Method and apparatus for spot-checking visual inspection system

Patent metadata

Field	Value
Publication number	US-12067710-B2
Application number	US-202318296995-A
Country	US
Kind code	B2
Filing date	Apr 7, 2023
Priority date	Aug 30, 2022
Publication date	Aug 20, 2024
Grant date	Aug 20, 2024

Abstract

A spot-checking method for a visual inspection system includes obtaining a plurality of to-be-inspected images, inspecting the plurality of to-be-inspected images to obtain defect types and/or parameters of a target object in the plurality of to-be-inspected images, and confirming availability of the visual inspection system based on the defect types and/or the parameters.

First claim

What is claimed is:

1. A spot-checking method for a visual inspection system, comprising:
obtaining a plurality of to-be-inspected images;
inspecting the plurality of to-be-inspected images to obtain defect types and/or parameters of a target object in the plurality of to-be-inspected images, comprising:
determining a size of the target object in each of the plurality of to-be-inspected images by calculating a number of pixels included in the target object in the each of the plurality of to-be-inspected images; and

confirming availability of the visual inspection system based on the defect types and/or the parameters, comprising:
confirming the availability of the visual inspection system by comparing the number of pixels included in the target object in each of the plurality of to-be-inspected images with a threshold.

2. The spot-checking method according to claim 1 , wherein obtaining the plurality of to-be-inspected images comprises:
obtaining the plurality of to-be-inspected images from a specimen image library, wherein a defect type of each image in the specimen image library is known.

3. The spot-checking method according to claim 1 , wherein inspecting the plurality of to-be-inspected images to obtain defect types and/or the parameters of the target object in the plurality of to-be-inspected images further comprises:
performing defect detection on the plurality of to-be-inspected images by using a defect detection algorithm in the visual inspection system, to obtain the defect types of the target object in the plurality of to-be-inspected images.

4. The spot-checking method according to claim 1 , wherein confirming the availability of the visual inspection system based on the defect types and/or the parameters further comprises:
confirming, in response to the defect type of the target object in each of the plurality of to-be-inspected images being identical to a known defect type, that a defect detection algorithm of the visual inspection system is available.

5. The spot-checking method according to claim 1 , wherein obtaining the plurality of to-be-inspected images comprises:
running a standard target object inspection process; and
obtaining images of the target object captured by the visual inspection system as the plurality of to-be-inspected images.

6. The spot-checking method according to claim 1 , wherein the target object includes a battery cell or a sheet film.

7. The spot-checking method according to claim 1 , wherein inspecting the plurality of to-be-inspected images to obtain the defect types and/or the parameters of the target object in the plurality of to-be-inspected images further comprises:
performing grayscale measurement on each of the plurality of to-be-inspected images through the visual inspection system, to obtain grayscale of the target object in each of the plurality of to-be-inspected images.

8. The spot-checking method according to claim 1 , wherein confirming the availability of the visual inspection system based on the defect types and/or the parameters further comprises:
confirming, in response to the size of the target object in each of the plurality of to-be-inspected images being consistent with the threshold, that hardware of the visual inspection system is available.

9. The spot-checking method according to claim 8 , wherein the hardware comprises a plurality of cameras and a plurality of light sources.

10. The spot-checking method according to claim 9 , further comprising, before obtaining the plurality of to-be-inspected images:
receiving a selection instruction of a camera; and
setting the threshold of the target object corresponding to the camera.

11. The spot-checking method according to claim 10 , further comprising:
setting a number of times that the camera is to be spot-checked.

12. A non-transitory computer-readable storage medium storing a computer program that, when executed on a computer, causes the computer to perform the spot-checking method according to claim 1 .

13. A spot-checking apparatus for a visual inspection system, comprising:
an obtaining unit, configured to obtain a plurality of to-be-inspected images; and
a processing unit, configured to:
inspect the plurality of to-be-inspected images to obtain defect types and/or parameters of a target object in the plurality of to-be-inspected images, comprising:
determining a size of the target object in each of the plurality of to-be-inspected images by calculating a number of pixels included in the target object in the each of the plurality of to-be-inspected images; and

confirm availability of the visual inspection system based on the defect types and/or the parameters, comprising:
confirming the availability of the visual inspection system by comparing the number of pixels included in the target object in each of the plurality of to-be-inspected images with a threshold.

14. The spot-checking apparatus according to claim 13 , wherein the obtaining unit is further configured to obtain the plurality of to-be-inspected images from a specimen image library, wherein a defect type of each image in the specimen image library is known.

15. The spot-checking apparatus according to claim 13 , wherein the processing unit is further configured to:
perform defect detection on the plurality of to-be-inspected images by using a defect detection algorithm in the visual inspection system, to obtain the defect types of the target object in the plurality of to-be-inspected images.

16. The spot-checking apparatus according to claim 13 , wherein the processing unit is further configured to:
confirm, in response to the defect type of the target object in each of the plurality of to-be-inspected images being identical to a known defect type, that a defect detection algorithm of the visual inspection system is available.

17. The spot-checking apparatus according to claim 13 , wherein:
the processing unit is further configured to run a standard target object inspection process; and
the obtaining unit is further configured to obtain images of the target object captured by the visual inspection system as the plurality of to-be-inspected images.

18. The spot-checking apparatus according to claim 13 , wherein the processing unit is further configured to:
perform grayscale measurement on each of the plurality of to-be-inspected images through the visual inspection system, to obtain grayscale of the target object in each of the plurality of to-be-inspected images.

19. A spot-checking apparatus for a visual inspection system, comprising:
a memory storing a program; and
a processor configured to call the program from the memory and run the program to:
obtain a plurality of to-be-inspected images;
inspect the plurality of to-be-inspected images to obtain defect types and/or parameters of a target object in the plurality of to-be-inspected images, comprising:
determining a size of the target object in each of the plurality of to-be-inspected images by calculating a number of pixels included in the target object in the each of the plurality of to-be-inspected images; and

confirm availability of the visual inspection system based on the defect types and/or the parameters, comprising:
confirming the availability of the visual inspection system by comparing the number of pixels included in the target object in each of the plurality of to-be-inspected images with a threshold.

20. The spot-checking method according to claim 1 , wherein the threshold comprises a number of pixels included in t

Assignees

• Contemporary Amperex Technology Co Ltd

Inventors

• Wu Qian
• Chen Jiwei
• Jiang Guannan

Classifications

• G01N21/8851

  Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges (G01N21/8806 and G01N21/93 - G01N21/95692 take precedence; optical measurement of dimensions G01B11/00; optical scanning G02B26/10; image transformation G06T3/00; computerised image enhancement G06T5/00; image processing per se for flaw detection G06T7/0002) · CPC title

• G01N2021/8887

  based on image processing techniques · CPC title

• G06T7/0004 Primary

  Industrial image inspection · CPC title

• G06T2207/30108

  Industrial image inspection · CPC title

• G06T7/001 Primary

  using an image reference approach · CPC title