Mark detecting apparatus, mark learning apparatus, substrate processing apparatus, mark detecting method, and manufacturing method of article

Patent metadata

Field	Value
Publication number	US-12481229-B2
Application number	US-202217736254-A
Country	US
Kind code	B2
Filing date	May 4, 2022
Priority date	May 14, 2021
Publication date	Nov 25, 2025
Grant date	Nov 25, 2025

Abstract

A mark detecting apparatus includes an imaging unit configured to generate an alignment mark image by imaging of an alignment mark on an object, a detecting unit configured to detect the alignment mark in the alignment mark image, and an adjusting unit configured to adjust a parameter relating to the imaging, based on a learning model generated by learning using the alignment mark image in which the alignment mark could not be detected and a first parameter as the parameter for the imaging of the alignment mark image in which the alignment mark could be detected. The adjusting unit acquires a second parameter as a result of inference processing based on the learning model. The imaging unit performs the imaging in a state where the parameter is adjusted to the second parameter.

First claim

What is claimed is:

1 . A mark detecting apparatus comprising:
an imaging unit configured to generate an alignment mark image by imaging of an alignment mark on an object; a detecting unit configured to detect the alignment mark in the alignment mark image; and an adjusting unit configured to adjust a parameter relating to an imaging condition, the imaging condition includes at least one of a position of the alignment mark at an observation field of view, a wavelength of an observation light, and an illuminance of an observation light, wherein the adjusting unit is configured to adjust the parameter based on an output of a learning model which outputs the parameter inferred by inputting the alignment mark image imaged in an initial parameter, wherein the learning model is generated by learning using the alignment mark image in which the alignment mark could not be detected and a first parameter as the parameter for the imaging of the alignment mark image in which the alignment mark could be detected, wherein the adjusting unit acquires a second parameter as a result of inference processing based on the learning model the second parameter is output from the learning model, and wherein the imaging unit performs the imaging in a state where the parameter is adjusted from the initial parameter to the second parameter.

2 . The mark detecting apparatus according to claim 1 , further comprising a learning unit configured to learn to generate the learning model.

3 . The mark detecting apparatus according to claim 2 , wherein the learning unit performs the learning in a case where the alignment mark in the alignment mark image generated by the imaging could not be detected while the parameter is adjusted to the second parameter.

4 . The mark detecting apparatus according to claim 1 ,
wherein the adjusting unit is configured to adjust only an imaging condition that needs to be adjusted for the initial parameter.

5 . The mark detecting apparatus according to claim 4 , wherein the learning model outputs a position of the alignment mark at an observation field of view, a wavelength of an observation light, and an illuminance of an observation light as the second parameter,
wherein the adjusting unit is configured to adjust only an imaging condition that needs to be adjusted for the initial parameter.

6 . A mark detecting method comprising the steps of:
generating an alignment mark image by imaging of an alignment mark on an object; detecting the alignment mark in the alignment mark image; and adjusting a parameter relating to an imaging condition, the imaging condition includes at least one of a position of the alignment mark at an observation field of view, a wavelength of an observation light, and an illuminance of an observation light, wherein the adjusting step includes adjusting the parameter based on an output of a learning model which outputs the parameter inferred by inputting the alignment mark image imaged in an initial parameter, wherein the learning model is generated by learning using the alignment mark image in which the alignment mark could not be detected and a first parameter as the parameter for the imaging of the alignment mark image in which the alignment mark could be detected, wherein the adjusting step acquires a second parameter as a result of inference processing based on the learning model, the second parameter is output from the learning model, and wherein the imaging is performed in a state where the parameter is adjusted from the initial parameter to the second parameter.

7 . A storage medium storing a program that causes a computer to execute a mark detecting method,
wherein the mark detecting method includes the steps of: generating an alignment mark image by imaging of an alignment mark on an object; detecting the alignment mark in the alignment mark image; and adjusting a parameter relating to an imaging condition, the imaging condition includes at least one of a position of the alignment mark at an observation field of view, a wavelength of an observation light, and an illuminance of an observation light, wherein the adjusting step includes adjusting the parameter based on an output of a learning model which outputs the parameter inferred by inputting the alignment mark image imaged in an initial parameter, wherein the learning model is generated by learning using the alignment mark image in which the alignment mark could not be detected and a first parameter as the parameter for the imaging of the alignment mark image in which the alignment mark could be detected, wherein the adjusting step acquires a second parameter as a result of inference processing based on the learning model, the second parameter is output from the learning model and wherein the imaging is performed in a state where the parameter is adjusted from the initial parameter to the second parameter.

8 . A substrate processing apparatus comprising:
a mark detecting apparatus; and a processing unit configured to process a substrate positioned by using an alignment mark detected by the mark detecting apparatus, wherein the mark detecting apparatus includes: an imaging unit configured to generate an alignment mark image by imaging of an alignment mark on an object; a detecting unit configured to detect the alignment mark in the alignment mark image; and an adjusting unit configured to adjust a parameter relating to an imaging condition, the imaging condition includes at least one of a position of the alignment mark at an observation field of view, a wavelength of an observation light, and an illuminance of an observation light, wherein the adjusting unit is configured to adjust the parameter based on an output of a learning model which outputs the parameter inferred by inputting the alignment mark image imaged in an initial parameter, wherein the learning model is generated by learning using the alignment mark image in which the alignment mark could not be detected and a first parameter as the parameter for the imaging of the alignment mark image in which the alignment mark could be detected, wherein the adjusting unit acquires a second parameter as a result of inference processing based on the learning model, the second parameter is output from the learning model and wherein the imaging unit performs the imaging in a state where the parameter is adjusted from the initial parameter to the second parameter.

9 . A manufacturing method of an article, the manufacturing method comprising the steps of:
processing a substrate using a substrate processing apparatus; and manufacturing the article from a processed substrate, wherein the substrate processing apparatus includes: a mark detecting apparatus; and a processing unit configured to process a substrate positioned by using an alignment mark detected by the mark detecting apparatus, wherein the mark detecting apparatus includes: an imaging unit configured to generate an alignment mark image by imaging of an alignment mark on an object; a detecting unit configured to detect the alignment mark in the alignment mark image; and an adjusting unit configured to adjust a parameter relating to the imaging, based on a learning model generated by learning using the alignment mark image in which the alignment mark could not be detected and a first parameter as the parameter for the imaging of the alignment mark image in which the alignment mark could be detected, wherein the adjusting unit acquires a second parameter as a result of inference processing based on the learning model, and wherein the imaging unit performs the imaging in a state where the parameter is adjusted to the second parameter.

Assignees

• Canon Kk

Inventors

• Yamamoto Masashi
• Suzuki Tohru
• Neya Hisatoshi
• Kurosawa Yoshiaki
• Yoneda Shingo
• Hioki Masanori

Classifications

• G03F9/7092

  Signal processing · CPC title

• G03F7/70491

  Information management, e.g. software; Active and passive control, e.g. details of controlling exposure processes or exposure tool monitoring processes · CPC title

• G03F9/7049

  Technique, e.g. interferometric · CPC title

• G03F9/7088 Primary

  Alignment mark detection, e.g. TTR, TTL, off-axis detection, array detector, video detection · CPC title

• G03F9/7046 Primary

  Strategy, e.g. mark, sensor or wavelength selection · CPC title