US 12,079,982 B2
Object defect detection
Kevin Andrew Perkins, Champaign, IL (US); and Ashwini Kumar Kounduri, Urbana, IL (US)
Assigned to Yahoo Ad Tech LLC, New York, NY (US)
Filed by Verizon Media Inc., New York, NY (US)
Filed on Nov. 17, 2021, as Appl. No. 17/528,238.
Prior Publication US 2023/0153987 A1, May 18, 2023
Int. Cl. G06T 7/00 (2017.01); G06T 7/11 (2017.01); G06T 7/64 (2017.01)
CPC G06T 7/001 (2013.01) [G06T 7/11 (2017.01); G06T 7/64 (2017.01); G06T 2207/20081 (2013.01); G06T 2207/30164 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
executing, on a processor of a computing device, instructions that cause the computing device to perform operations, the operations comprising:
receiving an image depicting an object for evaluation to determine whether the object has a defect;
inputting the image into a segmentation model to generate a segmentation mask identifying an object region of interest of the object;
calculating an object region area of the object region of interest;
calculating a convex hull area of a convex hull encompassing the object region of interest;
determining a ratio of the object region area of the object region of interest to the convex hull area of the convex hull encompassing the same object region of interest; and
comparing the ratio to a threshold to determine whether the object has the defect or does not have the defect.