CN-115343923-B - Mark detecting device, mark learning device, and substrate processing device

CN115343923BCN 115343923 BCN115343923 BCN 115343923BCN-115343923-B

Abstract

Disclosed are a mark detection device, a mark learning device, and a substrate processing device. The mark detection device includes an imaging unit configured to generate an alignment mark image by imaging an alignment mark on an object, a detection unit configured to detect the alignment mark in the alignment mark image, and an adjustment unit configured to adjust a parameter related to imaging based on a learning model generated by learning using the alignment mark image in which the alignment mark cannot be detected and a first parameter that is a parameter for imaging the alignment mark image in which the alignment mark can be detected. The adjustment unit obtains a second parameter as a result of the inference process based on the learning model. The imaging unit performs imaging in a state where the parameter is adjusted to the second parameter.

Inventors

YAMAMOTO MASASHI
TETSUYA SUZUKI
Gengu Shangren
AKIRA KUROSAWA
YONEDA SHINGO
HIOKI MAKOTO

Assignees

佳能株式会社

Dates

Publication Date: 20260508
Application Date: 20220510
Priority Date: 20210514

Claims (9)

1. A mark detection device comprising: an imaging unit configured to generate an alignment mark image by imaging an alignment mark on an object; a detection unit configured to detect an alignment mark in the alignment mark image, and An adjustment unit configured to adjust a parameter related to an imaging condition including at least one of a position of an alignment mark in an observation field of view, a wavelength of imaging light, and illuminance of the imaging light, Wherein the adjustment unit is configured to adjust the parameters based on an output of a learning model that outputs parameters estimated by inputting an alignment mark image imaged using the initial parameters, Wherein the learning model is generated by learning using an alignment mark image in which an alignment mark cannot be detected and a first parameter which is a parameter for imaging the alignment mark image in which the alignment mark can be detected, Wherein the adjusting unit obtains a second parameter as a result of the learning model-based inference process, the second parameter being output from the learning model, and Wherein the imaging unit performs imaging in a state in which the parameter is adjusted from the initial parameter to the second parameter.
2. The mark detection device of claim 1, wherein the learning model outputs a position of the alignment mark in the observation field, a wavelength of the imaging light, and illuminance of the imaging light as the second parameters, Wherein the adjustment unit is configured to adjust only the required imaging conditions of the initial parameters that should be adjusted.
3. The mark detection device according to claim 1, further comprising a learning unit configured to learn to generate a learning model.
4. The mark detection device according to claim 3, wherein the learning unit performs learning in a case where an alignment mark in an alignment mark image generated by imaging while adjusting the parameter to the second parameter cannot be detected.
5. A method of detecting a label, comprising the steps of: Generating an alignment mark image by imaging an alignment mark on an object; detecting an alignment mark in the alignment mark image, and Adjusting parameters related to imaging conditions including at least one of a position of an alignment mark in an observation field of view, a wavelength of imaging light, and illuminance of the imaging light, Wherein the adjusting step includes adjusting the parameters based on an output of a learning model that outputs parameters estimated by inputting an alignment mark image imaged using the initial parameters, Wherein the learning model is generated by learning using an alignment mark image in which an alignment mark cannot be detected and a first parameter which is a parameter for imaging the alignment mark image in which the alignment mark can be detected, Wherein the adjusting step takes a second parameter as a result of the learning model-based inference process, the second parameter being output from the learning model, and Wherein imaging is performed in a state in which the parameter is adjusted from the initial parameter to the second parameter.
6. The mark detection method according to claim 5, wherein the learning model outputs a position of the alignment mark in the observation field, a wavelength of the imaging light, and illuminance of the imaging light as the second parameters, Wherein the adjusting step adjusts only the required imaging conditions in the initial parameters that should be adjusted.
7. A computer-readable storage medium storing a computer program for causing a computer to execute the mark detection method according to claim 5 or 6.
8. A substrate processing apparatus comprising: The mark detection device according to any one of claims 1 to 4, and And a processing unit configured to process the substrate positioned by using the alignment mark detected by the mark detecting device.
9. A method of manufacturing an article, the method comprising the steps of: processing a substrate using the substrate processing apparatus according to claim 8, and Articles are manufactured from the processed substrates.

Description

Mark detecting device, mark learning device, and substrate processing device Technical Field The present invention relates to a technique for detecting an alignment mark from image data obtained by imaging the alignment mark. More specifically, the present invention relates to a mark detection device, a mark learning device, a substrate processing device, a mark detection method, and a method of manufacturing an article. Background For example, the above alignment mark is detected in an exposure apparatus for manufacturing a semiconductor device or a display device using a photolithography technique. The exposure apparatus projects a pattern of a master (such as a mask and a reticle) onto a substrate (such as a wafer and a glass plate) via a projection optical system and converts the pattern. When transferring a plurality of layers having different master patterns on the same substrate, highly accurate alignment is required to prevent the actual transfer position from deviating from the target transfer position. By using image data (alignment mark image) obtained by imaging the alignment mark, the position of the alignment mark is detected by alignment and corrected based on the result. Japanese patent laid-open No. ("JP") 2003-338455 discloses a method of detecting the position of an alignment mark in an alignment mark image by template matching, which is an optimization method using automatic deformation and brightness (brightness) change of a template corresponding to deformation of the alignment mark. This method self-learns to use the optimized template for the next match and improves the detection rate of the alignment marks. But even the method disclosed in JP 2003-338455 requires an operator to first manually adjust the alignment mark position to the imaging position, adjust a plurality of parameters such as the wavelength and illuminance (illuminence) of imaging light, and maintain a good imageable state of the alignment mark. At this time, the operator takes time to determine the combination of parameters to be used. Since the state of the alignment mark in the alignment mark image is changed according to the physical characteristics of the resist applied to the substrate, an operator needs sufficient knowledge to determine the combination. Some exposure devices may automatically adjust parameters, but this type of exposure device automatically and sequentially changes the combination of parameters and determines whether the combination is appropriate. Therefore, it takes a long time to determine the combination of parameters to be used. Disclosure of Invention The present invention provides an alignment mark detection device and the like capable of automatically and quickly adjusting imaging-related parameters to obtain a good alignment mark image. The mark detection device according to one aspect of the present invention includes an imaging unit configured to generate an alignment mark image by imaging an alignment mark on an object, a detection unit configured to detect the alignment mark in the alignment mark image, and an adjustment unit configured to adjust a parameter related to imaging based on a learning model generated by learning using the alignment mark image in which the alignment mark cannot be detected and a first parameter that is a parameter for imaging the alignment mark image in which the alignment mark can be detected. The adjustment unit obtains a second parameter as a result of the inference process based on the learning model. The imaging unit performs imaging in a state where the parameter is adjusted to the second parameter. A mark detection method corresponding to the mark detection device and a substrate processing device and an article manufacturing method each using the mark detection device also constitute other aspects of the present invention. A mark learning apparatus according to another aspect of the present invention includes an acquisition unit configured to acquire an alignment mark image that is an image in which an alignment mark in the image cannot be detected, which is generated by imaging an alignment mark on an object, and a first parameter that is a parameter related to imaging in imaging of the alignment mark image in which the alignment mark can be detected, and a learning unit configured to generate a learning model for use with an inference process, which outputs a second parameter that is a parameter by learning using the acquired alignment mark image and the first parameter. Other features of the present invention will become apparent from the following description of exemplary embodiments with reference to the accompanying drawings. Drawings Fig. 1 is a block diagram illustrating a configuration of a mark detection device according to a first embodiment. Fig. 2 illustrates the relation between the parameter to be adjusted and the adjustment unit according to the first embodiment. Fig. 3 is a flowchart illustrating a parameter inference process ac