Image generation apparatus, inspection apparatus, and image generation method

1. An image generation apparatus that generates a substrate image for inspection regarding a defect on a substrate,

the substrate having a frame pattern formed on a surface thereof, the frame pattern being a unique pattern for each kind of a treatment recipe for the substrate,

the image generation apparatus comprising:

a controller having a processor and a memory, the memory storing instructions that, when executed by the processor, cause the processor to

estimate a region corresponding to the frame pattern in a substrate image of an inspection object based on an identification model, the identification model being acquired by machine learning in advance and for identifying an image of the frame pattern included in a substrate image;

erase the image of the frame pattern from the substrate image of the inspection object based on an estimation result by the region estimator to generate the substrate image for inspection; and

acquire the identification model by the machine learning in advance using a data set including a substrate image and information on presence or absence of the image of the frame pattern in the substrate image.

2. The image generation apparatus according to claim 1 , wherein

the substrate image included in the data set includes both a frameless substrate image being a substrate image relating to a substrate which is not formed with the frame pattern but has defects, and a framed substrate image being a substrate image made by combining a substrate image relating to a substrate which has a known frame pattern and is formed with no defects with the frameless substrate image.

3. The image generation apparatus according to claim 2 , wherein

the frame pattern is at least one of a region where semiconductor devices are not formed, a boundary line between the semiconductor devices, and patterns on surfaces of the semiconductor devices.

4. The image generation apparatus according to claim 2 , wherein

the defect is at least one of a portion not having a predetermined shape in a coating film, a flaw on the substrate, and a foreign matter on the substrate.

5. The image generation apparatus according to claim 2 , wherein

the machine learning in advance is deep learning.

6. The image generation apparatus according to claim 2 , configured as an inspection apparatus, the processor being further configured to determine a kind of a defect formed on an inspection object substrate based on the substrate image for inspection, wherein

the kind of the defect is determined using machine learning.

7. The image generation apparatus according to claim 1 , wherein

the frame pattern is at least one of a region where semiconductor devices are not formed, a boundary line between the semiconductor devices, and patterns on surfaces of the semiconductor devices.

8. The image generation apparatus according to claim 1 , wherein

the defect is at least one of a portion not having a predetermined shape in a coating film, a flaw on the substrate, and a foreign matter on the substrate.

9. The image generation apparatus according to claim 1 , wherein

the machine learning in advance is deep learning.

10. The image generation apparatus according to claim 1 , configured as an inspection apparatus, the processor is further configured to determine a kind of a defect formed on an inspection object substrate based on the substrate image for inspection, using machine learning, wherein

the kind of the defect is determined using machine learning.

11. An image generation method for generating a substrate image for inspection regarding a defect on a substrate,

the substrate having a frame pattern formed on a surface thereof, the frame pattern being a unique pattern for each kind of a treatment recipe for the substrate,

the image generation method comprising:

estimating a region corresponding to the frame pattern in a substrate image of an inspection object based on an identification model, the identification model being acquired by machine learning in advance and for identifying an image of the frame pattern included in a substrate image;

erasing the image of the frame pattern from the substrate image of the inspection object based on an estimation result at the estimating to generate the substrate image for inspection; and

acquiring the identification model by the machine learning in advance using a data set including a substrate image and information on presence or absence of the image of the frame pattern in the substrate image.

12. The image generation method according to claim 11 , wherein

the frame pattern is at least one of a region where semiconductor devices are not formed, a boundary line between the semiconductor devices, and patterns on surfaces of the semiconductor devices.

13. The image generation method according to claim 11 , wherein

the defect is at least one of a portion not having a predetermined shape in a coating film, a flaw on the substrate, and a foreign matter on the substrate.

14. The image generation method according to claim 11 , wherein

the machine learning in advance is deep learning.

15. The image generation method according to claim 11 , further comprising

determining a kind of a defect formed on an inspection object substrate based on the substrate image for inspection, wherein

the kind of the defect is determined using machine learning.