US 11,982,628 B2
System and method for detecting defects on imaged items
Yonatan Hyatt, Tel-Aviv (IL); Gil Zohav, Beer Sheva (IL); Ran Ginsburg, Ramat Gan (IL); and Dagan Eshar, Tel Aviv (IL)
Assigned to INSPEKTO A.M.V. LTD., Ramat Gan (IL)
Appl. No. 17/053,809
Filed by INSPEKTO A.M.V. LTD., Ramat Gan (IL)
PCT Filed May 10, 2019, PCT No. PCT/IL2019/050532
§ 371(c)(1), (2) Date Nov. 9, 2020,
PCT Pub. No. WO2019/215746, PCT Pub. Date Nov. 14, 2019.
Claims priority of provisional application 62/669,403, filed on May 10, 2018.
Claims priority of application No. 259285 (IL), filed on May 10, 2018.
Prior Publication US 2021/0233229 A1, Jul. 29, 2021
Int. Cl. G06T 7/00 (2017.01); G01N 21/88 (2006.01); G06V 10/764 (2022.01); G06V 20/64 (2022.01)
CPC G01N 21/8851 (2013.01) [G06T 7/0004 (2013.01); G06V 10/764 (2022.01); G01N 2203/0062 (2013.01); G06T 2207/20081 (2013.01); G06V 20/64 (2022.01)] 16 Claims
OG exemplary drawing
 
1. A method for obtaining a prediction for an imaged item, the method comprising:
receiving a variable number of images of a same-type item of a known class and an image of the same-type item of an unknown class;
calculating a predetermined size representation of the received images by comparing the received images to extract attributes from the received images, and using the attributes to produce the predetermined size representation;
inputting the predetermined size representation to a machine learning predictor to obtain a prediction regarding the item of the unknown class; and
controlling a device based on the prediction.