Computer system, dimension measurement method, and storage medium

US2024200939A1 · US · A1

Patent metadata
FieldValue
Publication numberUS-2024200939-A1
Application numberUS-202117802673-A
CountryUS
Kind codeA1
Filing dateJun 14, 2021
Priority dateJun 14, 2021
Publication dateJun 20, 2024
Grant date

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

A computer system providing a function for: extracting, from image data of a semiconductor pattern, coordinate information of a base point for measuring a dimension of a desired location of the semiconductor pattern; and measuring the dimension using the coordinate information of the base point. The computer system includes a training device in which a pose estimation model for outputting coordinate information of at least two base points as a training result is implemented. The training device is trained in advance using teacher data having the image data of the semiconductor pattern as an input and the coordinate information of at least two base points as an output, and extracts, for new image data input into the training device, the coordinate information of at least two base points and a dimension.

First claim

Opening claim text (preview).

1 . A computer system for providing a function for: extracting, from image data of a semiconductor pattern, coordinate information about a base point for measuring a dimension of a desired location of the semiconductor pattern; and measuring the dimension using the coordinate information of the base point, the computer system comprising a training device in which a pose estimation model for outputting the coordinate information of at least two of the base points as a training result is implemented, wherein the training device is trained in advance using teacher data having image data of the semiconductor pattern as an input and the coordinate information of the at least two base points as an output, the computer system, with respect to new image data input into the training device, extracting the coordinate information of the at least two base points and the dimension. 2 . The computer system according to claim 1 , further comprising a storage medium having installed therein an image analysis tool having a function for calculating, through pixel computation, a distance between predetermined locations of the image data designated on a GUI, and a function for outputting coordinate information of the desired locations. 3 . The computer system according to claim 2 , further comprising a first software module for converting output data of the image analysis tool including the coordinate information, into annotation data constituting the teacher data. 4 . The computer system according to claim 2 , further comprising a second software module for, using output data of the image analysis tool including the coordinate information, and rule information input in advance, generating definition data of a skeleton structure of the pose estimation model. 5 . The computer system according to claim 1 , further comprising a display device functioning as a user interface for displaying the image data, wherein the display device displays, on the user interface, data in which the image data of the semiconductor pattern and the at least two extracted base points are overlapped. 6 . The computer system according to claim 5 , wherein the display device further displays, in an overlapped manner on the user interface, a skeleton structure of the semiconductor pattern composed of a plurality of connections of a line segment connecting the at least two base points. 7 . The computer system according to claim 1 , wherein the image data of the semiconductor pattern is a cross-sectional image obtained by a charged particle beam apparatus. 8 . A dimension measurement method comprising, using a computer system, extracting, from image data of a semiconductor pattern, coordinate information of a base point for measuring a dimension of a desired location of the semiconductor pattern, and measuring the dimension using the coordinate information of the base point, the method comprising the computer system inputting, into a pose estimation model trained to automatically design a skeleton including at least two base points on the semiconductor pattern as keypoints, and to output coordinate information of the keypoints, image data of an object to be measured including the semiconductor pattern, and generating coordinate information of the keypoints of the image data that has been input, and the computer system measuring the dimension using the coordinate information of the keypoints of the image data of the object to be measured, the pose estimation model being trained using teacher data having the image data of the semiconductor pattern as an input and the coordinate information of the at least two base points as an output. 9 . The dimension measurement method according to claim 8 , wherein the computer system, using an image analysis tool having a function for calculating, through pixel computation, a distance between predetermined locations of the image data designated on a GUI, measures the dimension with reference to the coordinate information of the at least two base points on the image analysis tool. 10 . The dimension measurement method according to claim 9 , wherein the image analysis tool further comprises a function for outputting the coordinate information of the desired locations, and the computer system, during training of the pose estimation model, converts output data of the image analysis tool including the coordinate information into annotation data of the teacher data. 11 . The dimension measurement method according to claim 9 , wherein the computer system, during training of the pose estimation model, generates, using output data of the image analysis tool including the coordinate information, and rule information input in advance, definition data of a skeleton structure of the pose estimation model. 12 . The dimension measurement method according to claim 8 , further comprising: the computer system receiving, via a network, new image data of the object to be measured from an external computer; and the computer system performing measurement of the dimension of the semiconductor pattern included in the new image data of the object to be measured, and transmitting a result of measurement of the dimension to the external computer. 13 . A storage medium storing a program for causing a computer to realize a dimension measurement function for: extracting, from image data of a semiconductor pattern, coordinate information of a base point for measuring a dimension of a desired location of the semiconductor pattern; and measuring the dimension using the coordinate information, the program including a program code for realizing a training device describing a pose estimation model for outputting coordinate information of at least two of the base points as a training result, wherein the training device has an input layer having the image data of the semiconductor pattern as an input, and an output layer outputting the coordinate information of the at least two base points, and the pose estimation model is capable of being trained using teacher data that has the image data of the semiconductor pattern as an input and the coordinate information of the at least two base points as an output. 14 . The storage medium according to claim 13 , wherein the program has a program code for converting output data of the image analysis tool including the coordinate information, into annotation data of the teacher data, and the image analysis tool has a function for calculating, through pixel computation, a distance between predetermined locations of the image data designated on a GUI. 15 . The storage medium according to claim 13 , wherein the program has a program code for generating, using output data of the image analysis tool including the coordinate information and rule information input in advance, definition data of a skeleton structure of the pose estimation model, and the image analysis tool has a function for calculating, through pixel computation, a distance between predetermined locations of the image data designated on a GUI.

Assignees

Inventors

Classifications

  • Testing or measuring during manufacture or treatment of wafers, substrates or devices · CPC title

  • Pattern inspection · CPC title

  • Image processing arrangements associated with the tube · CPC title

  • Industrial image inspection · CPC title

  • using a design-rule based approach · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US2024200939A1 cover?
A computer system providing a function for: extracting, from image data of a semiconductor pattern, coordinate information of a base point for measuring a dimension of a desired location of the semiconductor pattern; and measuring the dimension using the coordinate information of the base point. The computer system includes a training device in which a pose estimation model for outputting coord…
Who is the assignee on this patent?
Hitachi High Tech Corp
What technology area does this patent fall under?
Primary CPC classification G01B21/04. Mapped technology areas include Physics.
When was this patent published?
Publication date Thu Jun 20 2024 00:00:00 GMT+0000 (Coordinated Universal Time) (A1). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 9 related publications on this page (citations in our corpus or others sharing the same primary CPC).