WO2026023005A1 - データセット生成装置、データセット生成方法、撮像装置、撮像方法、顕微鏡装置、データセット生成システム、撮像システムおよび半導体デバイス製造システム - Google Patents
データセット生成装置、データセット生成方法、撮像装置、撮像方法、顕微鏡装置、データセット生成システム、撮像システムおよび半導体デバイス製造システムInfo
- Publication number
- WO2026023005A1 WO2026023005A1 PCT/JP2024/026566 JP2024026566W WO2026023005A1 WO 2026023005 A1 WO2026023005 A1 WO 2026023005A1 JP 2024026566 W JP2024026566 W JP 2024026566W WO 2026023005 A1 WO2026023005 A1 WO 2026023005A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- roi
- charged particle
- particle beam
- image
- generating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01J—ELECTRIC DISCHARGE TUBES OR DISCHARGE LAMPS
- H01J37/00—Discharge tubes with provision for introducing objects or material to be exposed to the discharge, e.g. for the purpose of examination or processing thereof
- H01J37/02—Details
- H01J37/22—Optical, image processing or photographic arrangements associated with the tube
- H01J37/222—Image processing arrangements associated with the tube
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
- G01N23/22—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material
- G01N23/225—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material using electron or ion
- G01N23/2251—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00 by measuring secondary emission from the material using electron or ion using incident electron beams, e.g. scanning electron microscopy [SEM]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01J—ELECTRIC DISCHARGE TUBES OR DISCHARGE LAMPS
- H01J37/00—Discharge tubes with provision for introducing objects or material to be exposed to the discharge, e.g. for the purpose of examination or processing thereof
- H01J37/02—Details
- H01J37/22—Optical, image processing or photographic arrangements associated with the tube
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01J—ELECTRIC DISCHARGE TUBES OR DISCHARGE LAMPS
- H01J37/00—Discharge tubes with provision for introducing objects or material to be exposed to the discharge, e.g. for the purpose of examination or processing thereof
- H01J37/26—Electron or ion microscopes; Electron or ion diffraction tubes
- H01J37/28—Electron or ion microscopes; Electron or ion diffraction tubes with scanning beams
Definitions
- the present invention relates to a dataset generation device, a dataset generation method, an imaging device, an imaging method, a microscope device, a dataset generation system, an imaging system, and a semiconductor device manufacturing system.
- the target shape In order to achieve the desired processing shape (called the target shape) using plasma etching, it is necessary to set parameters that control the many gas, power, and radio frequency systems equipped in the etching equipment. To achieve a complex processing shape, many parameters must be adjusted over multiple steps, and settings must be switched on a second-by-second basis, so a huge number of parameters must be set to process a single pattern.
- the processing conditions for etching, or the parameters set to execute the processing conditions, are called an etching recipe.
- X-SEM cross-sectional scanning electron microscope
- X-SEM observation involves three steps: (1) sample formation, (2) X-SEM observation, and (3) image measurement. Because these steps are performed manually, they require significant human and time costs, creating a need for automation of the process. (1) is less expensive than (2) and (3), and progress is being made with automated measurement of (3) using general-purpose image measurement software and deep learning technology.
- (2) X-SEM observation various microscope manufacturers have developed automated observation software that is available to users.
- TM template matching
- Patent Document 1 discloses a method for automatically correcting the position of the observation field in SEM observation using pattern matching technology.
- Patent Document 1 discloses the following as an invention for a charged particle beam device: "The imaging device is configured to be able to move the sample on at least two drive axes and is equipped with a sample stage that can move the imaging field of view in accordance with the positional information of the sample required by the computer system.
- the computer system is equipped with a classifier that, in response to input of image data of a tilt image captured while the sample is tilted with respect to the charged particle beam, outputs positional information of one or more feature parts present in the tilt image.
- the classifier has been trained in advance using training data that takes as input the image data of the tilt image and outputs positional information of feature parts, and the computer system executes a process of outputting positional information of feature parts for new tilt image data input to the classifier.”
- TM method has the effect of reducing the workload for the operator when aligning the field of view with the position of the object to be observed.
- the cross-sectional shape observed with an X-SEM during etching recipe development changes significantly when the etching recipe is changed. Because the image registered for the TM method and the shape of the ROI differ, it remains difficult to identify the ROI using the TM method for the cross-sectional shape observed with an X-SEM.
- Patent Document 2 proposes automating X-SEM observation using a classifier trained by machine learning.
- Patent Document 2 discloses a method for using a trained classifier to recognize markers on a sample and move to their coordinates.
- Patent Document 2 aims to provide an image display device with reduced power consumption, and discloses the following as an invention for an image display device: "An image display device comprising: first wiring interconnecting a plurality of electron-emitting elements each having an electron-emitting portion between a pair of electrodes; second wiring having a higher resistance than the first wiring; an insulating layer covering the second wiring; and a resistive film connected to the first wiring and covering the insulating layer and having a surface resistance of 108 ⁇ / ⁇ or more, wherein the resistive film is connected to the first wiring at a portion that does not overlap with the second wiring; and the length L between the portion of the resistive film connected to the first wiring and the portion that overlaps with the second wiring is five times or more the thickness T of the insulating layer.”
- Patent Document 2 also discloses a method of creating a style transfer model using a 3D model containing arbitrary cross sections generated from a layout pattern.
- etching recipes are often developed using test patterns, and there are limited cases in which layout patterns can be used.
- an object of the present disclosure is to provide a technology that can generate a data set required to construct a classifier with guaranteed recognition performance when classifying charged particle beam images.
- one representative dataset generation device of the present invention is a dataset generation device that generates a dataset used to train a classifier that performs image recognition of charged particle beam images, and is characterized in that non-ROI candidates, which are regions that do not include a Region of Interest (ROI) registered for the image recognition, are generated based on the ROI and the charged particle beam image, and the number of non-ROI candidates is reduced based on the ROI while the non-ROI is generated.
- ROI Region of Interest
- FIG. 1 is a diagram showing a schematic configuration of an imaging device when a scanning electron microscope (SEM) is used as a charged particle beam device.
- FIG. 2 is a diagram showing an example of the system configuration of an imaging system for performing electron microscope observation.
- FIG. 3 is a flowchart showing how the imaging device performs observation using the classifier in the imaging system 100.
- 4 is a diagram illustrating an example of the configuration of an automatic imaging system using the cloud.
- FIG. 5 is a diagram showing an example of a charged particle beam image 501.
- FIG. 6 is a schematic diagram showing the result of image recognition when a classifier is constructed by selecting non-ROI.
- FIG. 7 is a schematic diagram showing the result of image recognition when a classifier is constructed without selecting non-ROIs.
- FIG. 1 is a diagram showing a schematic configuration of an imaging device when a scanning electron microscope (SEM) is used as a charged particle beam device.
- FIG. 2 is a diagram showing an example of the system configuration of an imaging
- FIG. 8 is a diagram showing a setting method for setting a non-ROI candidate region in the horizontal direction of a charged particle beam image.
- FIG. 9 is a diagram showing a setting method for setting a non-ROI candidate region in the vertical direction of a charged particle beam image.
- FIG. 10 is a diagram showing a setting method for setting a non-ROI candidate region in an oblique direction of a charged particle beam image.
- 11 is a diagram showing a case where the ROI and non-ROI candidate regions overlap, which is an example of generating a non-ROI using the overlap method.
- FIG. 12 is a diagram showing a case where a ROI 901 and a non-ROI candidate region are included in a charged particle beam image.
- FIG. 13 is a diagram showing a case where a non-ROI candidate region is set in a charged particle beam image.
- FIG. 14 is a diagram showing an example in which the non-ROI candidate region is moved randomly.
- FIG. 15 is a diagram showing an example of a GUI for registering an ROI.
- FIG. 16 is a diagram showing an example of a GUI for adjusting parameters for generating a non-ROI.
- a region of interest (ROI) included in an image may be described.
- ROI region of interest
- the term “save the ROI” may also be used.
- expressions such as “save the non-ROI” and “save the non-ROI candidate region” may also be used to refer to regions of an image that do not include a region of interest (non-ROI) and non-ROI candidate regions.
- a “non-ROI candidate region” may also be simply referred to as a “non-ROI candidate.”
- an ROI when set in association with an image, it is also referred to as "registering an ROI in an image.”
- a non-ROI when set in association with an image, it is also referred to as “registering a non-ROI in an image.”
- FIG. 1 is a schematic diagram showing the configuration of an imaging device when a scanning electron microscope (SEM) is used as the charged particle beam device.
- the imaging device 200 comprises an electron gun 201, a focusing lens 202, a deflection coil 203, an objective lens 204, a secondary electron detector 205, a sample stage 206, an image forming unit 231, a display unit 235, and a control unit 236.
- the imaging device 200 consisting of the electron gun 201, the focusing lens 202, the deflection coil 203, the objective lens 204, the secondary electron detector 205, the sample stage 206, the image forming unit 231, the display unit 235, and the control unit 236, can also be referred to as the imaging device 2000.
- an imaging device 2000 that images a sample using a charged particle beam is equipped with a classifier that performs image recognition of the charged particle beam image, and generates non-ROI candidates, which are regions that do not include the region of interest (ROI), based on the region of interest (ROI) registered for image recognition and the charged particle beam image, and generates non-ROIs while reducing the number of non-ROI candidates based on the ROI, thereby generating a dataset used to train the classifier.
- ROI region of interest
- ROI region of interest
- the electron gun 201 is equipped with an electron gun 201, which is a radiation source that emits an electron beam 207 accelerated by a predetermined acceleration voltage.
- the emitted electron beam 207 is focused by a focusing lens 202 and an objective lens 204, and is irradiated onto a sample 220.
- a deflection coil 203 deflects the electron beam 207 using a magnetic field or electric field, thereby scanning the surface of the sample 220 with the electron beam 207.
- the sample stage 206 has the function of moving the sample 220 along a predetermined drive axis or tilting or rotating it around a predetermined drive axis in order to move the imaging field of view of the imaging device 200. These functions are achieved by driving actuators such as motors and piezoelectric elements provided on the sample stage 206.
- the secondary electron detector 205 is, for example, an Everhart-Thornley (ET) detector or a semiconductor detector composed of a scintillator, light guide, and photomultiplier tube, and detects secondary electrons 221 emitted from a sample 220 irradiated with an electron beam 207.
- a detection signal output from the secondary electron detector 205 is transmitted to the image forming unit 231.
- the imaging device 200 may also be equipped with a backscattered electron detector that detects backscattered electrons and a transmitted electron detector that detects transmitted electrons.
- the image forming unit 231 forms an observation image of the sample 220 using an AD converter 232 that converts the detection signal output from the secondary electron detector 205 into a digital signal, and a calculator 233 that synchronizes the secondary electron signal with the scanning of the electron beam 207 on the sample 220 using the digital signal output by the AD converter 232 and the deflection coil 203.
- the observation image formed by the image forming unit 231 is sent to the display unit 235 for display, or sent to the computer system 234 for various processing.
- the computer system 234 has, for example, a processor, memory, input/output devices, and storage devices.
- the input/output devices include input devices such as a keyboard and mouse for entering user instructions, and output devices such as a display device.
- a control unit 236 that controls the sample stage 206, display unit 235, and imaging device 200, a desired location on the sample 220 can be observed under specific conditions.
- a scanning electron microscope SEM
- a sample e.g., a semiconductor device
- a charged particle beam e.g., a charged particle beam
- FIB focused ion beam
- TEM transmission electron microscope
- the imaging device 2000 can be a microscope device 2001.
- the microscope device 2001 includes the imaging device 2000, and the microscope device 2001 detects an ROI using an image of the charged particle beam, thereby moving the field of view. Specific processing will be described later.
- FIG. 2 is a diagram showing an example system configuration of an imaging system 100 for performing electron microscope observations.
- the imaging system 100 has a dataset generation system 101, a classifier construction unit 109, a classifier storage unit 110, an observation recipe input unit 111, an observation recipe display unit 112, an input device 113, and an imaging device 200.
- the imaging system 100 since the imaging system 100 is basically capable of performing imaging without requiring user operation, the imaging system 100 can also be referred to as an automatic imaging system 100.
- the observation recipe input unit 111 and the observation recipe display unit 112 can also be referred to as the automatic observation recipe input unit 111 and the automatic observation recipe display unit 112, respectively.
- the dataset generation system 101 generates a dataset used for training a classifier that performs image recognition of charged particle beam images.
- the dataset generation system 100 generates a dataset used for training a classifier that performs image recognition of charged particle beam images, and generates non-ROI candidates, which are areas that do not include the region of interest (ROI) registered for image recognition and the charged particle beam image, and generates non-ROIs while reducing the number of non-ROI candidates based on the ROI.
- the classifier performs image recognition of the charged particle beam image (sometimes simply referred to as a "charged particle beam image").
- the dataset generation system 101 includes an image storage unit 102 that stores charged particle beam images, a dataset storage unit 103 that stores information indicating a region of interest (hereinafter also referred to as "ROI") 106 in the charged particle beam image stored in the image storage unit 102 and information indicating a region not including the ROI (hereinafter also referred to as "non-ROI") 107 (the combination of information indicating the ROI and information indicating the non-ROI is also referred to as a "dataset").
- a processor 108 that can access the image storage unit 102 and the dataset storage unit 103, and a memory 114.
- the processor 108 when a user inputs information indicating a charged particle beam image 105 and an ROI 106 into the dataset generation system 101, the processor 108 generates information indicating a non-ROI 107.
- the derivation of the non-ROI 107 will be described later. It can also be said that the ROI and non-ROI stored in the dataset storage unit 103 are registered in the charged particle beam image stored in the image storage unit 102.
- the dataset generation system 101 is configured using hardware, for example, it can also be used as a dataset generation device.
- the imaging system 100 constructs an image recognition classifier in the classifier construction unit 109 using the datasets of the ROI 106 and non-ROI 107 in the dataset generation system 101.
- the image recognition classifier is stored in the classifier storage unit 110.
- the image recognition classifier (hereinafter simply referred to as the "classifier") is referenced by the observation recipe input unit 111, and it can be confirmed that it has been referenced in the observation recipe display unit 112.
- An observation recipe created using the observation recipe display unit 112 to reflect the user's requests enables image classification based on the classifier.
- the observation recipe is sent to the imaging device 200 (more specifically, the control unit 236 of the imaging device 200), and observation based on the observation recipe is performed in the imaging system 100.
- the combination of the observation recipe input unit 111 and the observation recipe display unit 112 can also be called an observation recipe generation unit 115 that generates an observation recipe that enables image classification based on the classifier.
- the dataset generation system 101, classifier construction unit 109, classifier storage unit 110, and observation recipe input unit 111 can be arranged in the computer system 234 shown in FIG. 1.
- the memory 114 can store processing instructions that cause the processor 108 to execute the classifier construction unit 109, observation recipe input unit 111, and observation recipe display unit 112. These processing instructions may be installed as software in the computer system 234.
- the computer system 234 may have a processor and memory in addition to the processor 108 and memory 114, and may also have other software installed.
- the observation software may include software that causes the processor 108 or computer system 234 to generate an observation recipe.
- the dataset generation system 101 when placed in the computer system 234 shown in FIG. 1, it is possible to display a GUI on the output device of the computer system 234 and to accept user requests via the input device.
- the processor 108 is shown connected between the input device 113 and the dataset generation system 101, the present disclosure is not limited to this case.
- the processor 108 can also control components included in the imaging system 100, for example.
- the processor 108 executes a step of performing image recognition of the charged particle beam image and a step of generating a dataset used for learning to perform the image recognition.
- the dataset is generated by generating non-ROI candidates, which are regions that do not include the ROI, based on the region of interest (ROI) registered for image recognition and the charged particle beam image, and generating non-ROIs while reducing the number of non-ROI candidates based on the ROI. Specific processing will be described later.
- the processor 108 includes, for example, a CPU (Central Processing Unit) or a GPU (Graphical Processing Unit). Although the case where there is one processor 108 is shown, the processor 108 may include one or more processors.
- the dataset storage unit 103 and the classifier storage unit 110 include an HDD (Hard Disk Drive), an SSD (Solid State Drive), and memory.
- the dataset storage unit 103 and the classifier storage unit 110 are also not limited to being configured with a single storage device, and may, for example, have a storage device arranged for each type of data.
- the imaging system 100 has been described, it is also possible to include the imaging system 100 in the manufacturing apparatus 10 that manufactures semiconductor devices, thereby calling it the semiconductor device manufacturing system 1.
- the charged particle beam image 105 can also be acquired by using the imaging device 200 to image the semiconductor device manufactured by the manufacturing apparatus 10.
- the imaging device 200 images the semiconductor device manufactured by the manufacturing apparatus 10 based on an observation recipe described below, and acquires a charged particle beam image.
- the imaging device 200 acquires a charged particle beam image and analyzes the structure of the semiconductor device, thereby developing an etching recipe suitable for obtaining the desired structure.
- Figure 3 is a flowchart showing how the imaging device 200 performs observations using a classifier in the imaging system 100.
- the processor 108 inputs and outputs data to the dataset generation system 101 and controls the entire flowchart.
- the processor 108 determines 301 the charged particle beam image and ROI. For example, the user selects the charged particle beam image 105 and ROI 106 to be observed via the input device 113. At this time, the area in the charged particle beam image 105 that is to be image-recognized during observation is also saved (registered) as the ROI 106.
- the ROI 106 may be saved by saving an image file of the ROI 106 or by saving a text file specifying coordinates within the charged particle beam image 105.
- the processor 108 stores the charged particle beam image 105 input from the input device 113 in the image storage unit 102, and also stores the ROI 106 in the dataset storage unit 103.
- the processor 108 performs non-ROI candidate region calculation 302 using the charged particle beam image 105 and ROI 106.
- the processor 108 In non-ROI candidate region calculation 302, the processor 108 generates multiple non-ROI candidate regions based on the charged particle beam image 105 and ROI 106.
- the candidate region for non-ROI 107 is automatically calculated by the processor 108, basically without requiring user specification.
- the results of non-ROI candidate region calculation 302 may be temporarily stored in the memory 114, or may be saved in the dataset storage unit 103.
- the processor 108 performs non-ROI generation 303 using the results of non-ROI candidate region calculation 302, and information indicating the generated non-ROI 107 is saved in the dataset storage unit 103.
- the processor 108 determines 306 whether the number of generated non-ROIs 107 is greater or less than a threshold. If the number of non-ROIs 107 is greater than the standard, the processor 108 adjusts the parameters in non-ROI generation parameter adjustment 309 and executes non-ROI generation 303 again. The processor 108 generates a non-ROI by reducing the number of multiple non-ROI candidate regions based on the ROI 106.
- the processor 108 executes classifier construction 304.
- classifier construction 304 the non-ROIs 107 and ROIs 106 stored in the dataset storage unit 103 are used, and a classifier required for image recognition is constructed in the classifier construction unit 109.
- the constructed classifier is stored in the classifier storage unit 110.
- the classifier stored in the classifier storage unit 110 is referenced from the observation recipe input unit 111.
- the observation recipe includes observation conditions ranging from low-magnification observation to high-magnification observation, for example, and the observation conditions are displayed in the observation recipe display unit 112.
- an observation system may be configured in which the observation functions excluding the imaging device 200 are implemented as applications on a platform.
- An example of such implementation is shown in FIG.
- FIG. 4 shows an example configuration of an imaging system 100A that uses the cloud.
- the imaging system 100A includes an imaging device 200, a platform 400, and a terminal 410.
- the platform 400 is implemented with an application for generating a dataset used to train a classifier that performs image recognition of charged particle beam images.
- the platform 400 includes a database 401, an OS 402, middleware 403, an observation recipe creation application 405, and a dataset generation application 406.
- the platform 400 is built on the cloud, and applications that execute processing run on the OS 402 and middleware 403.
- the observation recipe creation application 405 executes processing equivalent to the classifier construction unit 109, observation recipe input unit 111, and observation recipe display unit 112 of the imaging system 100
- the dataset generation application 406 executes processing equivalent to the dataset generation system 101 of the imaging system 100.
- a user can access the platform from a terminal 410 via a network and use the functions of the applications built on the platform 400.
- the platform 400 includes a database 401, which stores data necessary for executing applications. Furthermore, the imaging device 200 is also connected via a network to enable data exchange with the platform 400. Note that the imaging system 100A and the observation recipe creation application 405 can also be referred to as the automatic imaging system 100A and the automatic observation recipe creation application 405.
- the platform 400 may be a server. Furthermore, the semiconductor device manufacturing apparatus 1 may be configured to include a platform 400 on which an application for generating a data set used for training a classifier that performs image recognition of charged particle beam images is implemented.
- FIG. 5 is a diagram showing an example of the charged particle beam image 501.
- the charged particle beam image 501 is, for example, an image of a cross section of a semiconductor device, and shows two insulating layers 505 extending in the horizontal direction (x-axis direction), ten trenches 504 extending in the vertical direction (y-axis direction), and fourteen electrode portions 506.
- the ROI 502 is shown surrounded by a solid-line frame
- the non-ROI 503 is shown surrounded by a dashed-line frame.
- the horizontal direction (x-axis direction) and vertical direction (y-axis direction) are set for convenience in explaining the charged particle beam image.
- explanations of the trenches 504, insulating layers 505, and electrode portions 506 may be omitted to facilitate understanding of this disclosure.
- ROI 502 includes the structure to be image-recognized by the imaging system 100, and in FIG. 5, as an example, it is an area including the tips of two trenches 504. There are five ROIs 502 in FIG. 5. Non-ROIs 503 are indicated by areas surrounded by dotted lines in FIG. 5. Non-ROIs 503 are areas within the charged particle beam image 501 excluding ROIs 502, and FIG. 5 shows 10 areas as an example.
- the method for setting non-ROIs 503 is not limited to the case shown in FIG. 5, and other areas may be set. With conventional methods, if a classifier is constructed in the classifier construction unit 109 using many non-ROI 503 areas, there is a possibility that a classifier with a low recognition success rate will be constructed.
- Figure 6 is a schematic diagram 601 showing the results of image recognition when a classifier is constructed by selecting non-ROI. ROIs are detected using the classifier, and four detected regions 602 are generated for a certain charged particle beam image.
- Figure 7 is a schematic diagram 603 showing the results of image recognition when a classifier is constructed without selecting non-ROI. As a result of detecting ROIs using the classifier, only one detection region 602 is generated for the same charged particle beam image as in Figure 6, and the three detection regions 602 found in Figure 6 are not included. It can be said that the recognition success rate is high for the classifier in Figure 6 and low for the classifier in Figure 7.
- Non-ROI candidate regions There are countless ways to select non-ROI 503, but a high recognition success rate can be achieved by using an appropriate generation method.
- a method is described in which multiple non-ROI candidate regions are first generated, and then three processes are combined to select a non-ROI from the multiple non-ROI candidate regions. Note that, in the following description, a case is described in which all non-ROI candidate regions have a common size, but the present disclosure is not limited to this case. The present disclosure can also be applied to cases in which the non-ROI candidate regions do not have a common size.
- FIGS. 8 to 10 are diagrams illustrating the calculation 302 of the non-ROI candidate region in FIG. 3 .
- FIG. 8 is a diagram illustrating a setting method for setting a non-ROI candidate region in the horizontal direction of a charged particle beam image.
- non-ROI candidate regions in a charged particle beam image 700 are surrounded by dotted lines. Let us assume that there are a first candidate region 701x, a second candidate region 702x, and a third candidate region 703x.
- Lx2 a ⁇ Lx1 (a ⁇ 1).
- Figure 9 is a diagram showing a setting method for setting non-ROI candidate regions in the vertical direction of a charged particle beam image.
- Non-ROI candidate regions can be set in the vertical direction using a method similar to that for the horizontal direction.
- the non-ROI candidate regions are designated as the first candidate region 701y, the second candidate region 702y, and the third candidate region 703y.
- ry is the vertical size of the non-ROI and dy is the distance from the top end (the side on the positive y-axis direction) of the first candidate region 701y to the bottom end (the side on the negative y-axis direction) of the second candidate region 702y
- non-ROI candidate regions can be set in the vertical direction.
- Figure 10 is a diagram showing a setting method for setting non-ROI candidate regions in the diagonal direction of a charged particle beam image. While Figure 8 shows the horizontal shift amount separately, and Figure 9 shows the vertical shift amount separately, it is also possible to set non-ROI candidate regions in the diagonal direction by combining the horizontal and vertical directions, as shown in Figure 10.
- Figure 10 shows an example of setting non-ROI candidate regions in the diagonal direction, with the first candidate region 701d, second candidate region 702d, and third candidate region 703d being set.
- the non-ROI candidate regions are calculated by the processor 108 of the dataset generation system 101 and stored in the dataset storage unit 103 or memory 114.
- the format of the information indicating the candidate regions can be an image file or a text file using coordinate information.
- the name of the charged particle beam image e.g., file name
- the coordinate information of the non-ROI candidate regions are stored in a format that can be referenced when generating the non-ROI (non-ROI generation 303 in Figure 3) (the format of reference will be described later using Figures 15 and 16).
- Non-ROI generation After setting the non-ROI candidate regions, the processor 108 generates the non-ROI (non-ROI generation 303 in FIG. 3 ).
- the non-ROI generation uses three methods: the overlap method, the ROI correlation method (ROI-non-ROI correlation coefficient method), and the non-ROI correlation method (non-ROI-non-ROI correlation coefficient method).
- the non-ROI is selected from the non-ROI candidates based on the ratio of the overlapping area between each ROI and each non-ROI candidate (overlap rate OR).
- the selection of the non-ROI from the non-ROI candidates is also performed based on a first correlation coefficient (correlation coefficient in the ROI-non-ROI correlation coefficient method) between each ROI and each non-ROI candidate.
- the selection of the non-ROI from the non-ROI candidates is performed by selecting two non-ROI candidates from the non-ROI candidates and based on a second correlation coefficient (correlation function of the non-ROI-non-ROI correlation coefficient method) between one of the two selected non-ROI candidates and the other of the two selected non-ROI candidates.
- the generation of the non-ROI (non-ROI generation 303 and determination 306 in FIG. 3 ) will be described with reference to FIGS. 11 and 12 .
- FIG. 11 is a diagram illustrating a case where an ROI and a non-ROI candidate region overlap.
- an ROI 801 is indicated by a solid-line frame
- a non-ROI candidate region 802 is indicated by a dotted-line frame.
- the number of ROIs registered in the charged particle beam image 800 is NR (NR is an integer) and the number of non-ROI candidate regions is NS (NS is an integer)
- the NCO overlap rates are calculated, and a threshold TOL for the overlap rate OR is set as a parameter to generate non-ROIs.
- the overlap rate threshold TOL is adjusted in non-ROI generation parameter adjustment 309 so that the difference between the number of non-ROIs calculated in non-ROI generation 303 and the target number of non-ROIs to be generated is small.
- the overlap rate OR calculation results are saved, for example, in a text file, and are stored in a format that can be referenced when generating non-ROIs, along with the name of the charged particle beam image and coordinate information for the non-ROI candidate region.
- FIG. 12 is a diagram showing a case where a charged particle beam image 900 includes an ROI 901 and non-ROI candidate regions 902 and 903.
- a selection method using the correlation coefficient between the ROI 901 and the non-ROI candidate region 902 (hereinafter referred to as the "ROI-non-ROI correlation coefficient method") will be described, and then a method for selecting and selecting two non-ROI candidate regions 902 and 903 (hereinafter referred to as the "non-ROI-non-ROI correlation coefficient method") will be described.
- a correlation coefficient is calculated between an ROI 901 registered in a charged particle beam image 900 and a non-ROI candidate region 902.
- the non-ROI candidate region 902 and the ROI 901 have the same number of pixels, but the present disclosure can also be applied even if the number of pixels differs. For example, if there is a difference between the two, one is converted to the same number of pixels as the other before calculation.
- the method using the sum of squared differences calculates the sum of squared errors of pixel values for each cell in two regions.
- T(x, y) be the pixel value at horizontal position x and vertical position y in the ROI 901
- I(x, y) be the pixel value at horizontal position x and vertical position y in the non-ROI candidate region 902
- rx be the number of pixels in the horizontal direction of the ROI 901
- ry be the number of pixels in the vertical direction.
- the sum of absolute differences RSAD is expressed by the following formula:
- the RSAD method requires no square calculations and therefore requires a short calculation time.
- the RNCC of the ROI 901 and the non-ROI candidate region 902 is expressed by the following equation: The RNCC value falls within the range of 0 to 1, and the closer the value is to 1, the more similar the images are determined to be.
- RZNCC average normalized cross-correlation
- the correlation coefficient derived by the ROI-non-ROI correlation coefficient method (hereinafter also referred to as the "ROI-non-ROI correlation coefficient") is calculated for only NCO results.
- Non-ROI selection requires sorting out images that differ from non-ROI from the ROI candidate regions.
- the ROI-non-ROI correlation coefficient threshold TCR1 is set to a value greater than 0 for RSSD and RSAD. It is also set to a value close to 0 for RNCC and -1 for RZNCC. By setting the threshold TCR1 to match the calculation method, non-ROI suitable for constructing a classifier can be selected from non-ROI candidate regions.
- NCO correlation coefficients are stored in the dataset storage unit 103.
- the calculation results of the correlation coefficients are saved in a text file, and are held in a format that can be referenced in the dataset storage unit 103, together with the name of the charged particle beam image and coordinate information of the non-ROI candidate region.
- Non-ROI-non-ROI correlation coefficient method Next, a method for selecting two non-ROI candidate regions and calculating a correlation coefficient to screen non-ROIs, i.e., the non-ROI-non-ROI correlation coefficient method, will be described.
- the calculation of the correlation coefficient derived by the non-ROI-non-ROI correlation coefficient method (hereinafter also referred to as the "non-ROI-non-ROI correlation coefficient”) is the same as that for the ROI-non-ROI correlation coefficient, and is performed using a non-ROI candidate region 902 and another non-ROI candidate region 903 as the calculation targets.
- RSSD sum of squared differences
- RSAD sum of absolute differences
- RNCC normalized correlation coefficient
- RZNCC mean normalized correlation coefficient
- the threshold TCR2 for the non-ROI-non-ROI correlation coefficient used to select non-ROIs varies depending on the method used to calculate the correlation coefficient, and is a value greater than 0 for RSSD and RSAD, a value between 0 and 1 for RCNN, and a value between -1 and 1 for RZNCC. Setting the threshold TNCC makes it possible to reduce the number of non-ROIs, thereby preventing a decrease in the recognition success rate for charged particle beam images of the classifier constructed by the classifier construction unit 109 depending on the number of non-ROIs generated.
- the threshold TCR2 for the non-ROI-non-ROI correlation coefficient is set to a value greater than 0 for RSSD and RSAD, 0 for RNCC, and close to -1 for RZNCC, just as with the threshold TCR1.
- the number of candidate non-ROI regions NS to be generated is generally set to approximately 2 to 5 times the number of ROIs. This number is affected by the amount of noise in the charged particle beam image and the number of gradations in the charged particle beam image. The less noise and the wider the gradations in the charged particle beam image, the more non-ROIs can be used to train the classifier.
- the number of non-ROIs to be generated is adjusted using the parameters of the overlap rate threshold TOL, the ROI-non-ROI correlation coefficient threshold TCR1, and the non-ROI-non-ROI correlation coefficient threshold TCR2.
- Non-ROI Generation Parameter Adjustment 3 is repeatedly performed using the processor 108 until the number of non-ROIs becomes appropriate, and the parameters and the number of generated non-ROIs at that time are stored as history in the memory 114 and the data set storage unit 103.
- the steepest descent method can be applied based on changes in the parameter setting values and the number of non-ROIs generated by those parameters until the number of non-ROIs reaches a target number.
- non-ROIs have been created using the user's experience and know-how, but with this disclosure, by setting parameters, it is possible to create non-ROIs without relying on experience or know-how. Furthermore, by using non-ROIs created in this way to train a classifier, it is possible to build a classifier that guarantees a certain level of classification performance.
- Classifier construction A system for learning a classifier from a dataset generated by a dataset generation system 101 will be described. Classifier construction 304 shown in FIG. 3 is performed using the generated non-ROI and registered ROI.
- the classifier construction method can be set depending on the type of charged particle beam image, the structure of the semiconductor device, and the like. For example, a cascade classifier may be used as the classifier, or RCNN (Region Based Convolutional Neural Networks) or Yolo (You Only Look Once), which utilize deep learning, may be used to construct the classifier.
- the classifier construction unit 109 constructs the classifier using the processor 108.
- the device used to construct the classifier varies depending on the construction method, and may be a central processing unit (CPU) or a graphical processing unit (GPU).
- the classifier constructed by the CPU or GPU is stored in the classifier storage unit 110.
- the classifier storage unit 110 may include, for example, a hard disk drive (HDD), a solid state drive (SSD), or memory, or may be cloud storage.
- observation recipe creation and observation An imaging system equipped with a classifier learning system will be described.
- the classifier constructed by the learning system (dataset generation system 101 and classifier construction unit 109) is stored in the classifier storage unit 110, referenced in the observation recipe, and used to classify images acquired by the imaging device 200.
- observation recipe creation 307 shown in FIG. 3 the observation recipe can be created using observation software installed in the computer system 234.
- the observation software also includes a GUI (graphical user interface), which is displayed on the observation recipe display unit 112.
- condition settings for causing the control unit 236 of the imaging device 200 to perform functions required for observation such as stage movement, focus adjustment, magnification setting, and image shift movement, are performed in the observation recipe input unit 111 and the observation recipe display unit 112.
- the condition settings for various functions of the observation recipe are transferred to the control unit 236 of the imaging device 200, and the imaging device 200 then performs imaging of the sample based on the observation recipe.
- the constructed classifier is used to recognize the charged particle beam image captured by the imaging device 200, and an ROI is detected in the charged particle beam image. According to the position of the detected ROI, the imaging device 200 performs stage movement, focus adjustment, magnification setting, image shift movement, etc., and observation is performed under conditions suitable for analyzing the ROI.
- the present disclosure makes it possible to use a classifier with a certain level of classification performance, making it possible to extract an ROI from a charged particle beam image, and essentially making it possible to observe a charged particle beam image without requiring user operation.
- Example 1 a method for setting non-ROI candidate regions in the horizontal direction, vertical direction, and a diagonal direction combining these directions was described for obtaining non-ROI candidate regions (calculating non-ROI candidate regions 302 in Figure 3).
- Example 2 with reference to Figures 13 and 14, a method for using random variables to set non-ROI candidate regions will be described.
- components that are the same as or equivalent to those in Example 1 above will be assigned the same reference numerals, and their description will be simplified or omitted.
- FIG. 13 is a diagram showing how to set a non-ROI candidate region in a charged particle beam image 1000.
- a first non-ROI candidate region 1001 is set in the charged particle beam image 1000.
- the non-ROI candidate region 1001 is a rectangular region bounded by dotted lines with a horizontal length of rx and a vertical length of ry.
- First, non-ROI candidate regions are set in a grid pattern within the charged particle beam image 1000, spaced at intervals of hx in the horizontal direction and hy in the vertical direction.
- the second non-ROI candidate region 1002 is one of the non-ROI candidate regions arranged in the grid pattern.
- each non-ROI candidate region is moved by a length of sx in the horizontal direction and a length of sy in the vertical direction.
- sx and sy are set for each non-ROI candidate region using, for example, random variables.
- the random variables can be generated, for example, from a library stored in the computer system 234.
- Figure 14 shows an example of randomly moving non-ROI candidate regions.
- Figure 14 shows the distribution of non-ROI candidate regions after movement, with the first non-ROI candidate region 1001 in Figure 13 becoming the first non-ROI candidate region 1003 after movement in Figure 14, and the second non-ROI candidate region 1002 in Figure 13 becoming the second non-ROI candidate region 1004 after movement in Figure 14.
- Figures 13 and 14 illustrate the case where the distances hx and hy are set so that the non-ROI candidate regions do not overlap, but hx and hy may also be set to a size such that the non-ROI candidate regions overlap, and this method also allows for the setting of sufficient non-ROI candidate regions.
- the generated non-ROI candidate regions are saved in the dataset storage unit 103 in the form of a text file.
- the overlap rate OR, the ROI-non-ROI correlation coefficient, and the non-ROI-non-ROI correlation coefficient it is possible to select from the generated non-ROI candidate regions and generate a non-ROI.
- Example 3 the GUI of the dataset generation system 101 will be described.
- the GUI is displayed, for example, on an output device in the computer system 234 of Figure 1.
- Figure 15 is a diagram showing an example of a GUI for registering an ROI.
- an input form into which information is entered by the user and check boxes and buttons that can be selected by clicking a mouse, are included.
- components that are the same as or equivalent to those in Example 1 above will be assigned the same reference numerals, and their explanations will be simplified or omitted.
- the ROI data registration window 1100 has an upload button 1102. Clicking this button displays the charged particle beam image in the charged particle beam image display area 1103.
- the file name of the currently displayed charged particle beam image is displayed in the input image name display area 1101. If the charged particle beam image has observation magnification information, the magnification is displayed in the magnification display area 1111.
- An example of a registered ROI area is the registration area 1106, which is highlighted with a dotted frame and has the registered number written in the upper left corner of the frame.
- two ROIs identified by numbers 1 and 2 are registered along with the charged particle beam image.
- the guide area 1104 displayed in a thick frame
- the mouse cursor 1105 positioned, and the guide area 1104 is positioned at the desired location on the charged particle beam image and then clicked (selected).
- a region size adjustment function display 1110 To the right of the ROI data registration window 1100 is a region size adjustment function display 1110, which allows you to change the size of the region to be registered in both the horizontal and vertical directions.
- the magnification link button 1107 is a button for automatically changing the size of the guide area of the registered area from the magnification of the previous charged particle beam image and the magnification of the new charged particle beam image when there are two or more charged particle beam images.
- the training data tag area 1109 shows tag information assigned as information in the registration area 1106.
- Tag information can include, for example, information about the semiconductor device structure, such as trench or fin, information about the type of semiconductor device, such as logic or memory, and information about the cross-sectional location, such as the top or bottom.
- the imaging system 100A shown in FIG. 4 by saving the ROI area registered in the database 401 in the dataset generation application 406 on the platform 400, it becomes possible to search for the ROI and charged particle beam image area based on the tag information. By constructing a classifier using registered images searched from the database 401 based on information such as logic and fin, it is possible to construct a classifier with a high recognition success rate even when the number of charged particle beam image samples is small.
- the user may have knowledge regarding the generation of non-ROIs required to construct a classifier, for example, knowledge regarding non-ROIs that should be selected from the information on the charged particle beam image and registered ROIs.
- the ROI data registration window 1100 used in FIG. 15 can also be used to select candidate non-ROI regions. For example, by displaying candidate non-ROI regions on the charged particle beam image in the charged particle beam image display area 1103 and allowing the user to select them, the user's knowledge regarding non-ROIs can be reflected in the generation of non-ROIs.
- Example 4 another example of the GUI of the dataset generation system 101 will be described.
- the GUI is displayed, for example, on an output device in the computer system 234 of Figure 1.
- the non-ROI generation parameter adjustment 309 of Figure 3 one method for adjusting the overlap rate OR threshold TOL, the ROI-non-ROI correlation coefficient threshold TCR1, and the non-ROI-non-ROI correlation coefficient threshold TCR2 to achieve the target number of non-ROIs is for the user to adjust using the GUI.
- Figure 16 will be used to explain the adjustment of generation parameters using the GUI.
- components that are the same or equivalent to those in Example 1 above will be assigned the same reference numerals, and their explanation will be simplified or omitted.
- FIG 16 shows an example of a GUI for adjusting parameters for non-ROI generation.
- the non-ROI data generation parameter adjustment window 1200 has a show button for calling up the charged particle beam image for registering the non-ROI, and a file name display section 1201 for displaying the name of the called file. For example, the user selects the show button and selects the charged particle beam image to register according to the file dialog that appears.
- the name of the selected charged particle beam image is displayed in the file name display section 1201, and the image itself is also displayed on the GUI.
- the base non-ROI display window 1202 displays the selected charged particle beam image and a non-ROI region 1203 generated using the reference parameters within a dotted line frame.
- the reference parameter display area 1205 displays the overlap rate OR threshold TOL, the ROI-non-ROI correlation coefficient threshold TCR1, and the non-ROI-non-ROI correlation coefficient threshold TCR2, and displays the number of non-ROIs calculated in each case.
- the new parameter display area 1204 also displays the non-ROI area generated using parameters adjusted by the user. The user adjusts the values of TOL, TCR1, and TCR2 using the adjustment buttons in the parameter adjustment area 1207. When the apply button is selected, the non-ROI area generated using the adjusted parameters is displayed in the new parameter display area 1204, allowing the results to be confirmed. The number of non-ROIs calculated using the adjusted parameters is also displayed in the new parameter non-ROI count display area 1206.
- the adjusted parameters are reflected in the reference parameters. If you are having trouble setting the initial parameters, you can enter the number of non-ROIs you want to generate in the target non-ROI number display area 1210 and click the Auto button 1209 to check the automatically generated non-ROI area in the new parameter non-ROI number display area 1206.
- an algorithm for automatic generation for example, it is possible to use a method of adjusting three threshold values using the steepest descent method until the target number of non-ROIs is reached.
- a data set generation device that generates a data set used for training a classifier that performs image recognition of a charged particle beam image, comprising: a region of interest (ROI) registered for the image recognition and a non-ROI candidate, which is a region not including the ROI, are generated based on the charged particle beam image;
- a data set generating device characterized in that non-ROIs are generated while the number of non-ROI candidates is reduced based on the ROI.
- a data set generating device characterized in that the non-ROIs are selected from the non-ROI candidates based on the proportion of an overlapping area between each of the ROIs and each of the non-ROI candidates.
- Aspect 3) In the data set generation device according to aspect 1 or aspect 2, The data set generating device is characterized in that the non-ROI is selected from the non-ROI candidates based on a first correlation coefficient relating to each of the ROIs and each of the non-ROI candidates.
- a data set generation method for generating a data set used for training a classifier that performs image recognition of a charged particle beam image comprising: generating non-ROI candidates, which are regions not including a region of interest (ROI) registered for the image recognition and the charged particle beam image, based on the ROI; generating non-ROIs while reducing the number of non-ROI candidates based on the ROIs.
- ROI region of interest
- a discriminator for performing image recognition of the image of the charged particle beam, and generating a dataset to be used for training the classifier by generating non-ROI candidates, which are regions that do not include a region of interest (ROI) that is registered for the image recognition and an image of the charged particle beam, and generating non-ROIs while reducing the number of non-ROI candidates based on the ROI.
- ROI region of interest
- An imaging method for imaging a sample using a charged particle beam comprising: performing image recognition of the image of the charged particle beam; generating a dataset to be used for learning to perform the image recognition;
- the imaging method is characterized in that the dataset is generated by generating non-ROI candidates, which are regions that do not include a region of interest (ROI) registered for image recognition and an image of the charged particle beam, and generating non-ROIs while reducing the number of non-ROI candidates based on the ROI.
- ROI 9 A microscope apparatus including the imaging device according to aspect 7, A microscope apparatus characterized in that the field of view is moved by detecting the ROI using an image of the charged particle beam.
- a dataset generation system for generating a dataset used for training a classifier that performs image recognition of a charged particle beam image comprising: generating non-ROI candidates, which are regions not including a region of interest (ROI) registered for the image recognition and the charged particle beam image, based on the ROI; and generating non-ROIs based on the ROIs while reducing the number of non-ROI candidates.
- ROI region of interest
- an imaging system for imaging a sample using a charged particle beam performing image recognition of the image of the charged particle beam; a step of generating a dataset to be used for learning to perform the image recognition, which is executed by a processor;
- the imaging system is characterized in that the dataset is generated by generating non-ROI candidates, which are regions that do not include a region of interest (ROI) that is registered for the image recognition and an image of the charged particle beam, and generating non-ROIs while reducing the number of non-ROI candidates based on the ROI.
- ROI region of interest
- a semiconductor device manufacturing system including a platform on which an application is implemented for generating a data set to be used for training a classifier that performs image recognition of a charged particle beam image, generating non-ROI candidates, which are regions not including a region of interest (ROI) registered for the image recognition and the charged particle beam image, based on the ROI; and generating non-ROIs based on the ROIs while reducing the number of non-ROI candidates.
- the semiconductor device manufacturing system according to claim 12 The semiconductor device manufacturing system is characterized in that the platform is a server.
- a semiconductor device manufacturing system, wherein the classifier is a cascade classifier.
Landscapes
- Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Analysing Materials By The Use Of Radiation (AREA)
Priority Applications (5)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020257023814A KR20260016453A (ko) | 2024-07-25 | 2024-07-25 | 데이터 세트 생성 장치, 데이터 세트 생성 방법, 촬상 장치, 촬상 방법, 현미경 장치, 데이터 세트 생성 시스템, 촬상 시스템 및 반도체 디바이스 제조 시스템 |
| CN202480008979.9A CN121753133A (zh) | 2024-07-25 | 2024-07-25 | 数据集生成装置、数据集生成方法、摄像装置、摄像方法、显微镜装置、数据集生成系统、摄像系统以及半导体器件制造系统 |
| PCT/JP2024/026566 WO2026023005A1 (ja) | 2024-07-25 | 2024-07-25 | データセット生成装置、データセット生成方法、撮像装置、撮像方法、顕微鏡装置、データセット生成システム、撮像システムおよび半導体デバイス製造システム |
| JP2025539928A JPWO2026023005A1 (cg-RX-API-DMAC7.html) | 2024-07-25 | 2024-07-25 | |
| TW114125499A TW202605870A (zh) | 2024-07-25 | 2025-07-04 | 資料集生成裝置、資料集生成方法、攝像裝置、攝像方法、顯微鏡裝置、資料集生成系統、攝像系統及半導體元件製造系統 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/JP2024/026566 WO2026023005A1 (ja) | 2024-07-25 | 2024-07-25 | データセット生成装置、データセット生成方法、撮像装置、撮像方法、顕微鏡装置、データセット生成システム、撮像システムおよび半導体デバイス製造システム |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2026023005A1 true WO2026023005A1 (ja) | 2026-01-29 |
Family
ID=98565099
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2024/026566 Pending WO2026023005A1 (ja) | 2024-07-25 | 2024-07-25 | データセット生成装置、データセット生成方法、撮像装置、撮像方法、顕微鏡装置、データセット生成システム、撮像システムおよび半導体デバイス製造システム |
Country Status (5)
| Country | Link |
|---|---|
| JP (1) | JPWO2026023005A1 (cg-RX-API-DMAC7.html) |
| KR (1) | KR20260016453A (cg-RX-API-DMAC7.html) |
| CN (1) | CN121753133A (cg-RX-API-DMAC7.html) |
| TW (1) | TW202605870A (cg-RX-API-DMAC7.html) |
| WO (1) | WO2026023005A1 (cg-RX-API-DMAC7.html) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2018163524A (ja) * | 2017-03-27 | 2018-10-18 | 株式会社日立ハイテクノロジーズ | 画像処理システム及び画像処理を行うためのコンピュータープログラム |
| JP7341241B2 (ja) * | 2019-08-30 | 2023-09-08 | 株式会社日立ハイテク | 計測システム、所定の構造を含む半導体の画像計測を行う際に用いる学習モデルを生成する方法、およびコンピュータに、所定の構造を含む半導体の画像計測を行う際に用いる学習モデルを生成する処理を実行させるためのプログラムを格納する記憶媒体 |
| CN118071631A (zh) * | 2024-02-29 | 2024-05-24 | 上海大学 | 一种基于深度学习的半导体sem图像降噪方法 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011129485A (ja) | 2009-12-21 | 2011-06-30 | Canon Inc | 画像表示装置 |
| JP7535193B2 (ja) | 2021-08-16 | 2024-08-15 | 株式会社日立ハイテク | 荷電粒子線装置 |
-
2024
- 2024-07-25 JP JP2025539928A patent/JPWO2026023005A1/ja active Pending
- 2024-07-25 CN CN202480008979.9A patent/CN121753133A/zh active Pending
- 2024-07-25 KR KR1020257023814A patent/KR20260016453A/ko active Pending
- 2024-07-25 WO PCT/JP2024/026566 patent/WO2026023005A1/ja active Pending
-
2025
- 2025-07-04 TW TW114125499A patent/TW202605870A/zh unknown
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2018163524A (ja) * | 2017-03-27 | 2018-10-18 | 株式会社日立ハイテクノロジーズ | 画像処理システム及び画像処理を行うためのコンピュータープログラム |
| JP7341241B2 (ja) * | 2019-08-30 | 2023-09-08 | 株式会社日立ハイテク | 計測システム、所定の構造を含む半導体の画像計測を行う際に用いる学習モデルを生成する方法、およびコンピュータに、所定の構造を含む半導体の画像計測を行う際に用いる学習モデルを生成する処理を実行させるためのプログラムを格納する記憶媒体 |
| CN118071631A (zh) * | 2024-02-29 | 2024-05-24 | 上海大学 | 一种基于深度学习的半导体sem图像降噪方法 |
Also Published As
| Publication number | Publication date |
|---|---|
| JPWO2026023005A1 (cg-RX-API-DMAC7.html) | 2026-01-29 |
| KR20260016453A (ko) | 2026-02-03 |
| CN121753133A (zh) | 2026-03-27 |
| TW202605870A (zh) | 2026-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102680501B1 (ko) | 화상 평가 장치 및 방법 | |
| US9488815B2 (en) | Pattern evaluation method and pattern evaluation device | |
| US7888638B2 (en) | Method and apparatus for measuring dimension of circuit pattern formed on substrate by using scanning electron microscope | |
| JP5525421B2 (ja) | 画像撮像装置および画像撮像方法 | |
| TWI750514B (zh) | 電子束檢測設備、用於對準一晶圓影像與一參考影像之方法及相關之非暫時性電腦可讀媒體 | |
| JP2023549733A (ja) | 能動学習に基づく欠陥位置の識別 | |
| JP2011137901A (ja) | パターン計測条件設定装置 | |
| TWI870221B (zh) | 非暫時性電腦可讀媒體 | |
| US20230222764A1 (en) | Image processing method, pattern inspection method, image processing system, and pattern inspection system | |
| US12474166B2 (en) | Pattern inspection/measurement device, and pattern inspection/measurement program | |
| US20250132123A1 (en) | Charged Particle Beam Device | |
| US7834316B2 (en) | Method for adjusting imaging magnification and charged particle beam apparatus | |
| TWI848804B (zh) | 尺寸計測系統、推測系統以及尺寸計測方法 | |
| US20250385070A1 (en) | Scanning electron microscopy (sem) back-scattering electron (bse) focused target and method | |
| KR20260016453A (ko) | 데이터 세트 생성 장치, 데이터 세트 생성 방법, 촬상 장치, 촬상 방법, 현미경 장치, 데이터 세트 생성 시스템, 촬상 시스템 및 반도체 디바이스 제조 시스템 | |
| WO2024170211A1 (en) | Method and system for identifying a center of a pattern using automatic thresholding | |
| JP2015203628A (ja) | 荷電粒子線装置及び座標補正方法 | |
| TW202105552A (zh) | 畫像產生方法 | |
| US20240240937A1 (en) | Depth Measurement Device, Depth Measurement System, and Depth Index Calculation Method | |
| WO2021210505A1 (ja) | パターンマッチング方法 | |
| KR20250140104A (ko) | 계측 시스템, 계산기 및 계측 방법 | |
| JP2024047481A (ja) | 半導体観察システムおよびオーバーレイ計測方法 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| ENP | Entry into the national phase |
Ref document number: 2025539928 Country of ref document: JP Kind code of ref document: A |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2025539928 Country of ref document: JP |
|
| WWP | Wipo information: published in national office |
Ref document number: 1020257023814 Country of ref document: KR |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 24948702 Country of ref document: EP Kind code of ref document: A1 |