# US 12,561,823 B2 · Structure estimation system and structure estimation program for estimating height of structure based on data from charged particle beam device

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

- Number: US 12,561,823 B2
- Document ID: US12561823B2
- Status: Granted
- Kind: B2
- Application number: 17/296,421
- Filed: 2019-02-15
- Published: 2022-04-28
- Granted: 2026-02-24
- Earliest claimed: 2019-02-15
- Assignees: Hitachi High-Tech Corporation
- Applicants: Hitachi High-Tech Corporation
- Inventors: Muneyuki Fukuda; Yasutaka Toyoda; Ryou Yumiba; Shuyang Dou; Ayumi Doi; Junichi Tanaka
- Web page: https://patentgrep.com/patent/US12561823B2

## CPC

- G06T 7/62: of area, perimeter, diameter or volume
- G01N 23/18: Investigating the presence of flaws defects or foreign matter
- G01N 23/225: using electron or ion
- G06T 7/0004: {Industrial image inspection}
- G06T 7/70: Determining position or orientation of objects or cameras (camera calibration G06T7/80)
- G06V 10/454: {Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]}
- G06V 10/764: using classification, e.g. of video objects
- G06V 10/82: using neural networks
- G06V 20/69: Microscopic objects, e.g. biological cells or cellular parts
- H10P 74/203: {Structural properties, e.g. testing or measuring thicknesses, line widths, warpage, bond strengths or physical defects}
- G01N 33/0078: {Testing material properties on manufactured objects}
- G01N 2223/418: electron microscope
- G01N 2223/6116: semiconductor wafer
- G01N 2223/652: impurities, foreign matter, trace amounts
- G06T 2207/10061: from scanning electron microscope
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30148: Semiconductor; IC; Wafer
- H01J 2237/24578: Spatial variables, e.g. position, distance
- H01J 2237/2814: Measurement of surface topography
- H01J 2237/2817: Pattern inspection
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- 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)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H10P: GENERIC PROCESSES OR APPARATUS FOR THE MANUFACTURE OR TREATMENT OF DEVICES COVERED BY CLASS H10
- H01J: ELECTRIC DISCHARGE TUBES OR DISCHARGE LAMPS (spark-gaps H01T; electric arc lamps H05B31/00; particle accelerators H05H)

## Abstract

The present disclosure relates to a system and a non-transitory computer-readable medium for estimating the height of foreign matter, etc. adhering to a sample. In order to achieve the abovementioned purpose, proposed is a system, etc. in which data acquired by a charged particle beam device or features extracted from the data are input to a learning model, which is provided with, in an intermediate layer thereof, a parameter learned using teacher data having data acquired by the charged particle beam device or features extracted from the data as inputs and having the heights or depths of the structures of samples or of foreign matter on the samples as outputs, and height or depth information is output.

## Claims

### Claim 1

A structure estimation system that estimates, from an observation image of a sample acquired by a charged particle beam apparatus, information about a depth or a height corresponding to the observation image on the sample or to a feature amount extracted from the observation image by one or more computer systems,
wherein the structure estimation system includes the one or more computer systems and the charged particle beam apparatus configured to irradiate the sample with a charged particle beam, the charged particle beam apparatus including a plurality of shadow image detectors arranged in a direction tilted and axis-symmetrically with respect to a beam optical axis of the charged particle beam to obtain structure data about the structure of the sample,
wherein the one or more computer systems include a non-transitory computer-readable medium storing a plurality of modules for implementing one or more functions implemented including at least a calculation module,
wherein the one or more computer systems include an identifier that outputs information about the depth or the height corresponding to the observation image or to the feature amount extracted from the observation image,
wherein the identifier is configured to receive as an input a plurality of types of background images in which an image is acquired for each of a plurality of different layouts and also to receive as an input a plurality of types of foreign object images acquired for each of a plurality of different signal processing conditions, and is configured to output information about the depth or the height corresponding to the observation image or to the feature amount extracted from the observation image, and
wherein the calculation module acquires, from the identifier, information about the depth or the height corresponding to the observation image or to the feature amount extracted from the observation image by inputting the background images and the foreign object images to the identifier.

### Claim 2 (depends on 1)

The structure estimation system according to claim 1,
wherein the feature amount includes information about brightness of the observation image of the structure of the sample, and
wherein the feature amount includes information about a size or an area of the structure of the sample.

### Claim 3 (depends on 1)

The structure estimation system according to claim 1,
wherein the information on the depth is information on whether the depth is deeper or shallower than a predetermined reference value, and
wherein the calculation module outputs an estimation result of whether the depth is deeper or shallower than the predetermined reference value.

### Claim 4 (depends on 1)

The structure estimation system according to claim 1,
wherein the computer system acquires the plurality of types of foreign object images under different signal processing conditions with respect to one foreign object placed on the sample.

### Claim 5 (depends on 1)

The structure estimation system according to claim 1,
wherein the background image is an image of the sample on which a pattern is formed through a predetermined manufacturing process.

### Claim 6 (depends on 4)

The structure estimation system according to claim 4,
wherein the plurality of types of background images is acquired under the different signal processing conditions, under which the plurality of types of foreign object images is acquired.

### Claim 7 (depends on 1)

The structure estimation system according to claim 1,
wherein the identifier is a learner of any one of a neural network, a regression tree, and a Bayesian identifier.

### Claim 8 (depends on 7)

The structure estimation system according to claim 7,
wherein the learner performs a learning process using training data in advance, the training data being configured such that the learner is configured to receive as an input the plurality of types of background images in which an image is acquired for each of different layouts and also to receive as an input the plurality of types of foreign object images acquired for each of different signal processing conditions, and is configured to output information about the depth or the height corresponding to the observation image or to the feature amount extracted from the observation image.

### Claim 9

A structure estimation system that estimates, from an observation image of a sample acquired by a charged particle beam apparatus, information about a depth or a height corresponding to the observation image on the sample or to a feature amount extracted from the observation image by one or more computer systems,
wherein the structure estimation system includes the one or more computer systems and the charged particle beam apparatus configured to irradiate the sample with a charged particle beam, the charged particle beam apparatus including a plurality of shadow image detectors arranged in a direction tilted and axis-symmetrically with respect to a beam optical axis of the charged particle beam to obtain structure data about the structure of the sample,
wherein the one or more computer systems include a non-transitory computer-readable medium storing a plurality of modules for implementing one or more functions implemented including at least a calculation module,
wherein the one or more computer systems include an identifier that outputs information about the depth or the height corresponding to the observation image or to the feature amount extracted from the observation image,
wherein the identifier is configured to receive as an input a composite image obtained by using a plurality of types of background images in which an image is acquired for each of a plurality of different layouts and also by using a plurality of types of foreign object images acquired for each of a plurality of different signal processing conditions, and is configured to output information about the depth or the height corresponding to the observation image or to the feature amount extracted from the observation image, and
wherein the calculation module acquires, from the identifier, information about the depth or the height corresponding to the observation image or to the feature amount extracted from the observation image by inputting the composite image to the identifier.

### Claim 10

A structure estimation system for estimating, from data obtained by a charged particle beam apparatus, information about a depth or a height of a pattern formed on a structure of a sample,
wherein the structure estimation system includes one or more computer systems and the charged particle beam apparatus configured to irradiate the sample with a charged particle beam, the charged particle beam apparatus including a plurality of shadow image detectors arranged in a direction tilted and axis-symmetrically with respect to a beam optical axis of the charged particle beam to obtain structure data about the structure of the sample,
wherein the one or more computer systems include a non-transitory computer-readable medium storing a plurality of modules for implementing one or more functions implemented including at least a calculation module,
wherein the one or more computer systems include an identifier that outputs information about the depth or the height of the pattern formed on the structure of the sample,
wherein the identifier is configured to receive as an input at least one of: an output of the multiple direction detector, which is data obtained by the charged particle beam apparatus, an image formed based on the output, or a feature of the pattern extracted from the image, and is configured to output information about the depth or the height of the pattern formed on the structure of the sample, and
wherein the calculation module acquires, from the identifier, information about the depth or the height of the pattern formed on the structure of the sample by inputting to the identifier at least one of: the output of the multiple direction detector, the image formed based on the output, or the feature of the pattern extracted from the image.

### Claim 11 (depends on 10)

The structure estimation system according to claim 10,
wherein the feature of the pattern extracted from the image is a parameter indicating at least one of:
a brightness value of the pattern;
a size value of the pattern;
an evaluation value of a shape of the pattern, and a deformation amount of the shape of the pattern; and
an evaluation value of quality of the pattern.