Processing apparatus, measurement apparatus, lithography apparatus, method of manufacturing article, model, processing method, measurement method, generation method, and generation apparatus
The present invention provides a processing apparatus comprising: a generator configured to generate, based on image data of a measurement target, position information of the measurement target in a first direction; and a determinator configured to determine, based on a feature quantity of the image data related to a second direction different from the first direction, confidence of the position information of the measurement target generated by the generator.
1. A processing apparatus comprising:
a generator configured to generate, based on image data of a measurement target, position information of the measurement target in a first direction; and
a determinator configured to determine, based on a feature quantity of the image data of the measurement target related to a second direction different from the first direction, confidence of the position information of the measurement target in the first direction generated by the generator,
wherein the measurement target is a mark that is detected to obtain the position information in the first direction.
2. The processing apparatus according to claim 1 , wherein the determinator determines the confidence from the feature quantity by using a model configured to obtain the confidence based on the feature quantity.
3. The processing apparatus according to claim 2 , wherein the model uses the feature quantity as an input and outputs a probability distribution of an error estimated to be included in the position information generated by the generator, and
the determinator determines, as the confidence, a variance of the probability distribution output from the model.
4. The processing apparatus according to claim 2 , further comprising:
a machine learning controller configured to generate the model by performing machine learning by using the feature quantity as input data and a measurement value of an error, included in the position information generated by the generator, as training data.
5. The processing apparatus according to claim 3 , wherein the measurement value of the error is obtained by a difference between the position information of the measurement target generated by the generator and position information of the measurement target measured by an external inspection apparatus.
6. The processing apparatus according to claim 2 , further comprising:
a machine learning controller configured to generate the model by performing unsupervised machine learning by using the feature quantity as input data.
7. The processing apparatus according to claim 1 , further comprising:
a setting unit configured to set, based on the confidence determined by the determinator, a setting related to a use of the position information of the measurement target in the first direction generated by the generator.
8. The processing apparatus according to claim 7 , wherein the setting unit sets, based on the confidence determined by the determinator, whether to use the position information of the measurement target in the first direction generated by the generator.
9. The processing apparatus according to claim 7 , wherein the setting unit sets, based on the confidence determined by the determinator, a weight added to the position information of the measurement target in the first direction generated by the generator.
10. The processing apparatus according to claim 1 , wherein the feature quantity obtained from the image data related to the second direction includes a plurality of values corresponding to a plurality of positions in the second direction.
11. The processing apparatus according to claim 10 , wherein the plurality of values include a plurality of integrated values, and each of the plurality of integrated values is an integrated value of signal values of pixels whose positions in the second direction are equal to each other among a plurality of pixels forming the image data.
12. The processing apparatus according to claim 10 , wherein the plurality of values include signal values of a plurality of pixels on a line parallel to the second direction among a plurality of pixels forming the image data.
13. The processing apparatus according to claim 10 , wherein the plurality of values are obtained by processing signal values of a plurality of pixels on a line parallel to the second direction among a plurality of pixels forming the image data.
14. The processing apparatus according to claim 10 , wherein the plurality of values are obtained by performing basis transformation on a plurality of integrated values, and each of the plurality of integrated values is an integrated value of signal values of pixels whose positions in the second direction are equal to each other among a plurality of pixels forming the image data.
15. The processing apparatus according to claim 10 , wherein the plurality of values are obtained by performing basis transformation on signal values of a plurality of pixels on a line a parallel to the second direction among a plurality of pixels forming the image data.
16. The processing apparatus according to claim 10 , wherein the plurality of values are obtained by performing basis transformation on a plurality of values obtained by processing signal values of a plurality of pixels on a line parallel to the second direction among a plurality of pixels forming the image data.
17. A measurement apparatus that measures a position of a measurement target, comprising:
an image capturing device configured to generate image data by capturing an image of the measurement target; and
a processing apparatus defined in claim 1 and configured to process the image data obtained by the image capturing device,
wherein based on the image data obtained by the image capturing device, the processing apparatus generates position information of a measurement target and determines confidence of the position information.
18. A lithography apparatus that transfers a pattern of an original onto a substrate, comprising:
a measurement apparatus defined in claim 17 ; and
a controller configured to control, based on an output of the measurement apparatus, alignment of the substrate and the original.
19. The lithography apparatus according to claim 18 , wherein the controller adjusts a completion time of the alignment in accordance with confidence output from a processing apparatus.
20. A method of manufacturing an article, comprising:
forming a pattern on a substrate by using a lithography apparatus defined in claim 18 ;
processing the substrate which has undergone the forming; and
obtaining the article from the substrate which has undergone the processing.
21. A model that generates information indicating confidence of position information of a measurement target in a first direction generated based on image data of the measurement target,
wherein the model is configured to generate the information by determining, based on a feature quantity of the image data of the measurement target related to a second direction different from the first direction, the confidence of the position information of the measurement target in the first direction, and
wherein the measurement target is a mark that is detected to obtain the position information in the first direction.
22. A processing method of image data of a measurement target for measuring a position, comprising:
generating, based on the image data of the measurement target, position information of the measurement target in a first direction; and
determining, based on a feature quantity of the image data of the measurement target related to a second direction different from the first direction, confidence of the position information of the measurement target in the first direction generated in the generating,
wherein the measurement target is a mark that is detected to obtain the position information in the first direction.
23. A measurement method for measuring a position of a measurement target, comprising:
capturing an image of the measurement target to generate image data;
generating, based on the image data of the measurement target, position information of the measurement target in a first direction; and
determining, based on a feature quantity of the image data of the measurement target related to a second direction different from the first direction, confidence of the position information of the measurement target in the first direction generated in the generating,
wherein the measurement target is a mark that is detected to obtain the position information in the first direction.
24. A generation method of generating a model for determining confidence of position information of a measurement target in a first direction generated based on image data of the measurement target, comprising:
obtaining a feature quantity of the image data of the measurement target related to a second direction different from the first direction;
obtaining a measurement value of an error included in the position information of the measurement target in the first direction; and
generating a model by performing machine learning by setting the feature quantity as input data of the model and setting the measurement value of the error as training data,
wherein the measurement target is a mark that is detected to obtain the position information in the first direction.
25. A generation apparatus that generates a model for determining confidence of position information of a measurement target in a first direction generated based on image data of the measurement target,
wherein a feature quantity of the image data of the measurement target related to a second direction different from the first direction and a measurement value of an error included in the position information of the measurement target in the first direction are obtained,
the model is generated by performing machine learning by setting the feature quantity as input data of the model and the measurement value of the error as training data, and
wherein the measurement target is a mark that is detected to obtain the position information in the first direction.