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

A detection method, device and medium for uncertain samples in defect detection

A defect detection and detection method technology, which is applied in neural learning methods, image analysis, image enhancement, etc., can solve problems such as difficult to meet real-time detection, and achieve high-volume automated industrial production, small computing overhead, and low error detection rate Effect

Active Publication Date: 2022-05-03
宁波海棠信息技术有限公司
View PDF8 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 detection method for uncertain samples in defect detection, to solve the problem that current uncertainty estimation methods are difficult to meet real-time detection

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 detection method, device and medium for uncertain samples in defect detection
  • A detection method, device and medium for uncertain samples in defect detection
  • A detection method, device and medium for uncertain samples in defect detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] It should be noted that all directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relationship between the components in a certain posture (as shown in the figure). Relative positional relationship, movement conditions, etc., if the specific posture changes, the directional indication will also change accordingly.

[0041] In addition, in the present invention, descriptions such as "first", "second", "one" and so on are used for descriptive purposes only, and should not be understood as indicating or implying their relative importance or implicitly indicating the indicated technical features quantity. Thus, the features defined as "first" and "second" may explicitly or implicitly include at least one of these features. In the description of the present invention, "plurality" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0042] In addition...

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 belongs to the technical field of image target detection, and provides a detection method, device and medium for an uncertain sample in defect detection, including steps: S1, collecting an image of a sample to be detected; S2, passing a trained defect target detector to The input sample image to be detected is detected, and the category and feature vector of the defective target are obtained; S3, according to the category and feature vector of the defective target, the cognitive uncertainty of the target is estimated by a preset Gaussian mixture model group after modeling, And judge whether the sample to be tested is an uncertain sample according to the cognitive uncertainty of the target. The advantage of the present invention is that the cognitive uncertainty estimation method based on the Gaussian mixture model can effectively detect the uncertainty samples for the defect detector, assign them to manual detection, and greatly reduce the error of the defect detection model The detection rate has achieved a reasonable combination of manual detection and machine detection.

Description

technical field [0001] The invention relates to the technical field of image target detection, in particular to a detection method, device and medium for uncertain samples in defect detection. Background technique [0002] Since it is impossible to maintain an absolutely ideal state in the manufacturing process and production environment during the production process, there may inevitably be defects on the surface of the product, resulting in unqualified quality. If unqualified defective products flow into the market, it will affect the user experience at least, damage the reputation of the manufacturer, and lead to safety accidents at worst, causing irreparable and serious consequences. Therefore, it is very important for the development of production enterprises to inspect the appearance quality of products according to production standards before leaving the factory. [0003] With the continuous development of computer vision technology, defect detection based on deep le...

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): G06T7/00G06V10/762G06V10/764G06V10/774G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06T7/0004G06N3/04G06N3/08G06T2207/20081G06T2207/20084G06F18/23G06F18/214G06F18/24
Inventor 张重阳李若琦秦彪张保柱
Owner 宁波海棠信息技术有限公司
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