement of the im...

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): G06T7/00G06T7/136G06T7/194G06V10/25G06V10/774G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06T7/0002G06T7/136G06T7/194G06N3/084G06T2207/10004G06T2207/20016G06T2207/20104G06T2207/20081G06T2207/20084G06T2207/30168G06V10/25G06N3/045G06F18/2148
Inventor 许玉格郭子兴吴宗泽
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