System and method for combined automatic and manual inspection
US-2019164270-A1 · May 30, 2019 · US
US11295436B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11295436-B2 |
| Application number | US-202016877000-A |
| Country | US |
| Kind code | B2 |
| Filing date | May 18, 2020 |
| Priority date | May 18, 2020 |
| Publication date | Apr 5, 2022 |
| Grant date | Apr 5, 2022 |
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 vision inspection system includes a rotary sorting platform rotated about an axis to rotate parts. The vision inspection system includes an inspection station positioned adjacent the rotary sorting platform including imaging devices to image different sides of the parts. The vision inspection system includes a vision inspection controller receiving images from the imaging devices and processing the images from the imaging devices based on an image analysis model. The vision inspection controller processes the images to determine inspection results for each of the parts. The vision inspection controller has an artificial intelligence learning module operated to update the image analysis model based on the images received from the imaging devices.
Opening claim text (preview).
What is claimed is: 1. A vision inspection system comprising: a rotary sorting platform being rotated about an axis, the rotary sorting platform rotating parts from a first position to a second position; an inspection station positioned adjacent to the rotary sorting platform, the inspection station including imaging devices to image different sides of the parts, the imaging devices imaging the different sides of the parts at different times and at different rotary distances from the first position; and a vision inspection controller receiving images from the imaging devices and processing the images from the imaging devices based on an image analysis model, the vision inspection controller processing the images to determine inspection results for each of the parts, the vision inspection controller having an artificial intelligence learning module operated to update and expand the image analysis model in real time based on the images of the different sides of the parts received from the imaging devices such that the image analysis model is configured to learn from the images of the imaging devices. 2. The vision inspection system of claim 1 , wherein the image analysis model changes over time based on input from the artificial intelligence learning module. 3. The vision inspection system of claim 1 , wherein the artificial intelligence learning module is operable in a learning mode to train the vision inspection controller and develop the image analysis model. 4. The vision inspection system of claim 1 , wherein the rotary sorting platform includes a glass plate being transparent, at least one of the imaging devices imaging the parts through the transparent glass plate. 5. The vision inspection system of claim 1 , wherein the inspection results include a pass result if the processed image is acceptable based on the image analysis model and the inspection results include a reject result if the processed image is defective based on the image analysis model. 6. The vision inspection system of claim 1 , wherein the vision inspection controller processes the images by performing pattern recognition based on the image analysis model. 7. The vision inspection system of claim 1 , wherein the vision inspection controller processes the images by performing feature extraction of boundaries and surfaces in the images and comparing the boundaries and surfaces to the image analysis model. 8. The vision inspection system of claim 7 , wherein the artificial intelligence learning module updates the image analysis model based on the boundaries and surfaces extracted from the images. 9. The vision inspection system of claim 1 , further comprising a triggering sensor positioned adjacent to the rotary sorting platform upstream of the inspection station, the triggering sensor triggering operation of the imaging devices based on the triggering sensor sensing the parts. 10. The vision inspection system of claim 1 , further comprising an ejector and a collection bin, the ejector being operated to eject the parts from the rotary sorting platform into the collection bin based on the inspection results. 11. A vision inspection system comprising: a rotary sorting platform having a transparent plate being rotated about an axis, the rotary sorting platform rotating parts from a first position to a second position; an inspection station positioned adjacent to the transparent plate, the inspection station including imaging devices to image different sides of the parts including an upper imaging device, a lower imaging device, and a first side imaging device, the upper imaging device located above the transparent plate for imaging top sides of the parts, the lower imaging device located below the transparent plate for imaging bottom sides of the parts through the transparent plate, the first side imaging device located adjacent to the transparent plate generally coplanar with an upper surface of the transparent plate for imaging first sides of the parts; a vision inspection controller receiving images from the imaging devices and processing the images from the imaging devices based on an image analysis model, the vision inspection controller processing the images to determine inspection results for each of the parts, the vision inspection controller having an artificial intelligence learning module operated to update the image analysis model based on the images received from the imaging devices; and a triggering sensor positioned adjacent to the rotary sorting platform upstream of the inspection station, the triggering sensor triggering operation of the imaging devices based on the triggering sensor sensing the parts, wherein the upper imaging device is located at a first rotary distance from the triggering sensor, the lower imaging device being located at a second rotary distance from the triggering sensor, and the first side imaging device being located at a third rotary distance from the triggering sensor, timing of imaging of the upper imaging device being based on the first rotary distance, timing of imaging of the lower imaging device being based on the second rotary distance, and timing of imaging of the first side imaging device being based on the third rotary distance. 12. The vision inspection system of claim 11 , wherein the image analysis model changes over time based on input from the artificial intelligence learning module. 13. The vision inspection system of claim 11 , wherein the artificial intelligence learning module is operable in a learning mode to train the vision inspection controller and develop the image analysis model. 14. The vision inspection system of claim 11 , wherein the vision inspection controller processes the images by performing feature extraction of boundaries and surfaces in the images and comparing the boundaries and surfaces to the image analysis model. 15. The vision inspection system of claim 14 , wherein the artificial intelligence learning module updates the image analysis model based on the boundaries and surfaces extracted from the images. 16. The vision inspection system of claim 11 , wherein the inspection station further includes a second side imaging device located adjacent to the transparent plate generally coplanar with the upper surface of the transparent plate for imaging second sides of the parts opposite the first sides of the parts. 17. The vision inspection system of claim 16 , wherein the inspection station further includes a front side imaging device and a rear side imaging device, the front side imaging device located adjacent to the transparent plate generally coplanar with the upper surface of the transparent plate for imaging front side of the parts, the rear side imaging device located adjacent to the transparent plate generally coplanar with the upper surface of the transparent plate for imaging rear sides of the parts. 18. A method of inspecting parts comprising: loading a first part of the parts on a rotary sorting platform; rotating the first part from a first position to a second position; imaging the first part at an inspection station positioned adjacent to the rotary sorting platform using imaging devices to image different sides of the first part, wherein the imaging devices image the different sides of the parts at different times and at different rotary distances from the first position; receiving images from the imaging devices at a vision inspection controller; processing the images from the imaging devices at the vision inspection controller based on an image analysis model to determine inspection results for the firs
Industrial image inspection · CPC title
Three-dimensional [3D] objects · CPC title
Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title
using a design-rule based approach · CPC title
Control of cameras or camera modules · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.