US 12,333,695 B2
Sample observation system and image processing method
Naoaki Kondo, Tokyo (JP); Minoru Harada, Tokyo (JP); and Yohei Minekawa, Tokyo (JP)
Assigned to HITACHI HIGH-TECH CORPORATION, Tokyo (JP)
Appl. No. 17/802,161
Filed by Hitachi High-Tech Corporation, Tokyo (JP)
PCT Filed Jan. 8, 2021, PCT No. PCT/JP2021/000484
§ 371(c)(1), (2) Date Aug. 25, 2022,
PCT Pub. No. WO2021/176841, PCT Pub. Date Sep. 10, 2021.
Claims priority of application No. 2020-038745 (JP), filed on Mar. 6, 2020.
Prior Publication US 2023/0005123 A1, Jan. 5, 2023
Int. Cl. G06T 7/00 (2017.01); G06V 10/75 (2022.01)
CPC G06T 7/0002 (2013.01) [G06V 10/751 (2022.01); G06T 2207/10061 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30141 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A sample observation system comprising:
a scanning electron microscope; and
a calculator, wherein
the calculator:
(1) acquires a plurality of images captured by the scanning electron microscope;
(2) acquires, from the plurality of images, a learning defect image including a defect portion and a learning reference image not including the defect portion;
(3) calculates an estimation processing parameter by using the learning defect image and the learning reference image;
(4) acquires an inspection defect image including a defect portion; and
(5) estimates a pseudo reference image by using the estimation processing parameter and the inspection defect image, and
the process (3) includes:
(3A) aligning the learning defect image and the learning reference image based on a predetermined evaluation value to acquire an alignment amount;
(3B) cutting out a partial learning defect image from the learning defect image based on the alignment amount;
(3C) cutting out a partial learning reference image from the learning reference image based on the alignment amount; and
(3D) calculating the estimation processing parameter by using the partial learning defect image and the partial learning reference image.