# US 2026/0268470 A1 · Measurement System, Computer, and Measurement Method

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0268470 A1
- Document ID: US20260268470A1
- Status: Published application
- Kind: A1
- Application number: 19/163,699
- Filed: 2023-06-22
- Published: 2026-09-10
- Earliest claimed: 2023-06-22
- Assignees: Hitachi High-Tech Corporation
- Applicants: Hitachi High-Tech Corporation
- Inventors: Shinya KYOGOKU; Takahiro NISHIHATA; Mayuka OSAKI; Yasunori GOTO
- Web page: https://patentgrep.com/patent/US20260268470A1

## CPC

- G06T 7/0006: {using a design-rule based approach}
- G01B 15/00: Measuring arrangements characterised by the use of electromagnetic waves or particle radiation, e.g. by the use of microwaves, X-rays, gamma rays or electrons (characterised by the use of optical techniques G01B9/00, G01B11/00)
- G01N 23/203: Measuring back scattering
- G01N 23/2206: Combination of two or more measurements, at least one measurement being that of secondary emission, e.g. combination of secondary electron [SE] measurement and back-scattered electron [BSE] measurement
- G01N 23/2251: using incident electron beams, e.g. scanning electron microscopy [SEM]
- G06T 7/00: Image analysis
- G06T 7/0004: {Industrial image inspection}
- G06T 7/001: {using an image reference approach}
- G06T 7/60: Analysis of geometric attributes
- G06T 7/62: of area, perimeter, diameter or volume
- G01N 2223/401: image processing
- G01N 2223/6116: semiconductor wafer
- G06T 2207/10056: Microscopic image
- G06T 2207/10061: from scanning electron microscope
- G06T 2207/20021: Dividing image into blocks, subimages or windows
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/20221: Image fusion; Image merging
- G06T 2207/30148: Semiconductor; IC; Wafer
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G01B: MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)

## Abstract

To provide a technique capable of measuring an overlay deviation amount or the like with high accuracy. In a measurement system, a processor acquires an image (309) of a structure of a semiconductor device captured by a microscope, acquires a measurement area cursor generation rule (308) related to the structure, generates a measurement area cursor to be disposed with respect to the structure based on the image and the measurement area cursor generation rule, disposes the measurement area cursor with respect to the structure in the image, and performs measurement related to the structure using a portion of an image (313) in the measurement area cursor.

## Claims

### Claim 1

A measurement system for a semiconductor device, the measurement system comprising:
a microscope; and
a processor, wherein
the processor
acquires an image of a structure of the semiconductor device captured by the microscope,
acquires a measurement area cursor generation rule related to the structure,
generates a measurement area cursor to be disposed with respect to the structure based on the image and the measurement area cursor generation rule,
disposes the measurement area cursor with respect to the structure in the image, and
performs measurement related to the structure using a portion of the image in the measurement area cursor.

### Claim 2 (depends on 1)

The measurement system according to claim 1, wherein
the processor
generates a region divided image based on the image, and
generates, based on the region divided image and the measurement area cursor generation rule, the measurement area cursor to be disposed in the structure by applying the measurement area cursor generation rule to a region element included in the region divided image.

### Claim 3 (depends on 2)

The measurement system according to claim 2, wherein
the processor
acquires a sample image as the image,
generates the region divided image based on the sample image,
acquires the measurement area cursor generation rule set based on the region divided image of the sample image,
acquires a measurement target image of the structure of the semiconductor device captured by the microscope during measurement,
generates the region divided image based on the measurement target image,
generates the measurement area cursor to be disposed with respect to the structure based on the region divided image of the measurement target image and the measurement area cursor generation rule,
disposes the measurement area cursor with respect to the structure in the measurement target image, and
performs the measurement related to the structure using a portion of the measurement target image in the measurement area cursor.

### Claim 4 (depends on 1)

The measurement system according to claim 1, wherein
the structure has, as a three-dimensional structure, at least a lower layer pattern and an upper layer pattern overlapping the lower layer pattern, and
the processor measures an overlay deviation amount in a set of the lower layer pattern and the upper layer pattern as a measurement target.

### Claim 5 (depends on 2)

The measurement system according to claim 2, wherein
the processor provides a user with a screen displaying the region divided image and the measurement area cursor generation rule, and sets the measurement area cursor generation rule based on an operation of checking the region divided image by the user on the screen.

### Claim 6 (depends on 2)

The measurement system according to claim 2, wherein
the structure has, as a three-dimensional structure, at least a lower layer pattern and an upper r layer pattern overlapping the lower layer pattern,
the region divided image has a region type for each region element,
the region type has at least the lower layer pattern, the upper layer pattern, and a background region, and
the measurement area cursor generation rule has the region type of the region element for generating the measurement area cursor to be applied to the structure as a measurement target.

### Claim 7 (depends on 6)

The measurement system according to claim 6, wherein
the measurement area cursor generation rule includes reference coordinate information of the region element of the region type for generating the measurement area cursor and a correction value indicating a relative relationship from the reference coordinate information.

### Claim 8 (depends on 7)

The measurement system according to claim 7, wherein
the measurement area cursor generation rule has a maximum value or a minimum value in a designated direction in a designated region element as the reference coordinate information, has a correction value in the designated direction as the correction value, and is capable of designating coordinate information selected from coordinate information of the upper layer pattern and coordinate information of the lower layer pattern as the reference coordinate information for generating the measurement area cursor to be applied to the lower layer pattern.

### Claim 9 (depends on 1)

The measurement system according to claim 1, wherein
the measurement area cursor generation rule is attached with a measurement area cursor possibility determination rule for determining whether measurement is possible by generating the measurement area cursor with respect to the structure, and
the processor does not generate the measurement area cursor with respect to the structure when it is determined as no based on the measurement area cursor possibility determination rule.

### Claim 10 (depends on 9)

The measurement system according to claim 9, wherein
the measurement area cursor possibility determination rule includes a condition that the measurement area cursor is not to be generated in a case where a width of the measurement area cursor is less than or is less than or equal to a designated width when the measurement area cursor is to be generated with respect to the structure based on the measurement area cursor generation rule.

### Claim 11 (depends on 3)

The measurement system according to claim 3, wherein
the processor
trains a learning model that generates the region divided image based on the sample image,
sets the measurement area cursor generation rule based on the region divided image generated by the learning model, and
generates the region divided image by the learning model based on the measurement target image during the measurement, and
the learning is unsupervised machine learning that does not use, as an input, training data in which a label indicating a region type is assigned to a pixel of the image, or supervised machine learning that uses the training data as an input.

### Claim 12 (depends on 3)

The measurement system according to claim 3, wherein
the measurement area cursor generation rule is set to generate the measurement area cursor by rule-based program processing, and
the processor generates the measurement area cursor by the rule-based program processing based on the region divided image and the measurement area cursor generation rule.

### Claim 13 (depends on 2)

The measurement system according to claim 2, wherein
an image type of the image includes an SE image of the structure of the semiconductor device captured by detecting a secondary electron (SE) by the microscope, a BSE image of the structure of the semiconductor device captured by detecting a backscattered electron (BSE) by the microscope, and a composite image obtained by combining the SE image and the BSE image, and
the processor
generates the region divided image based on the composite image as the image having a designated image type, and
disposes the measurement area cursor with respect to the structure in the image having the designated image type.

### Claim 14

A computer in a measurement system for a semiconductor device including a microscope and a processor, the computer comprising:
the processor, wherein
the processor
acquires an image of a structure of the semiconductor device captured by the microscope,
acquires a measurement area cursor generation rule related to the structure,
generates a measurement area cursor to be disposed with respect to the structure based on the image and the measurement area cursor generation rule,
disposes the measurement area cursor with respect to the structure in the image, and
performs measurement related to the structure using a portion of the image in the measurement area cursor.

### Claim 15

A measurement method to be executed by a computer including a processor measurement system for a semiconductor device including a microscope and the computer, the measurement method comprising, as steps to be executed by the computer:
a step of acquiring an image of a structure of the semiconductor device captured by the microscope;
a step of acquiring a measurement area cursor generation rule related to the structure;
a step of generating a measurement area cursor to be disposed with respect to the structure based on the image and the measurement area cursor generation rule;
a step of disposing the measurement area cursor with respect to the structure in the image; and
a step of performing measurement related to the structure using a portion of the image in the measurement area cursor.
