Inspection apparatus and measurement apparatus

1. An inspection apparatus that inspects an inspection image by comparison with a reference image, the inspection apparatus comprising:

an image distortion estimation unit that estimates a distortion amount between the reference image and the inspection image;

an image distortion correction unit that corrects an inspection image and/or a reference image using an estimated distortion amount; and

an inspection unit that performs inspection using a corrected inspection image and a reference image or an inspection image and a corrected reference image,

wherein the image distortion estimation unit estimates a distortion amount in which only distortion occurring in an entire image can be corrected by adjustment of a correction condition.

2. The inspection apparatus according to claim 1 , wherein

the image distortion estimation unit

estimates a first distortion amount by using, pre-processing on an inspection image and a reference image, processing content of which can be changed based on a correction condition, and an inspection image and a reference image processed by the pre-processing as inputs, and

performs post-processing defined in a correction condition on the first distortion amount, and sets a second distortion amount as the estimated distortion amount.

3. The inspection apparatus according to claim 2 , wherein

at least pre-processing defined in a correction condition is downsample processing for reducing image sizes of an inspection image and a reference image, and the post-processing is upsample processing for processing an estimated distortion amount into a form that can be input to an image distortion correction unit, and

by adjusting magnification of the downsample processing and the upsample processing and/or a filter size of a smoothing filter that smooths an inspection image and a reference image as correction conditions, the image distortion estimation unit estimates a distortion amount except for a local and high-frequency image feature.

4. The inspection apparatus according to claim 2 , wherein the image distortion estimation unit includes processing of evaluating similarity between an inspection image and a reference image and a variation in distortion amount in a region near the first distortion amount, and estimates a distortion amount to reduce a variation in distortion amount in a region near the estimated distortion amount while increasing similarity between an inspection image and a reference image based on a correction condition.

5. The inspection apparatus according to claim 1 , comprising a machine learning unit that creates a model for estimating a distortion amount between the reference image and the inspection image by using a learning inspection image and a learning reference image corresponding to the learning inspection image as a teacher,

wherein the image distortion estimation unit estimates a distortion amount using a model created by the machine learning unit.

6. The inspection apparatus according to claim 5 , wherein

the image distortion estimation unit

estimates a first distortion amount from pre-processing on an inspection image and a reference image, processing content of which can be changed based on a correction condition, and an inspection image and a reference image processed by the pre-processing by using a model created by the machine learning unit, and

performs post-processing defined in a correction condition on the first distortion amount, and sets a second distortion amount as the estimated distortion amount.

7. The inspection apparatus according to claim 6 , wherein

at least pre-processing defined in a correction condition is downsample processing for reducing image sizes of an inspection image and a reference image, and the post-processing is upsample processing for processing an estimated distortion amount into a form that can be input to an image distortion correction unit, and

by adjusting magnification of the downsample processing and the upsample processing and/or a filter size of a smoothing filter that smooths an inspection image and a reference image as correction conditions, the image distortion estimation unit estimates a distortion amount except for a local and high-frequency image feature.

8. A measurement apparatus that measures a length of a sample using an inspection image, the measurement apparatus comprising:

an image distortion estimation unit that estimates a distortion amount between a reference image and the inspection image based on the reference image and the inspection image;

an image distortion correction unit that corrects an inspection image using an estimated distortion amount; and

a measurement unit that measures a length of a sample using a corrected inspection image,

wherein the image distortion estimation unit estimates a distortion amount in which only distortion occurring in an entire image can be corrected by adjustment of a correction condition.

9. The measurement apparatus according to claim 8 , wherein

the image distortion estimation unit

estimates a first distortion amount by using, pre-processing on an inspection image and a reference image, processing content of which can be changed based on a correction condition, and an inspection image and a reference image processed by the pre-processing as inputs, and

performs post-processing defined in a correction condition on the first distortion amount, and sets a second distortion amount as the estimated distortion amount.

10. The measurement apparatus according to claim 9 , wherein

at least pre-processing defined in a correction condition is downsample processing for reducing image sizes of an inspection image and a reference image, and the post-processing is upsample processing for processing an estimated distortion amount into a form that can be input to an image distortion correction unit, and

by adjusting magnification of the downsample processing and the upsample processing and/or a filter size of a smoothing filter that smooths an inspection image and a reference image as correction conditions, the image distortion estimation unit estimates a distortion amount except for a local and high-frequency image feature.

11. The measurement apparatus according to claim 9 , wherein the image distortion estimation unit includes processing of evaluating similarity between an inspection image and a reference image and a variation in distortion amount in a region near the first distortion amount, and estimates a distortion amount to reduce a variation in distortion amount in a region near the estimated distortion amount while increasing similarity between an inspection image and a reference image based on a correction condition.

12. The measurement apparatus according to claim 8 , comprising a machine learning unit that creates a model for estimating a distortion amount between the reference image and the inspection image by using a learning inspection image and a learning reference image corresponding to the learning inspection image as a teacher,

wherein the image distortion estimation unit estimates a distortion amount using a model created by the machine learning unit.

13. The measurement apparatus according to claim 12 , wherein

the image distortion estimation unit

estimates a first distortion amount from pre-processing on an inspection image and a reference image, processing content of which can be changed based on a correction condition, and an inspection image and a reference image processed by the pre-processing by using a model created by the machine learning unit, and

performs post-processing defined in a correction condition on the first distortion amount, and sets a second distortion amount as the estimated distortion amount.

14. The measurement apparatus according to claim 13 , wherein

at least pre-processing defined in a correction condition is downsample processing for reducing image sizes of an inspection image and a reference image, and the post-processing is upsample processing for processing an estimated distortion amount into a form that can be input to an image distortion correction unit, and

by adjusting magnification of the downsample processing and the upsample processing and/or a filter size of a smoothing filter that smooths an inspection image and a reference image as correction conditions, the image distortion estimation unit estimates a distortion amount except for a local and high-frequency image feature.