US 11,995,812 B2
Next generation quality inspection
Kyryll Zaytsev, Montreal (CA); Jarred Knecht, Montreal (CA); Hafizur Md Rahman, Montreal (CA); Ahmad Raza, Surrey (CA); Prabhjyot Gill, Montreal (CA); Vikrant Vikrant, Montreal (CA); and Sandeep Annabathuni, Longueuil (CA)
Assigned to Electrical Components International, Inc., St. Louis, MO (US)
Filed by Electrical Components International, Inc., St. Louis, MO (US)
Filed on Jun. 29, 2022, as Appl. No. 17/853,188.
Prior Publication US 2024/0005471 A1, Jan. 4, 2024
Int. Cl. G06T 7/00 (2017.01); G06V 10/25 (2022.01); G06V 10/764 (2022.01); G06V 10/77 (2022.01); G06V 10/774 (2022.01); H03M 7/30 (2006.01); H04N 7/18 (2006.01); H04N 23/56 (2023.01); H03M 3/00 (2006.01); H03M 7/32 (2006.01)
CPC G06T 7/0004 (2013.01) [G06V 10/25 (2022.01); G06V 10/764 (2022.01); G06V 10/7715 (2022.01); G06V 10/7747 (2022.01); H04N 7/183 (2013.01); H04N 23/56 (2023.01); G06T 2207/30164 (2013.01); H03M 3/412 (2013.01); H03M 7/302 (2013.01)] 29 Claims
OG exemplary drawing
 
1. A method performed by an inspection system, the method comprising:
using a camera of an inspection station to output a video stream including captured product images of a product in a field of view of the camera, wherein a stand of the inspection station is configured to position the camera, and the product includes one or more product features;
using an inspection station computer system of the inspection station to receive the video stream;
using the inspection station computer system to convey a captured product image of the captured product images;
using a server computer system to receive the conveyed captured product image;
using a machine learning (ML) model of the server computer system to detect one or more objects in the captured product image and provide, for each of the detected one or more objects, an identification of a class of the detected object and an identification of a region of the detected object in the captured product image, wherein the class of the detected object is either an acceptable product feature class or an unacceptable product feature class;
using the inspection station computer system to receive, for each of the detected one or more objects, the identification of the class of the detected object and the identification of the region of the detected object in the captured product image; and
using the inspection station computer system to cause a display of the inspection station to display an enhanced product image that includes the conveyed captured product image to which the identification of the class of the detected object and the identification of the region of the detected object in the captured product image for each of the detected one or more objects have been added.