Tire X-ray defect detection method for carrying out re-ranking by utilizing background features

A defect detection and defect technology, applied in the fields of computer vision and industrial inspection, can solve problems affecting traffic driving safety, high production requirements, air bubbles, etc., and achieve the effects of avoiding inefficiency, enhancing robustness, and increasing probability

Active Publication Date: 2020-05-19
ZHEJIANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, radial tires have very high production requirements, and their manufacturing process is more complicated than that of bias tires
In the production process of radial tires, it is very susceptible to the influence of mechanical eq

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
  • Tire X-ray defect detection method for carrying out re-ranking by utilizing background features
  • Tire X-ray defect detection method for carrying out re-ranking by utilizing background features
  • Tire X-ray defect detection method for carrying out re-ranking by utilizing background features

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0036] The implementation of the present application will be described in detail below in conjunction with the accompanying drawings and embodiments, so as to fully understand and implement the implementation process of how the application uses technical means to solve technical problems and achieve technical effects.

[0037] Reference Figure 1-2 This example aims to realize the defect detection of tire X-ray images according to the present invention. The process of the method includes data collection, image preprocessing, model training, and the use of background features for re-ranking and defect detection, such as image 3 As shown, the specific implementation process is as follows:

[0038] Step (1): Data collection. In this example, a total of 10,919 flawed pictures are marked. Each flawed picture indicates the location of all the flaws and the type of flaw. The marking format of the type is 0, 1, 3,..., 5. The specific types are shown in Table 1. This implementation In the...

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 tire X-ray defect detection method for carrying out re-ranking by utilizing background features. When defect detection is carried out after a model is trained, a to-be-detected picture is input into the model, and a plurality of pictures without any defect are randomly selected and are input into the model; when feature extraction is carried out on the to-be-detected picture, features of corresponding positions in the picture without any defect are also extracted; and the similarity between the defect feature vector and the background feature vector is calculated, candidate boxes are reranked according to the similarity, and a final detection result is output. The method has the following advantage: 1) the problems of low efficiency, high labor cost and the like inthe tire quality inspection process caused by human factors can be avoided through tire X-ray flaw detection based on deep learning; and 2) the information of the picture without defects is fully utilized, and the probability of the candidate boxes is corrected to a certain extent.

Description

technical field [0001] The invention relates to the technical fields of computer vision and industrial detection, in particular to a tire X-ray defect detection method using background features for reranking. Background technique [0002] Tires are an important pillar of my country's national economy, and tires in my country can be divided into bias-ply tires and radial-ply tires according to their carcass. Radial tires are widely used due to the advantages of small flow resistance, long service life, and good shock absorption performance. However, radial tires have very high production requirements, and their manufacturing process is more complicated than bias-ply tires. In the production process of radial tires, it is very susceptible to the influence of mechanical equipment, production process and other external environments, and there will be some defects such as impurities, thin tires, air bubbles, etc. These defects will affect the quality of tires and further affect ...

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): G06T7/00G06N3/08G06N3/04G06K9/62
CPCG06T7/0004G06N3/08G06T2207/10116G06T2207/20081G06T2207/20084G06T2207/30164G06N3/045G06F18/22G06F18/2415
Inventor 卢建刚郭培林陈金水
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap