Vision-based medical injection molded part appearance defect detection method

A technology of appearance defects and detection methods, which is applied in the field of computer vision recognition, can solve the problems that the detection accuracy of silicone parts cannot meet the product detection requirements, and achieve the effect of improving the degree of automation

Pending Publication Date: 2022-02-01
博科视(苏州)技术有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The detection accuracy of the existing detection technology for silicone parts cannot meet the detection requirements of the product, and the detection of silicone parts cannot be completed within the time range of the production cycle

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
  • Vision-based medical injection molded part appearance defect detection method
  • Vision-based medical injection molded part appearance defect detection method
  • Vision-based medical injection molded part appearance defect detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0075] The defect types of medical injection molded parts can be abstractly divided into shape and texture. The optical imaging solution uses two methods of ring light and light collection for these two types of defects.

[0076] For morphological defects, the main manifestations are burrs and edging. These defects will change the shape of injection molded parts to a certain extent. Using light collection for imaging and shooting can achieve a good per...

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 medical injection molding part appearance defect detection method based on combination of visual template matching and deep learning, and the method comprises the steps: carrying out the photographing and imaging of a to-be-detected medical injection molding part under an annular light source and a collected light source, and obtaining an annular light image and a collected light image of the to-be-detected medical injection molding part; using the deep learning model to carry out defect feature detection of glue shortage, pocking marks and joint lines on the ring light image of the medical injection molding part to be detected, and storing the ring light judgment result of the ring light image; adopting a template matching method for carrying out burr and burr defect feature detection on the light collection image of the medical injection molding part to be detected, and outputting a light collection judgment result of the light collection image; integrating the light-surrounding judgment result and the light-collecting judgment result, and if all the judgment results are qualified, outputting the detection result of the medical injection-molded part to be detected as a qualified product, otherwise, outputting the detection result of the medical injection-molded part to be detected as a defective product. According to the invention, on the premise of ensuring the production takt, unqualified products can be quickly detected, and the treatment time of a single sample is reduced by comprehensively judging and outputting two types of detection results.

Description

technical field [0001] The invention relates to the technical field of computer vision recognition, in particular to a vision-based method for detecting appearance defects of medical injection molded parts. Background technique [0002] This injection molded part is used in the inspiratory mixing part of the ventilator. It is used to mix the air and oxygen input into the ventilator and ensure the airtightness of the ventilator. It is a very important part of the ventilator. At present, the pain point of injection molded parts inspection lies in the existence of tiny defects, and the traditional manual inspection method has poor stability and efficiency. [0003] In the prior art, Eggert et al. proposed a candidate frame extraction method based on feature map upsampling in ACM's Improving small object proposals for company logo detection. They used high-resolution feature maps to extract candidate frames for small objects. On the one hand, the candidate frame is closer to th...

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): G06T7/00G06T3/00G06N3/04G06N3/08
CPCG06T7/0004G06T3/0006G06N3/08G06N3/045
Inventor 张立兴毛亮孟春婵
Owner 博科视(苏州)技术有限公司
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