US 11,836,909 B2
Active learning of product inspection engine
Siddha Ganju, Santa Clara, CA (US); Elad Mentovich, Tel Aviv (IL); David Greenlaw, Palo Alto, CA (US); and Tony Altinis, Cupertino, CA (US)
Assigned to MELLANOX TECHNOLOGIES, LTD., Yokneam (IL)
Filed by Mellanox Technologies, Ltd., Yokneam (IL)
Filed on Jan. 26, 2022, as Appl. No. 17/584,914.
Prior Publication US 2023/0237635 A1, Jul. 27, 2023
Int. Cl. G06T 7/00 (2017.01); G06V 10/774 (2022.01); G06V 10/762 (2022.01); G06T 7/10 (2017.01)
CPC G06T 7/0004 (2013.01) [G06T 7/10 (2017.01); G06V 10/762 (2022.01); G06V 10/7747 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20092 (2013.01)] 22 Claims
OG exemplary drawing
 
1. A method for inspecting a product, the method comprising:
obtaining, by one or more processors, at least one inspection image of an at least partially fabricated product;
causing, by the one or more processors, the at least one inspection image to be processed by a product inspection engine, wherein the product inspection engine comprises a machine learning-trained model;
obtaining, by the one or more processors, an inspection result determined based on the processing of the at least one inspection image by the product inspection engine;
identifying, by the one or more processors, one or more training images from a plurality of images stored in an image database based at least in part on the at least one inspection image;
associating, by the one or more processors, automatically generated labeling data with the one or more training images based at least in part on the inspection result determined by the processing of the at least one inspection image; and
causing, by the one or more processors, training of the product inspection engine using the one or more training images and labeling data associated with the one or more training images.