Automated inspection system
US-2024420305-A1 · Dec 19, 2024 · US
US2025035559A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2025035559-A1 |
| Application number | US-202418912297-A |
| Country | US |
| Kind code | A1 |
| Filing date | Oct 10, 2024 |
| Priority date | Apr 18, 2022 |
| Publication date | Jan 30, 2025 |
| Grant date | — |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A method for defect detection of a cathode electrode plate of a composite material strip includes obtaining a continuous image of the composite material strip; intercepting at least one image segment from the continuous image of the composite material strip, where the image segment includes a cathode electrode plate body region; and performing detection on the cathode electrode plate body region.
Opening claim text (preview).
What is claimed is: 1 . A method for defect detection of a cathode electrode plate of a composite material strip, comprising: obtaining a continuous image of the composite material strip; intercepting at least one image segment from the continuous image of the composite material strip, wherein the image segment comprises a cathode electrode plate body region; and performing detection on the cathode electrode plate body region. 2 . The method according to claim 1 , wherein the image segment further comprises a separator region surrounding the cathode electrode plate body region, a plurality of tab protruding regions, and a background region adjacent to the separator region; the method further comprising: extracting the cathode electrode plate body region from the image segment. 3 . The method according to claim 2 , wherein extracting the cathode electrode plate body region from the image segment comprises: removing the background region from the image segment based on a maximum grayscale threshold of the background region to obtain an intermediate image; and removing the separator region and the plurality of tab protruding regions from the intermediate image based on a maximum grayscale threshold of the cathode electrode plate body region to obtain the cathode electrode plate body region. 4 . The method according to claim 1 , wherein performing detection on the cathode electrode plate body region comprises: determining, based on the cathode electrode plate body region, a detection region corresponding to the cathode electrode plate body region. 5 . The method according to claim 4 , wherein determining the detection region corresponding to the cathode electrode plate body region comprises: determining a minimum rectangular region circumscribed about edges of the cathode electrode plate body region, and taking the minimum rectangular region as the detection region corresponding to the cathode electrode plate body region. 6 . The method according to claim 5 , wherein determining the minimum rectangular region circumscribed about edges of the cathode electrode plate body region comprises: extracting a first straight edge and a second straight edge of the cathode electrode plate body region that have the same extension direction as the composite material strip and a third straight edge and a fourth straight edge that are orthogonal to the extension direction of the composite material strip; and determining the minimum rectangular region circumscribed about the edges of the cathode electrode plate body region based on intersections of the first straight edge, the second straight edge, the third straight edge, and the fourth straight edge. 7 . The method according to claim 4 , wherein performing detection on the cathode electrode plate body region comprises: determining whether the detection region comprises a suspected defect region. 8 . The method according to claim 7 , wherein determining whether the detection region comprises the suspected defect region comprises: in response to determining that the detection region comprises an abnormal pixel set, obtaining at least one independently connected abnormal pixel subset based on the abnormal pixel set, wherein a grayscale of each pixel in the abnormal pixel set is greater than the maximum grayscale threshold of the cathode electrode plate body region or less than a minimum grayscale threshold of the cathode electrode plate body region; and for each such abnormal pixel subset, in response to determining that an area of the abnormal pixel subset is greater than an area threshold, determining that the detection region comprises the suspected defect region. 9 . The method according to claim 8 , wherein performing detection on the cathode electrode plate body region comprises: determining a suspected defect type corresponding to the suspected defect region based on geometrical characteristic information and/or grayscale of the suspected defect region, wherein the suspected defect type comprises suspected damage or suspected wrinkle. 10 . The method according to claim 8 , wherein performing detection on the cathode electrode plate body region comprises: determining a confidence coefficient of the suspected defect region based on image information of the suspected defect region and image information of at least one electrode plate defect sample in an electrode plate defect sample library; and in response to determining that the confidence coefficient is greater than a confidence threshold, determining that the suspected defect region is a defect region. 11 . The method according to claim 1 , wherein obtaining a continuous image of the composite material strip comprises: obtaining a continuous image shot by a line scan camera for each side surface of the composite material strip. 12 . The method according to claim 1 , further comprising: outputting a detection result; wherein the detection result comprises at least one of the following: positioning information of the defect region in the image segment, geometrical characteristic information of the defect region, positioning information of the image segment corresponding to the composite material strip, alarm information indicating that the cathode electrode plate is defective, and a defect type, wherein the defect type comprises damage or wrinkle. 13 . An electronic device, comprising at least one processor and a memory communicatively connected to the at least one processor, wherein: the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is caused to execute the method according to claim 1 . 14 . A system for defect detection of a cathode electrode plate of a composite material strip, comprising: a first image acquisition unit, configured to acquire a continuous image of one side surface of the composite material strip; a second image acquisition unit, configured to acquire a continuous image of another side surface of the composite material strip; and the electronic device according to claim 13 , connected to the first image acquisition unit and the second image acquisition unit. 15 . The system according to claim 14 , wherein: the first image acquisition unit is a first line scan camera, and the second image acquisition unit is a second line scan camera; and the system further comprises a first line light source for illuminating an acquisition region of the first line scan camera and a second line light source for illuminating an acquisition region of the second line scan camera. 16 . The system according to claim 15 , further comprising: a first support roller and a first encoder connected to the first support roller, wherein the first support roller abuts against one side surface of the composite material strip, and the first encoder is configured to send a pulse signal to the first line scan camera to trigger the first line scan camera to acquire images line by line; and a second support roller and a second encoder connected to the second support roller, wherein the second support roller abuts against another side surface of the composite material strip, and the second encoder is configured to send a pulse signal to the second line scan camera to trigger the second line scan camera to acquire images line by line. 17 . The system according to claim 16 , wherein: the acquisition region of the first line scan camera is arranged at a tangent position of the composite material strip and the first suppo
Workpiece; Machine component · CPC title
involving thresholding · CPC title
Region-based segmentation · CPC title
Industrial image inspection · CPC title
involving foreground-background segmentation · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.