Inference computing apparatus, model training apparatus, inference computing system
US-2021209488-A1 · Jul 8, 2021 · US
Method of detecting defect and system of detecting defect
US12277694B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12277694-B2 |
| Application number | US-202117325396-A |
| Country | US |
| Kind code | B2 |
| Filing date | May 20, 2021 |
| Priority date | Aug 27, 2020 |
| Publication date | Apr 15, 2025 |
| Grant date | Apr 15, 2025 |
How to read this patent
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
- Title
What the patent document calls the invention.
- Abstract
A short plain-language summary of the technical disclosure.
- Assignees and inventors
Who owns or filed the patent and who is credited as inventor.
- Key dates
Filing, priority, publication, and grant dates set the timeline.
- First independent claim
The legal scope of protection — read this for what is actually claimed.
- CPC / IPC classifications
Technology tags used to group this patent with similar filings.
- Citations and related patents
Prior art links and similar publications in this corpus.
Abstract
Official abstract text for this publication.
A method of detecting a defect in a stacked structure of a display panel includes collecting a first image of the defect and a plurality of layers in the stacked structure from a database, learning a defect information of the defect and a layer information of the layers using a deep learning model based on the first image and detecting a location of the defect among the layers by the defect information and the layer information.
First claim
Opening claim text (preview).
What is claimed is: 1. A method of detecting a defect in a stacked structure of a display panel, the method comprising: collecting a first image of the defect and a plurality of layers in the stacked structure in a cross-section from a database; learning a defect information of the defect and a layer information of the plurality of layers using a deep learning model based on the first image; and detecting a location of the defect among the plurality of layers by the defect information and the layer information, wherein the defect information includes a component information of the defect, the layer information includes a component information of the plurality of layers, and the component information of the defect and the component information of the plurality of layers each exhibit a predetermined color. 2. The method of claim 1 , wherein the first image is one of a transmission electron microscope image, a scanning electron microscope image, a scanning transmission electron microscope image and a secondary ion microscope image. 3. The method of claim 1 , wherein the first image is an energy dispersive X-ray spectroscopy elemental mapping image. 4. The method of claim 1 , wherein the deep learning model includes a convolutional neural network. 5. The method of claim 1 , wherein the deep learning model includes a plurality of convolution layers and an attention module. 6. A method of detecting a defect in a stacked structure of a display panel, the method comprising: collecting a first image of the defect and a plurality of layers in the stacked structure from a database; learning a first defect information of the defect and a first layer information of the plurality of layers using a deep learning model based on the first image; extracting a first location information of the defect by the first defect information and the first layer information; collecting a second image of the defect and the plurality of layers in the stacked structure from a database; learning a second defect information of the defect and a second layer information of the plurality of layers using the deep learning model based on the second image; extracting a component information of the defect and first component information of the plurality of layers using the second defect information and the second layer information; learning a second location information of the defect and a second component information of the plurality of layers using the deep learning model based on the first location information of the defect, the component information of the defect and the first component information of the plurality of layers; and detecting a location of the defect among the plurality of layers by the second location information of the defect and the second component information of the plurality of layers. 7. The method of claim 6 , wherein the deep learning model includes a convolutional neural network. 8. The method of claim 6 , wherein the deep learning model includes a plurality of convolution layers and an attention module. 9. The method of claim 6 , wherein the deep learning model includes an average pooling. 10. A system of detecting a defect in a stacked structure of a display panel, the system comprising; a collection unit which collects a first image of the defect and a plurality of layers in the stacked structure in a cross-section from a database; a learning unit which learns a defect information of the defect and a layer information of the plurality of layers using a deep learning model based on the first image; and a detection unit which detects a location of the defect among the plurality of layers using the defect information and the layer information, wherein the defect information includes a component information of the defect, the layer information includes a component information of the plurality of layers, and the component information of the defect and the component information of the plurality of layers each exhibit a predetermined color. 11. The system of claim 10 , wherein the first image is one of a transmission electron microscope image, a scanning electron microscope image, a scanning transmission electron microscope image and a secondary ion microscope image. 12. The system of claim 10 , wherein the first image is an energy dispersive X-ray spectroscopy elemental mapping image. 13. The system of claim 10 , wherein the deep learning model includes a convolutional neural network. 14. The system of claim 10 , wherein the deep learning model includes a plurality of convolution layers and an attention module.
Assignees
Inventors
Classifications
Convolutional networks [CNN, ConvNet] · CPC title
Supervised learning · CPC title
Learning methods · CPC title
X-ray image · CPC title
from scanning electron microscope · CPC title
Patent family
Related publications grouped by family.
External sources
Frequently asked questions
Answers are generated from the same data shown on this page.
- What does patent US12277694B2 cover?
- A method of detecting a defect in a stacked structure of a display panel includes collecting a first image of the defect and a plurality of layers in the stacked structure from a database, learning a defect information of the defect and a layer information of the layers using a deep learning model based on the first image and detecting a location of the defect among the layers by the defect inf…
- Who is the assignee on this patent?
- Samsung Display Co Ltd
- What technology area does this patent fall under?
- Primary CPC classification G06T7/0004. Mapped technology areas include Physics.
- When was this patent published?
- Publication date Tue Apr 15 2025 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
- What related patents are in patentsdb?
- We list 4 related publications on this page (citations in our corpus or others sharing the same primary CPC).