Apparatus and methods for generating denoising model
Described herein is a method for training a denoising model. The method includes obtaining a first set of simulated images based on design patterns. The simulated images may be clean and can be added with noise to generate noisy simulated images. The simulated clean and noisy images are used as training data to generate a denoising model.
1 . A method for training a denoising model, the method comprising:
converting a design pattern to a first set of simulated images; and
training the denoising model using training data comprising the first set of simulated images, an image noise, and captured images, wherein the denoising model is operable to generate a denoised image of an input image.
2 . The method of claim 1 , wherein the converting the design patterns to the first set of simulated images comprises:
executing a trained model configured to use the design patterns as an input to generate the simulated images.
3 . The method of claim 2 , wherein the trained model is trained based on the design patterns and the captured images of a patterned substrate, each captured image being associated with a design pattern.
4 . The method of claim 3 , wherein the captured images are SEM images acquired via a scanning electron microscope (SEM).
5 . The method of claim 4 , further comprising adding the image noise to the first set of simulated images to generate a second set of simulated images, wherein the image noise is extracted from the captured images of the patterned substrate.
6 . The method of claim 2 , wherein the trained model comprises a first machine learning model.
7 . The method of claim 6 , wherein the trained model comprises a convolutional neural network or a deep convolutional neural network trained using a generative adversarial network training method.
8 . The method of claim 7 , wherein the trained model is a generative model configured to generate a simulated SEM image for a given design pattern.
9 . The method of claim 1 , wherein the image noise is a Gaussian noise, white noise, salt and paper noise characterized by user specified parameters.
10 . The method of claim 1 , wherein the denoising model comprises a second machine learning model.
11 . The method of claim 1 , wherein the design patterns are in Graphic Data Signal (GDS) file format.
12 . The method of claim 1 , further comprising:
obtaining a captured SEM image of a patterned substrate; and
executing the trained denoising model using the captured SEM image as the input image to generate a denoised SEM image.
13 . The method of claim 1 , further comprising updating the denoising model based on a captured image of a patterned substrate.
14 . One or more non-transitory, computer-readable media storing instructions, that when executed by a processor, causes the processor to perform operations comprising:
converting a design pattern to a first set of simulated images; and
training a denoising model using training data comprising the first set of simulated images, an image noise, and captured images, wherein the denoising model is operable to generate a denoised image of an input image.
15 . A system comprising:
e-beam optics configured to capture an image of a patterned substrate; and
one or more processors configured to:
execute a denoising model using the captured image as input to generate a denoised image of the patterned substrate, the denoising model having been trained using training data comprising a set of simulated images converted from a design pattern, an image noise, and ground truth data comprising captured images.
16 . The system of claim 15 , wherein the denoising model is a convolutional neural network.
17 . The system of claim 15 , the one or more processors is further configured to:
execute a trained model using the design pattern provided in Graphic Data Signal (GDS) file format to generate the set of simulated images.
18 . The system of claim 15 , wherein the one or more processors is further configured to:
update the denoising model based on the captured image of the patterned substrate.
19 . The system of claim 15 , wherein the one or more processors is further configured to:
update one or more parameters of the denoising model based on a comparison of the denoised image with a reference denoised image.