	US 12,243,213 B2
	Substrate inspection device, substrate inspection system, and substrate inspection method
Shuji Iwanaga, Sapporo (JP); and Tadashi Nishiyama, Koshi (JP)
Assigned to TOKYO ELECTRON LIMITED, Tokyo (JP)
Appl. No. 17/615,442
Filed by TOKYO ELECTRON LIMITED, Tokyo (JP)
PCT Filed May 28, 2020, PCT No. PCT/JP2020/021160 § 371(c)(1), (2) Date Nov. 30, 2021, PCT Pub. No. WO2020/246366, PCT Pub. Date Dec. 10, 2020.
Claims priority of application No. 2019-106292 (JP), filed on Jun. 6, 2019; and application No. 2020-074213 (JP), filed on Apr. 17, 2020.
Prior Publication US 2022/0237770 A1, Jul. 28, 2022
Int. Cl. G06T 7/00 (2017.01)

CPC G06T 7/0004 (2013.01) [G06T 2207/20084 (2013.01); G06T 2207/30148 (2013.01)]

15 Claims

1. A substrate inspection apparatus for inspecting a substrate, comprising:

a first control circuit; and

a second control circuit that is associated with a substrate inspection along with the first control circuit,

wherein the first control circuit is configured to:

acquire an estimated image of an inspection target substrate after a process by a substrate processing apparatus, based on an image estimation model created by machine learning by using a captured image before the process by the substrate processing apparatus and a captured image after the process by the substrate processing apparatus for each of a plurality of substrates, and a captured image of the inspection target substrate before the process by the substrate processing apparatus; and

determine presence or absence of a defect in the inspection target substrate, based on the captured image of the inspection target substrate after the process by the substrate processing apparatus and the estimated image of the inspection target substrate after the process by the substrate processing apparatus,

wherein the second control circuit is configured to:

create an image estimation model by machine learning by using the captured image before the process by the substrate processing apparatus and the captured image after the process by the substrate processing apparatus for each of the plurality of substrates; and

select an image set for model creation, which is a captured image set composed of a combination of the captured image before the process and the captured image after the process for each of the plurality of substrate, and

wherein the second control circuit is further configured to select the captured image set for model creation based on a degree of abnormality determined by using a correlation distribution between in-plane tendency of a pixel value in the captured image before the process and in-plane tendency of a pixel value in the captured image after the process.

10. A substrate inspection method of inspecting a substrate, the method comprising:

acquiring an estimated image of an inspection target substrate after a process by a substrate processing apparatus, based on an image estimation model created by machine learning by using a captured image before the process by the substrate processing apparatus and a captured image after the process by the substrate processing apparatus for each of a plurality of substrates, and a captured image of the inspection target substrate before the process by the substrate processing apparatus;

determining presence or absence of a defect in the inspection target substrate, based on a captured image of the inspection target substrate after the process by the substrate processing apparatus, and the estimated image of the inspection target substrate after the process by the substrate processing apparatus;

creating an image estimation model by machine learning by using the captured image before the process by the substrate processing apparatus and the captured image after the process by the substrate processing apparatus for each of the plurality of substrates; and

selecting an image set for model creation, which is a captured image set composed of a combination of the captured image before the process and the captured image after the process for each of the plurality of substrate,

wherein the selecting the image set for model creation includes selecting the captured image set for model creation based on a degree of abnormality determined by using a correlation distribution between in-plane tendency of a pixel value in the captured image before the process and in-plane tendency of a pixel value in the captured image after the process.

15. A non-transitory computer-readable recording medium recording a computer program for causing a computer to execute a process of inspecting a substrate,

wherein the process includes:

acquiring an estimated image of an inspection target substrate after the process by a substrate processing apparatus, based on an image estimation model created by machine learning by using a captured image before the process by the substrate processing apparatus and a captured image after the process by the substrate processing apparatus for each of a plurality of substrates, and a captured image of the inspection target substrate before the process by the substrate processing apparatus;

determining presence or absence of a defect in the inspection target substrate, based on the captured image of the inspection target substrate after the process by the substrate processing apparatus and the estimated image of the inspection target substrate after the process by the substrate processing apparatus;