US 12,272,042 B2
Detection of defects using a computationally efficient segmentation approach
Elad Cohen, Beer Sheva (IL); Victor Egorov, Ramat Gan (IL); Ilan Ben-Harush, Rehovot (IL); and Rafael Bistritzer, Petach Tikva (IL)
Assigned to Applied Materials Israel Ltd., Rehovot (IL)
Filed by Applied Materials Israel Ltd., Rehovot (IL)
Filed on Dec. 29, 2021, as Appl. No. 17/565,273.
Prior Publication US 2023/0206417 A1, Jun. 29, 2023
Int. Cl. G06T 7/00 (2017.01); G06T 7/10 (2017.01)
CPC G06T 7/0004 (2013.01) [G06T 7/10 (2017.01)] 20 Claims
OG exemplary drawing
 
1. A system of examination of a semiconductor specimen, the system comprising a processor and memory circuitry (PMC) configured to:
obtain, for each given candidate defect of a plurality of candidate defects in an image of the semiconductor specimen acquired by an examination tool, a given area of the given candidate defect in the image;
obtain a reference image;
perform a segmentation of at least part of the reference image, the segmentation comprising, for each given candidate defect:
obtaining a given reference area in the reference image corresponding to the given area of said given candidate defect in the image according to a correspondence criterion, and
determining first reference areas in the reference image, wherein, for each given first reference area, first data informative of a pixel intensity of said given first reference area matches first data informative of a pixel intensity of the given reference area according to a first similarity criterion; and
for each given candidate defect:
for each given first reference area, compare second data informative of a pixel intensity of said given first reference area to second data informative of a pixel intensity of the given reference area;
select among the first reference areas, a plurality of second reference areas for which the comparison indicates a match according to a second similarity criterion;
obtain a plurality of second areas in the image, wherein each given second area corresponds to one of the second reference areas according to the correspondence criterion; and
use data informative of a pixel intensity of the second areas and data informative of a pixel intensity of the given area to determine whether the given candidate defect corresponds to a defect.