公开(公告)号：US20180173839A1

公开(公告)日：2018-06-21

申请号：US15810898

申请日：2017-11-13

Applicant: KLA-Tencor Corporation

Inventor： Chao Fang ,  Mark D. Smith ,  Brian Duffy

IPC: G06F17/50 ,  G01B21/02 ,  G06T7/00 ,  G03F7/20

CPC classification number: G06F17/5081 ,  G01B21/02 ,  G03F7/705 ,  G03F7/70616 ,  G06F2217/82 ,  G06T7/0004 ,  G06T7/001 ,  G06T2200/04 ,  G06T2200/08 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/30148

Abstract: A metrology system includes a controller communicatively coupled to a metrology tool. The controller may generate a three-dimensional model of a sample, generate a predicted metrology image corresponding to a predicted analysis of the sample with the metrology tool based on the three-dimensional model, evaluate two or more candidate metrology recipes for extracting the metrology measurement from the one or more predicted metrology images, select, based on one or more selection metrics, a metrology recipe from the two or more candidate metrology recipes for extracting a metrology measurement from an image of the structure from the metrology tool, receive an output metrology image of a fabricated structure from the metrology tool based on a metrology measurement of the fabricated structure, and extract the metrology measurement associated with the fabricated structure from the output metrology image based on the metrology recipe.

公开(公告)号：US10769761B2

公开(公告)日：2020-09-08

申请号：US16019422

申请日：2018-06-26

Applicant: KLA-Tencor Corporation

Inventor： Saurabh Sharma ,  Amitoz Singh Dandiana ,  Mohan Mahadevan ,  Chao Fang ,  Amir Azordegan ,  Brian Duffy

IPC: G06T5/00 ,  G06T3/40

Abstract: Methods and systems for generating a high resolution image for a specimen from a low resolution image of the specimen are provided. One system includes one or more computer subsystems configured for acquiring a low resolution image 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 deep convolutional neural network that includes one or more first layers configured for generating a representation of the low resolution image. The deep convolutional neural network also includes one or more second layers configured for generating a high resolution image of the specimen from the representation of the low resolution image. The second layer(s) include a final layer configured to output the high resolution image and configured as a sub-pixel convolutional layer.

公开(公告)号：US20190005629A1

公开(公告)日：2019-01-03

申请号：US16019422

申请日：2018-06-26

Applicant: KLA-Tencor Corporation

Inventor： Saurabh Sharma ,  Amitoz Singh Dandiana ,  Mohan Mahadevan ,  Chao Fang ,  Amir Azordegan ,  Brian Duffy

IPC: G06T5/00

CPC classification number: G06T5/007 ,  G06T3/4053 ,  G06T2207/20084 ,  G06T2207/20208

Abstract: Methods and systems for generating a high resolution image for a specimen from a low resolution image of the specimen are provided. One system includes one or more computer subsystems configured for acquiring a low resolution image 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 deep convolutional neural network that includes one or more first layers configured for generating a representation of the low resolution image. The deep convolutional neural network also includes one or more second layers configured for generating a high resolution image of the specimen from the representation of the low resolution image. The second layer(s) include a final layer configured to output the high resolution image and configured as a sub-pixel convolutional layer.