Generating high resolution images from low resolution images for semiconductor applications

Patent metadata

Field	Value
Publication number	US-2017193680-A1
Application number	US-201715396800-A
Country	US
Kind code	A1
Filing date	Jan 2, 2017
Priority date	Jan 4, 2016
Publication date	Jul 6, 2017
Grant date	—

Abstract

Methods and systems for generating a high resolution image for a specimen from one or more low resolution images of the specimen are provided. One system includes one or more computer subsystems configured for acquiring one or more low resolution images of a specimen. The system also includes one or more components executed by the one or more computer subsystems. The one or more components include a model that includes one or more first layers configured for generating a representation of the one or more low resolution images. The model also includes one or more second layers configured for generating a high resolution image of the specimen from the representation of the one or more low resolution images.

First claim

What is claimed is:

1 . A system configured to generate a high resolution image for a specimen from one or more low resolution images of the specimen, comprising:
one or more computer subsystems configured for acquiring one or more low resolution images of a specimen; and one or more components executed by the one or more computer subsystems, wherein the one or more components comprise:
a model, wherein the model comprises:
one or more first layers configured for generating a representation of the one or more low resolution images; and
one or more second layers configured for generating a high resolution image for the specimen from the representation of the one or more low resolution images.

2 . The system of claim 1 , wherein the model is a deep learning model.

3 . The system of claim 1 , wherein the model is a machine learning model.

4 . The system of claim 1 , wherein the model is a generative model.

5 . The system of claim 1 , wherein the model is a neural network.

6 . The system of claim 1 , wherein the model is a convolution neural network.

7 . The system of claim 1 , wherein the one or more first layers comprise one or more convolutional and pooling layers followed by an encoder, and wherein the one or more second layers comprise a decoder followed by one or more convolutional and pooling layers.

8 . The system of claim 7 , wherein the representation of the one or more low resolution images generated by the one or more first layers comprises a compact representation of the one or more low resolution images.

9 . The system of claim 1 , wherein the one or more first layers comprise one or more first convolutional and pooling layers, and wherein the one or more second layers comprise one or more second convolutional and pooling layers.

10 . The system of claim 1 , wherein the one or more first layers comprise a discrete cosine transform layer, wherein the one or more first and second layers comprise a deep belief net, and wherein the one or more second layers comprise an inverse discrete cosine transform layer.

11 . The system of claim 10 , wherein the representation of the one or more low resolution images comprises a hidden representation generated by the deep belief net.

12 . The system of claim 1 , wherein the one or more low resolution images are generated with a single mode of an imaging system.

13 . The system of claim 1 , wherein the one or more low resolution images are generated with multiple modes of an imaging system.

14 . The system of claim 1 , wherein the one or more low resolution images are generated with multiple values for a focus parameter of an imaging system.

15 . The system of claim 1 , wherein the one or more low resolution images are generated with multiple values for a spectral parameter of an imaging system.

16 . The system of claim 1 , wherein the one or more low resolution images are generated with multiple values for a polarization parameter of an imaging system.

17 . The system of claim 1 , wherein the one or more second layers are further configured for generating at least one additional high resolution image of the specimen from the representation of the one or more low resolution images, and wherein the high resolution image and the at least one additional high resolution image represent different images generated for the specimen with different modes of a high resolution imaging system.

18 . The system of claim 1 , wherein the high resolution image represents an image of the specimen generated by a high resolution electron beam system.

19 . The system of claim 1 , wherein the high resolution image represents design data for the specimen.

20 . The system of claim 1 , wherein the one or more low resolution images are generated by an electron beam based imaging system.

21 . The system of claim 1 , wherein the one or more low resolution images are generated by an optical based imaging system.

22 . The system of claim 1 , wherein the one or more low resolution images are generated by an inspection system.

23 . The system of claim 1 , wherein the specimen is a wafer.

24 . The system of claim 1 , wherein the specimen is a reticle.

25 . The system of claim 1 , wherein the one or more computer subsystems are further configured for verifying a defect detected in the one or more low resolution images, and wherein said verifying is performed using the high resolution image.

26 . The system of claim 1 , wherein the one or more computer subsystems are further configured for classifying a defect detected in the one or more low resolution images, and wherein said classifying is performed using the high resolution image.

27 . The system of claim 1 , wherein the one or more computer subsystems are further configured for detecting defects on the specimen based on a combination of the one or more low resolution images and the high resolution image.

28 . A system configured to generate a high resolution image for a specimen from one or more low resolution images of the specimen, comprising:
an imaging subsystem configured for generating one or more low resolution images of a specimen; one or more computer subsystems configured for acquiring the one or more low resolution images; and one or more components executed by the one or more computer subsystems, wherein the one or more components comprise:
a model, wherein the model comprises:
one or more first layers configured for generating a representation of the one or more low resolution images; and
one or more second layers configured for generating a high resolution image for the specimen from the representation of the one or more low resolution images.

29 . A non-transitory computer-readable medium, storing program instructions executable on one or more computer systems for performing a computer-implemented method for generating a high resolution image for a specimen from one or more low resolution images of the specimen, wherein the computer-implemented method comprises:
acquiring one or more low resolution images of a specimen; generating a representation of the one or more low resolution images by inputting the one or more low resolution images into one or more first layers of a model; and generating a high resolution image for the specimen based on the representation, wherein generating the high resolution image is performed by one or more second layers of the model, wherein said acquiring, said generating the representation, and said generating the high resolution image are performed by one or more computer systems, wherein one or more components are executed by the one or more computer systems, and wherein the one or more components comprise the model.

30 . A computer-implemented method for generating a high resolution image for a specimen from one or more low resolution images of the specimen, comprising:
acquiring one or more low resolution images of a specimen; generating a representation of the one or more low resolution images by inputting the one or more low resolution images into one or more first layers of a model; and generating a high resolution image for the specimen based on the representation, wherein generating the high resolution image is performed by one or more second layers of the model, wherein said acquiring, said generating the representation, and

Assignees

• Kla Tencor Corp

Inventors

• Zhang Jing
• Chen Grace Hsiu-Ling
• Bhaskar Kris
• Wells Keith
• Bai Nan
• Gu Ping
• Gao Lisheng

Classifications

• G06V30/19173

  Classification techniques · CPC title

• G06V10/82

  using neural networks · CPC title

• G06F18/2414

  Smoothing the distance, e.g. radial basis function networks [RBFN] · CPC title

• G06V10/454

  Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN] · CPC title

• G01N2201/12

  Circuits of general importance; Signal processing · CPC title