WO2021255819A1 - 画像処理方法、形状検査方法、画像処理システム及び形状検査システム - Google Patents

画像処理方法、形状検査方法、画像処理システム及び形状検査システム Download PDF

Info

Publication number
WO2021255819A1
WO2021255819A1 PCT/JP2020/023554 JP2020023554W WO2021255819A1 WO 2021255819 A1 WO2021255819 A1 WO 2021255819A1 JP 2020023554 W JP2020023554 W JP 2020023554W WO 2021255819 A1 WO2021255819 A1 WO 2021255819A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
captured image
data
unit
statistic
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.)
Ceased
Application number
PCT/JP2020/023554
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
将記 大内
昌義 石川
康隆 豊田
博之 新藤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hitachi High Tech Corp
Original Assignee
Hitachi High Tech Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hitachi High Tech Corp filed Critical Hitachi High Tech Corp
Priority to US18/009,890 priority Critical patent/US20230222764A1/en
Priority to PCT/JP2020/023554 priority patent/WO2021255819A1/ja
Priority to KR1020227041722A priority patent/KR102780234B1/ko
Priority to JP2022531135A priority patent/JP7390486B2/ja
Priority to CN202080101502.7A priority patent/CN115698690A/zh
Priority to TW110121442A priority patent/TWI777612B/zh
Publication of WO2021255819A1 publication Critical patent/WO2021255819A1/ja
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
    • 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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • 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
    • G06T7/0006—Industrial image inspection using a design-rule based approach
    • 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
    • G06T7/001—Industrial image inspection using an image reference approach
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/758—Involving statistics of pixels or of feature values, e.g. histogram matching
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/761—Proximity, similarity or dissimilarity measures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/772—Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/40—Imaging
    • G01N2223/401—Imaging image processing
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/40—Imaging
    • G01N2223/418—Imaging electron microscope
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/60—Specific applications or type of materials
    • G01N2223/611—Specific applications or type of materials patterned objects; electronic devices
    • G01N2223/6116—Specific applications or type of materials patterned objects; electronic devices semiconductor wafer
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N2223/00—Investigating materials by wave or particle radiation
    • G01N2223/60—Specific applications or type of materials
    • G01N2223/646—Specific applications or type of materials flaws, defects
    • G01N2223/6462—Specific applications or type of materials flaws, defects microdefects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10056—Microscopic image
    • G06T2207/10061—Microscopic image from scanning electron microscope
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30148—Semiconductor; IC; Wafer
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
    • G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
    • G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]

Definitions

  • the present invention relates to an image processing method, a shape inspection method, an image processing system, and a shape inspection system.
  • a target article is a semiconductor circuit.
  • circuit In the inspection and measurement of a semiconductor circuit (hereinafter, also simply referred to as “circuit”), the process of comparing the design data of the circuit and the photographed image data (hereinafter, also simply referred to as “photographed image”) and aligning the positions is performed. Will be. This process is called pattern matching.
  • the circuit has shape deformation due to various conditions set in the manufacturing process. Further, in the captured image of the circuit, a difference in image quality (contrast change, generation of image noise, etc.) occurs due to various conditions set in the imaging process. In addition, even under the same conditions, the shape of the circuit and the image quality of the captured image change due to the variation.
  • Patent Document 1 is a computer mounting method for generating a simulation image from design information, and the characteristics of the design information of the object are determined by inputting the design information to two or more encoder layers of the generated model. Disclosed include a step and a step of generating one or more simulation images by inputting the determined features into two or more decoder layers of the generation model. Here, the simulation image shows the design information that appears in the image of the object generated by the image system. Patent Document 1 also discloses that the generative model can be replaced by a convolutional neural network (CNN).
  • CNN convolutional neural network
  • Patent Document 2 describes a pattern for inspecting an image of an inspection target pattern using a classifier configured by machine learning based on an image of an inspection target pattern of an electronic device and data used for manufacturing the inspection target pattern. It is an inspection system that stores multiple pattern images of electronic devices and pattern data used to manufacture patterns of electronic devices, and based on the stored pattern data and pattern images, it is possible to perform machine learning from multiple pattern images. By selecting the pattern image for learning to be used, it is disclosed that the labor of creating the true value of the training data can be saved, the training data can be reduced in size, and the learning time can be shortened.
  • Patent Document 2 reduces the amount of learning data during machine learning and makes it possible to shorten the learning time, and the obtained learning data can be used for actual inspection. If it is used in such cases, it is considered necessary to improve the data processing method separately.
  • An object of the present invention is to shorten the time required for the estimation when collating the simulated image estimated from the design data with the actually captured image, and to perform the collation in real time.
  • the image processing method of the present invention uses a system including an input receiving unit, an estimation unit, and an output unit to collate an estimated captured image obtained from reference data of a sample with an actual captured image of the sample. It is a method to acquire the data of the estimated photographed image used at the time, and the input receiving unit receives the input of the reference data, the process information of the sample, and the trained model data, and the estimation unit , An estimation process that calculates a photographed image statistic that represents the probability distribution of the values that the photographed image data can take using reference data, process information, and model data, and an output process that the output unit outputs the photographed image statistic. And, the estimated captured image can be generated from the captured image statistics.
  • the time required for the estimation can be shortened and the collation can be performed in real time.
  • the present invention relates to an image processing technique for processing image data. Among them, in particular, the present invention relates to an image processing technique applicable to inspection using image data.
  • An example of an inspection target includes a semiconductor circuit.
  • the image processing method and the image processing system calculate a photographed image statistic representing a probability distribution of values that can be taken by each pixel of the photographed image as a variation of the photographed image corresponding to the design data and process information. ..
  • the image processing system is equipped with a CNN model that can calculate the probability distribution for each pixel representing the variation of the captured image from the design data and the process information.
  • CNN is an abbreviation for Convolutional Neural Network.
  • the image processing system uses the calculated probability distribution for each pixel to evaluate the effect of process information on the circuit or its captured image.
  • the shape inspection system creates a template image that can be used for pattern matching using the calculated probability distribution for each pixel, and performs pattern matching with high accuracy.
  • the present embodiment also includes determining parameters (model data) included in a mathematical model using CNN in machine learning or the like.
  • semiconductor circuits In addition to semiconductor circuits, it can be applied to various articles such as automobile parts (pistons, etc.), trays, containers such as bottles, and liquid crystal panels.
  • the shape includes the size, length, and the like of the sample (article).
  • the image processing method described below is a photographed image of a circuit manufactured under the conditions of the design data and the process information using the design data which is the reference data of the circuit, the process information, and the trained model data. It relates to an image processing method for directly estimating a variation of the above, and an image inspection system using the same.
  • the correspondence relationship between the design data image obtained by imaging the design data, the process information, and the photographed image of the circuit is learned by using machine learning, and the model data obtained by the learning is obtained.
  • An example of a method of directly estimating the variation of the captured image of the circuit corresponding to these from an arbitrary design data image and an arbitrary process information is shown.
  • the variation of the captured image of the circuit is treated as a statistic (mean, variance, etc.) that defines the probability distribution of the pixel values that each pixel of the image can take.
  • the design data of an arbitrary circuit, the process information, and the trained model data are accepted as inputs, and the variation of the captured image of the circuit corresponding to the combination of the design data and the process information is directly estimated as a statistic of the pixel value.
  • a device or measurement inspection system equipped with a function for outputting estimated statistics will be described with reference to the drawings. More specifically, an apparatus including a length measuring scanning electron microscope (Critical Measurement-Scanning Electron Microscope: CD-SEM), which is a kind of measuring apparatus, and a system thereof will be described.
  • a charged particle beam device will be exemplified as a device for forming a photographed image of a circuit.
  • SEM scanning electron microscope
  • a focused ion beam (FIB) device to be formed may be adopted as a charged particle beam device.
  • FIB focused ion beam
  • FIG. 13 is a schematic configuration diagram showing an example of a semiconductor measurement system, and shows a measurement / inspection system in which a plurality of measuring devices or inspection devices are connected to a network.
  • the measurement / inspection system is included in the image processing system or the shape inspection system.
  • the system shown in this figure includes a scanning electron microscope 1301 (CD-SEM) for measuring length that measures pattern dimensions of semiconductor wafers, photomasks, etc., and an image obtained by irradiating a sample with an electron beam.
  • a defect inspection device 1302 for extracting defects based on comparison with a reference image registered in advance, a condition setting device 1303, a simulator 1304, and a storage medium 1305 (storage unit) are included. And these are connected via a network.
  • the condition setting device 1303 has a function of setting a measurement position, measurement conditions, etc. on the design data of the semiconductor device.
  • the simulator 1304 has a function of simulating the quality of a pattern based on the design data of a semiconductor device, the manufacturing conditions of a semiconductor manufacturing apparatus, and the like.
  • the storage medium 1305 stores layout data of the semiconductor device, design data in which manufacturing conditions are registered, and the like.
  • the storage medium 1305 may store the trained model data.
  • the design data is expressed in, for example, GDS format or OASIS (registered trademark) format, and is stored in a predetermined format.
  • the type of design data does not matter as long as the software for displaying the design data can display the format and can handle it as graphic data.
  • the storage medium 1305 may be built in the control device of the measuring device or the inspection device, the condition setting device 1303, or the simulator 1304.
  • the scanning electron microscope 1301 for length measurement and the defect inspection device 1302 are provided with their respective control devices, and the control required for each device is performed.
  • a setting function may be incorporated.
  • the electron beam emitted from the electron source is focused by a multi-stage lens, and the focused electron beam is scanned one-dimensionally or two-dimensionally on the sample by a scanning deflector.
  • Secondary electrons (Secondary Electron: SE) or backscattered electrons (Backscattered Electron: BSE) emitted from the sample by scanning the electron beam are detected by the detector and synchronized with the scanning of the scanning deflector, such as a frame memory. It is stored in the storage medium of. The image signals stored in this frame memory are integrated by an arithmetic unit built in the control device. Also, scanning with a scanning deflector is possible for any size, position and orientation.
  • SE Secondary Electron
  • BSE Backscattered Electron
  • the above control and the like are performed by the control device of each SEM, and the images and signals obtained as a result of scanning the electron beam are sent to the condition setting device 1303 via the communication line network.
  • control device that controls the SEM and the condition setting device 1303 are described as separate bodies, but the present invention is not limited to this.
  • the condition setting device 1303 may collectively perform the device control and the measurement process, or each control device may perform the SEM control and the measurement process together.
  • condition setting device 1303 or the control device stores a program for executing the measurement process, and the measurement or the calculation is performed according to the program.
  • condition setting device 1303 is provided with a function of creating a program (recipe) for controlling the operation of the SEM based on the design data of the semiconductor, and functions as a recipe setting unit. Specifically, on the design data, pattern contour line data, or simulated design data, positions for performing necessary processing for SEM such as desired measurement points, autofocus, autostigma, and addressing points. Etc. are set. Then, based on the setting, a program for automatically controlling the sample stage, the deflector, etc. of the SEM is created.
  • a program for automatically controlling the sample stage, the deflector, etc. of the SEM is created.
  • a processor that extracts information on the template area from the design data and creates a template based on the extracted information, or a program that creates a template with a general-purpose processor is built-in or It is remembered.
  • this program may be distributed via a network.
  • FIG. 14 is a schematic configuration diagram showing a scanning electron microscope.
  • the scanning electron microscope shown in this figure has an electron source 1401, an extraction electrode 1402, a condenser lens 1404 which is a form of a focusing lens, a scanning deflector 1405, an objective lens 1406, a sample table 1408, a conversion electrode 1412, a detector 1413, and a control. It is equipped with a device 1414 and the like.
  • the electron beam 1403 drawn from the electron source 1401 by the extraction electrode 1402 and accelerated by the acceleration electrode (not shown) is focused by the condenser lens 1404. Then, the scanning deflector 1405 scans the sample 1409 one-dimensionally or two-dimensionally.
  • the electron beam 1403 is decelerated by the negative voltage applied to the electrodes provided on the sample table 1408, focused by the lens action of the objective lens 1406, and irradiated onto the sample 1409.
  • electrons 1410 such as secondary electrons and backscattered electrons are emitted from the irradiated portion.
  • the emitted electrons 1410 are accelerated toward the electron source by the acceleration action based on the negative voltage applied to the sample, collide with the conversion electrode 1412, and generate secondary electrons 1411.
  • the secondary electrons 1411 emitted from the conversion electrode 1412 are captured by the detector 1413, and the output I of the detector 1413 changes depending on the amount of the captured secondary electrons.
  • the brightness of a display device (not shown) changes according to the output I.
  • the image of the scanning region is formed by synchronizing the deflection signal to the scanning deflector 1405 with the output I of the detector 1413.
  • the scanning electron microscope illustrated in this figure is provided with a deflector (not shown) that moves the scanning region of the electron beam.
  • the control device 1414 controls each configuration of the scanning electron microscope, has a function of forming an image based on the detected electrons, and a pattern formed on the sample based on the intensity distribution of the detected electrons called a line profile. It has a function to measure the pattern width.
  • Statistic estimation processing or model data learning processing can also be executed by an arithmetic unit built in the control device 1414 or an arithmetic unit having an image processing function. Further, it is also possible to execute the process by an external arithmetic unit (for example, the condition setting device 1303) via the network.
  • the processing division between the arithmetic unit built in the control device 1414 or the arithmetic unit having an image processing function and the external arithmetic unit can be appropriately set, and is not limited to the above-mentioned example.
  • FIG. 1A is a diagram showing an example of a photographed image obtained from design data and process information.
  • a photographed image 104 of the circuit can be obtained from the design data image 101 and the predetermined process information 102.
  • the design data image 101 is one format of reference data showing the wiring of the circuit and its arrangement.
  • FIG. 1B is a diagram showing another example of a photographed image obtained from design data and process information.
  • a photographed image 105 of the circuit can be obtained from the design data image 101 and the predetermined process information 103.
  • a design data image that is an image of the design data described by CAD data or the like is used.
  • a binary image in which the wiring portion of the circuit and the other regions are painted separately.
  • a semiconductor circuit there is also a multi-layer circuit having two or more layers of wiring.
  • the wiring is one layer, it can be used as a binary image of the wiring and the other area, and if the outer line is two layers, it can be used as a binary image of the wiring portion of the lower layer and the upper layer and the other area.
  • the design data image is an example of reference data, and is not limited thereto.
  • Process information 102 and 103 are one or more types of parameters used in each process from circuit manufacturing to photographing.
  • the process information is treated as a real value.
  • Specific examples of the process include an etching process, a lithography process, and a photographing process by SEM.
  • Specific examples of the parameters include exposure amount (Dose) and focus (Focus) in the case of the lithography process.
  • the photographed images 104 and 105 of the circuit are photographed images of the circuit manufactured by using the process information 102 and 103, respectively, based on the design data shown in the design data image 101.
  • the photographed image handled in this embodiment is treated as a grayscale image photographed by SEM. Therefore, the captured image itself has an arbitrary height and width, and the channel of the image is 1.
  • the circuit is deformed to the extent that it is electrically acceptable without any problem due to the parameters of the manufacturing process, and the circuit shape does not match the design data.
  • the captured image of the circuit differs in how the circuit is captured depending on the parameters of the imaging process using the SEM. Therefore, although the captured image 104 and the captured image 105 correspond to the same design data image 101, the process information is different, so that the amount of deformation of the same circuit is not the same, and the image quality of the image is also different.
  • the image quality of the image there are noise and contrast change.
  • the reference data is a design data image
  • the process information is a real value indicating the parameter value
  • the photographed image of the circuit is an image taken by SEM, but these are not limited.
  • FIG. 2 is a configuration diagram showing an image processing system of this embodiment.
  • the image processing system includes an input reception unit 201, an estimation unit 202, and an output unit 203. Further, the image processing system appropriately includes a storage unit.
  • the input receiving unit 201 receives the input of the reference data 204, the process information 205, and the trained model data 206. Then, the estimation unit 202 converts the input received by the input reception unit 201 into a statistic that captures variations of the captured image of the circuit. The output unit 203 outputs this statistic as the captured image statistic 207.
  • the reference data 204 describes the shape and arrangement of the wiring of the circuit, and in this embodiment, it is treated as design data or design data which is an image of the design data.
  • the estimation unit 202 converts the input received by the input reception unit 201 into a statistic representing a variation of the captured image of the circuit corresponding to the input reception unit 201.
  • the estimation unit 202 includes a mathematical model in which parameters are set by the model data 206 and the captured image statistics are estimated from the design data image and the process information.
  • CNN convolutional neural network
  • an encoder is composed of two or more convolutional layers and a pooling layer
  • a decoder is composed of two or more deconvolution layers.
  • the model data becomes the weight (conversion parameter) of the filter of each layer possessed by CNN.
  • the mathematical model for estimating the photographed image statistic can be used other than the CNN model, and is not limited thereto.
  • the input receiving unit 201 reads the reference data 204, the process information 205, and the model data 206 according to a predetermined format.
  • the output unit 203 outputs the calculation result of the estimation unit 202 in a predetermined format.
  • the input reception unit 201, the estimation unit 202, and the output unit 203 shown in this figure are a part of the components of the system shown in this embodiment, and are distributed and arranged in a plurality of computers connected by a network. You may. Further, the data including the input reference data 204, the process information 205, and the trained model data 206 may be input from the outside by the user, but may be stored in a predetermined storage device. good.
  • FIG. 8A is a diagram showing an example of a design data image.
  • the design data image 801 has a wiring 811 composed of white pixels (squares). Since the design data image 801 is based on the design data, ideally orthogonal wiring 811 is shown.
  • FIG. 8B to 8D are diagrams showing an example of a captured image corresponding to the design data image 801 of FIG. 8A.
  • FIG. 8B a captured image 802 corresponding to the design data image 801 is shown.
  • FIG. 8C a captured image 803 corresponding to the design data image 801 is shown.
  • FIG. 8D a captured image 804 corresponding to the design data image 801 is shown.
  • the captured image 802 of FIG. 8B, the captured image 803 of FIG. 8C, and the captured image 804 of FIG. 8D are affected by at least one of the manufacturing conditions and the photographing conditions. Therefore, the shape of the wiring 811 is different in each of the captured images 802, 803, and 804. In other words, the difference in the shape of the wiring 811 is caused by both the manufacturing cycle and the photographing cycle. Therefore, when a certain pixel on the design data image takes an arbitrary luminance value, there are a plurality of luminance values that the same pixel on the captured image can take.
  • the luminance value that each pixel can take is an integer from 0 to 255.
  • the luminance value distribution represents the frequency with respect to the luminance value of 0 to 255. Examples of statistics include the mean and standard deviation if the luminance value distribution is normal, and the arrival rate if the Poisson distribution.
  • FIG. 10A is a diagram showing an example of a design data image.
  • the pixel 1001 of interest and the peripheral region 1002 thereof are shown in the design data image 1000a.
  • FIG. 10B is a diagram showing an example of a photographed image.
  • the pixel 1003 is shown in the captured image 1000b.
  • the pixel 1001 of interest in FIG. 10A and the pixel 1003 in FIG. 10B are located at the same coordinates when aligned to compare the images of the circuit (sample).
  • the pixel value statistics that the pixel 1003 can take are estimated from the pixel values of the pixel of interest 1001 and the peripheral region 1002. This is because when calculating with the convolutional layer of CNN, the calculation including the surrounding pixels is performed.
  • the size of the peripheral region 1002 is determined by the filter size, stride size, and the like of the CNN.
  • 3A and 3B are block diagrams showing the flow of data processed in the image processing system of this embodiment.
  • the input receiving unit 201 receives the input of the design data image 101, the process information 102 or 103, and the model data 301, and the estimation unit 202 defines the variation of the captured image of the circuit corresponding to this input. It is converted into a quantity, and the output unit 203 outputs the calculated captured image statistic 302 or 305.
  • FIG. 9 is a graph showing an example of the expression format of the photographed image statistic.
  • the captured image statistic is represented as a probability density function 901, which is a probability distribution of pixel values in each pixel.
  • the probability density function 901 is a probability distribution of pixel values in each pixel.
  • the average and standard deviation values of the probability density function 901 can be obtained.
  • the average image 303 and the standard deviation image 304 can be obtained.
  • the probability density function 901 is represented by a probability density function of the appearance frequency for a pixel value that can be taken by each pixel on a captured image of a certain circuit. Specifically, if the captured image is grayscale, the distribution can be defined as the appearance frequency of 256 different pixel values. The statistic may be in units other than pixels.
  • the probability density function 901 can be uniquely defined by its mean and standard deviation (or variance).
  • the average image 303 and the standard deviation image 304 are examples of the output format of the captured image statistic 302. If the captured image statistic is a Gaussian distribution for each pixel, the average and standard deviation values can be estimated and output as an average image and a standard deviation image converted into an image.
  • the average image 303 is obtained by converting the average of the Gaussian distribution of each pixel into a grayscale image. Assuming that the captured image statistic 302 is a Gaussian distribution, the average value of the distribution matches the mode. Therefore, the average image 303 obtained uses the design data image 101 and under the conditions of the process information 102. The captured image has the most average circuit shape.
  • the standard deviation image 304 is a grayscale image converted from the standard deviation of the Gaussian distribution of each pixel.
  • the standard deviation image 304 is a grayscale image converted from the standard deviation of the Gaussian distribution of each pixel.
  • the shape of the manufactured circuit and the image quality of the captured image depend on the process information.
  • FIG. 4 is a flow chart showing an example of learning processing for creating model data used for estimating captured image statistics.
  • the learning process is performed by the machine learning department.
  • the user inputs model data (S401), and the user inputs a design data image and process information (S402). Then, the machine learning unit estimates and outputs the captured image statistics from these inputs (S403).
  • the input by the user does not have to be by the user, and may be performed by, for example, automatically selecting the data possessed by the predetermined storage unit and reading the data by the machine learning unit.
  • the photographed image which is the teacher data is input (S405). Then, the captured image (teacher data) is compared with the estimated image information (photographed image statistic) (S406), and the model data is updated according to the comparison result (S407).
  • the comparison method there is a method of converting estimated image information (photographed image statistic) into an "estimated photographed image” and comparing them. In other words, the estimated captured image can be generated from the captured image statistic.
  • the input of S401 can be omitted.
  • S401 and S402 are collectively referred to as "input process”. Further, S403 is also referred to as an "estimation process”. Further, S403 can be said to be an "output process" from the viewpoint of processing corresponding to the output unit 203 of FIG.
  • the model data input in S401, updated in S407, and stored in S408 is the weight of the filter of the convolution layer or the deconvolution layer used in S403. In other words, it is the configuration information of each layer of the CNN encoder and decoder used in S403, and the conversion parameters (weights) thereof. This conversion parameter is determined to minimize the value of the loss function calculated using the captured image statistic estimated in S403 and the captured image input in S405 in the comparison process of S406.
  • the model data in S401 can be estimated from the design data image and the process information after the learning process.
  • specific examples of the loss function include mean square error, cross entropy error, and the like.
  • the reference data input in S402 is a design data image in this embodiment.
  • Examples of the learning necessity determination in S404 include whether the number of times of learning is repeated more than the specified number of times, and whether the loss function used for learning has converged.
  • the model data saved in S408 is saved by outputting the weight of each layer of CNN to a file in a predetermined format.
  • the estimated photographed image statistic (estimated photographed image) is compared with the photographed image.
  • the training data set (learning data set) requires a pair of the aligned design data image and the captured image.
  • the number of images in the training data set is large.
  • the shape of the circuit used for learning and the shape of the circuit used for evaluation are similar.
  • the design data received by S401 and the captured image received by S405 are aligned.
  • the position on the image is adjusted so that the circuit pattern matches the design data image for learning and the captured image of the circuit that manufactured the image.
  • the alignment method there is a method of obtaining the outline of the wiring of the design data image and the photographed image and performing positioning so that the centers of gravity of the figures surrounded by the outline are aligned.
  • the process information used in the learning process or the process information used in the estimation process of the captured image statistic using the trained model data only the parameters to be considered may be used, or the manufacturing process or the imaging process may be used. All parameters may be used. However, if the process information increases, the amount of calculation in the CNN increases, so it is preferable to use only the minimum necessary parameters from the viewpoint of processing speed.
  • the machine learning unit determines the necessity of learning for the model data, and when it is determined that the necessity of learning is necessary in the learning necessity determination process, the reference data for learning, the process information, and the photographed image are determined.
  • the storage unit stores the parameters used by the estimation unit when calculating the captured image statistics as model data.
  • FIG. 6A schematically shows an example of converting a design data image into a feature amount.
  • the design data image 601 is a binary image obtained by imaging design data such as CAD.
  • the grid-separated grids represent the respective pixels that make up the image.
  • the feature amount 602 is calculated by using the CNN convolution layer (encoder layer) of the photographed image statistic estimation unit (estimation unit) for the design data image 601 and is represented by a matrix.
  • the feature amount 602 has design information as to whether each pixel on the design data image belongs to the wiring portion or other than the wiring portion, and design information regarding the shape and arrangement of the wiring such as near the edge or the corner of the wiring.
  • the feature quantity 602 can be represented as a three-dimensional matrix having a height, a width, and a channel. At this time, the height, width, and channel of the feature amount 602 calculated from the design data image 601 are determined depending on the number of convolutional layers possessed by the CNN, its filter size, stride size, padding size, and the like.
  • FIG. 6B shows an example of the combination format between the feature amount and the process information.
  • the feature amount 602 of FIG. 6A is represented as a three-dimensional matrix combined with the process information 603, 604, 605.
  • the process information 603, 604, and 605 are given as a matrix in which the height and width of the feature amount 602 are equal and the channel size is 1, and are displayed as a three-dimensional matrix, in which real values indicating manufacturing conditions and photographing conditions are given. Is. Specifically, a three-dimensional matrix in which the values of all the elements are 1, the height and width are equal to the feature amount 602, and the channel size is 1, is prepared, and this is multiplied by a real value indicating manufacturing conditions and shooting conditions. There is a three-dimensional matrix.
  • the design data image 601 is converted into the feature amount 602 by the convolutional layer (encoder layer) of the CNN, and the feature amount 602 and the process information 603, 604, 605 are converted. Are combined in the order of channels, and the combined products are input to the deconvolutional layer (decoder layer) of the CNN.
  • the process information to be specified may be one or two or more, and this is not limited. It was
  • FIG. 7A is a diagram showing an example of the input format in this embodiment.
  • the design data image 701 is an image of design data such as CAD.
  • An example is a binary image in which the wiring part and the space part of the circuit are painted separately.
  • the wiring has two or more layers. For example, if the wiring is one layer, it can be used as a binary image of the wiring portion and the space portion, and if the wiring is two layers, it can be used as a binary image of the lower layer wiring portion, the upper layer wiring portion, and the space portion.
  • the design data image is an example of a reference image and is not limited thereto. It was
  • the process information 702 and the process information 703 give real values indicating manufacturing conditions and shooting conditions as images of the same size as the design data image. Specifically, a matrix in which the values of all the elements are 1 and the image size is the same as the design data is multiplied by a real value indicating manufacturing conditions and shooting conditions can be mentioned. It was
  • FIG. 7B is a diagram showing an example of the coupling form in this embodiment.
  • An example of the method of inputting the CNN possessed by the captured image statistic estimation unit is to combine the design data image 701, the process information 702, and the process information 703 in the order of the image channels.
  • the process information to be used may be one or two or more, and this is not limited.
  • the method of combining the process information shown in FIGS. 6A to 7B does not limit this.
  • Another example is to evaluate the influence of process information on the circuit or its captured image.
  • the captured image statistic is calculated by changing only one of the parameters of the process information.
  • the change in the process information causes little change in the average image and the standard deviation value is small in the standard deviation image, it can be said that the influence of the parameter on the shape deformation of the circuit and the degree of its variation is small.
  • the process information is set to two and only one of them is changed is described, but this is not limited, and the number of parameters of the process information may be one or three. The above may be sufficient. Further, only one parameter in the process information may be changed and executed, or a plurality of parameters may be changed and executed.
  • FIG. 5 is a configuration diagram showing the flow of data processed in the shape inspection system, and shows an example of processing for performing pattern matching using captured image statistics.
  • the shape inspection system shown in this figure includes an input reception unit 501 for inputting a captured image statistic 207, an input reception unit 505 for inputting a captured image 504, a template image creation unit 502, and a pattern matching processing unit 503. , And an output unit 506.
  • the data flow shown in this figure is an example of a shape inspection method.
  • the photographed image 504 is a photographed image (actual photographed image) that is the target of pattern matching.
  • the captured image statistic 207 receives input as shown in FIG. 2 for process information when the circuit of the captured image 504 is manufactured and captured, a design data image of the circuit of the captured image 504, and model data created by the learning process. It is received by unit 201, calculated by estimation unit 202, and output by output unit 203.
  • the pattern matching process shown in this figure is performed as follows.
  • the input receiving unit 501 receives the captured image statistic 207
  • the template image creating unit 502 converts the captured image statistic 207 into a template image, and passes it to the pattern matching processing unit 503.
  • the input receiving unit 505 receives the captured image 504 and delivers it to the pattern matching processing unit 503.
  • the pattern matching processing unit 503 performs pattern matching processing using the captured image 504 and the template image. Then, the output unit 506 outputs the matching result 507.
  • the pattern matching processing unit 503 collates the template image with the captured image 504 and performs a process of aligning the positions.
  • An example of a specific method is to calculate the normalized cross-correlation as a similarity score while shifting the relative positions of the template image and the captured image 504, and output the relative position having the highest similarity score.
  • the format of the matching result 507 may be, for example, a two-dimensional coordinate value representing the amount of movement of the image, or may be an image in which the template image and the captured image 504 are overlaid at the position having the highest degree of similarity. good.
  • the input photographed image statistic 207 is estimated by the estimation unit 202 of FIG. 2 using the design data image and process information corresponding to the photographed image 504 to be matched. At this time, it is desirable that the model data given to the estimation unit 202 is created by the learning process in advance of the pattern matching process.
  • Examples of the template image created by the template image creation unit 502 include an average image obtained by imaging the average value of the captured image statistic 207, and sampling obtained by sampling the value of each pixel from the captured image statistic 207. The image is mentioned.
  • the photographed image of the circuit used in the learning process performed before the pattern matching process the photographed image acquired from the wafer manufactured in the past may be used, or the photographed image acquired from the wafer to be matched may be used. good.
  • FIG. 11 is a configuration diagram showing a GUI for estimating a photographed image statistic and evaluating a circuit.
  • GUI is an abbreviation for a graphical user interface.
  • a design data image setting unit 1101 a model data setting unit 1102, a process information setting unit 1103, an evaluation result display unit 1104, and a display image operation unit 1107 are displayed. ing.
  • the design data image setting unit 1101 is an area for setting the design data image necessary for estimating the captured image statistic.
  • the model data setting unit 1102 is an area for setting the trained model data necessary for estimating the captured image statistic.
  • the process information setting unit 1103 is an area for setting the process information necessary for estimating the captured image statistic. For example, as a method of setting process information, there is a method of individually inputting parameters required for each process such as lithography and etching.
  • the design data image setting unit 1101, the model data setting unit 1102, and the process information setting unit 1103 read each data by designating the storage area stored in a predetermined format.
  • the evaluation result display unit 1104 is an area for displaying information related to the captured image statistics estimated from the data set by the design data image setting unit 1101, the model data setting unit 1102, and the process information setting unit 1103. Examples of the information to be displayed include an average image 1105 and a standard deviation image 1106 created from captured image statistics.
  • the display image operation unit 1107 is an area for performing operations related to the information displayed by the evaluation result display unit 1104. Operations include switching the displayed image to another image and enlarging or reducing the image.
  • FIG. 12 is a configuration diagram showing a GUI for carrying out the learning process.
  • a learning data set setting unit 1201 a model data setting unit 1202, a learning condition setting unit 1203, and a learning result display unit 1204 are displayed.
  • the learning data set setting unit 1201 is an area for setting a learning data set including a design data image used in the learning process, process information, and a photographed image.
  • data is read by designating a storage area stored in a predetermined format.
  • the model data setting unit 1202 is an area for setting model data that is input, updated, and saved in the learning process.
  • the learning condition setting unit 1203 for reading model data by designating a storage area stored in a predetermined format is an area for setting learning conditions for learning processing.
  • the number of learnings may be specified as the learning necessity determination S404, or the value of the loss function as a reference for ending the learning may be specified.
  • the learning result display unit 1204 is an area for displaying the learning result during or after the learning process.
  • the graph 1205 of the time change of the loss function may be displayed, or the image 1206 which visualizes the captured image statistics estimated by using the model during or at the end of training may be displayed.
  • the GUI (1100) and the GUI (1200) may be individual or integrated as a GUI related to learning processing and evaluation. Further, the area for setting, displaying or operating indicated by the GUI (1100) or the GUI (1200) is an example, and all of them are not essential to the GUI and may be realized only in a part. Further, the device that executes these processes may execute each process in one device or may be executed in different devices in the same manner as the program.
  • the process of estimating the captured image statistics of FIGS. 2, 3A and 3B, the learning process of FIG. 4, and the pattern matching process of FIG. 5 may be executed by different programs, or each may be executed as an individual program. You may run it with. Further, the device that executes these processes may execute each process in one device or may be executed in different devices in the same manner as the program.
  • the present invention is not limited to the above-described embodiment, but includes various modifications.
  • the above-described embodiment has been described in detail in order to explain the present invention in an easy-to-understand manner, and is not necessarily limited to the one including all the described configurations.
  • the deformation range of the sample shape according to the process information is estimated as a statistic from the design data image based on the correspondence between the reference image such as the sample design data, the process information, and the photographed image. Can be done. Using the estimated statistics, pattern matching can be performed on the captured image of the sample.
  • any sample can be obtained. From the reference data and the process information thereof, it is possible to estimate the deformation or physical properties of the sample and the fluctuation of the image quality of the captured image of the sample.
  • the deformation range of the circuit under the conditions can be directly estimated from any design data image and any process information. Therefore, if a pattern matching template image is created from the estimation result and used, highly accurate pattern matching can be realized in consideration of the difference in the deformation range due to the difference in the process information.
  • 101 Design data image
  • 102, 103 Process information
  • 104, 105 504: Photographed image
  • 202 Estimator
  • 204 Reference data
  • 205 Process information
  • 206, 301 Model data
  • 207 Photographed image statistics
  • 303 average image
  • 304 standard deviation image
  • 502 template image creation unit
  • 503 pattern matching processing unit
  • 901 probability density function, 1100, 1200: GUI.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Quality & Reliability (AREA)
  • Analytical Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Pathology (AREA)
  • Biochemistry (AREA)
  • Immunology (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)
  • Testing Or Measuring Of Semiconductors Or The Like (AREA)
PCT/JP2020/023554 2020-06-16 2020-06-16 画像処理方法、形状検査方法、画像処理システム及び形状検査システム Ceased WO2021255819A1 (ja)

Priority Applications (6)

Application Number Priority Date Filing Date Title
US18/009,890 US20230222764A1 (en) 2020-06-16 2020-06-16 Image processing method, pattern inspection method, image processing system, and pattern inspection system
PCT/JP2020/023554 WO2021255819A1 (ja) 2020-06-16 2020-06-16 画像処理方法、形状検査方法、画像処理システム及び形状検査システム
KR1020227041722A KR102780234B1 (ko) 2020-06-16 2020-06-16 화상 처리 방법, 형상 검사 방법, 화상 처리 시스템 및 형상 검사 시스템
JP2022531135A JP7390486B2 (ja) 2020-06-16 2020-06-16 画像処理方法、形状検査方法、画像処理システム及び形状検査システム
CN202080101502.7A CN115698690A (zh) 2020-06-16 2020-06-16 图像处理方法、形状检查方法、图像处理系统以及形状检查系统
TW110121442A TWI777612B (zh) 2020-06-16 2021-06-11 影像處理方法、形狀檢查方法、影像處理系統及形狀檢查系統

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/023554 WO2021255819A1 (ja) 2020-06-16 2020-06-16 画像処理方法、形状検査方法、画像処理システム及び形状検査システム

Publications (1)

Publication Number Publication Date
WO2021255819A1 true WO2021255819A1 (ja) 2021-12-23

Family

ID=79268639

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/023554 Ceased WO2021255819A1 (ja) 2020-06-16 2020-06-16 画像処理方法、形状検査方法、画像処理システム及び形状検査システム

Country Status (6)

Country Link
US (1) US20230222764A1 (https=)
JP (1) JP7390486B2 (https=)
KR (1) KR102780234B1 (https=)
CN (1) CN115698690A (https=)
TW (1) TWI777612B (https=)
WO (1) WO2021255819A1 (https=)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115242982A (zh) * 2022-07-28 2022-10-25 业成科技（成都）有限公司 镜头调焦方法及其系统
WO2023127081A1 (ja) * 2021-12-28 2023-07-06 株式会社日立ハイテク 画像検査装置、画像処理方法
KR20250143803A (ko) 2023-06-21 2025-10-02 주식회사 히타치하이테크 화상 검사 장치 및 화상 처리 방법

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2024108492A (ja) * 2023-01-31 2024-08-13 東京エレクトロン株式会社 堆積判定方法及び基板処理装置
WO2026047363A1 (en) * 2024-08-30 2026-03-05 Applied Materials Inc Self-operating substrate measurement

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170148226A1 (en) * 2015-11-19 2017-05-25 Kla-Tencor Corporation Generating simulated images from design information
US20170191948A1 (en) * 2016-01-04 2017-07-06 Kla-Tencor Corporation Optical Die to Database Inspection
JP2018028636A (ja) * 2016-08-19 2018-02-22 株式会社ニューフレアテクノロジー マスク検査方法
US20180293721A1 (en) * 2017-04-07 2018-10-11 Kla-Tencor Corporation Contour based defect detection

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006302952A (ja) * 2005-04-15 2006-11-02 Toshiba Corp パターン計測システムおよび半導体装置の製造方法
JP5239686B2 (ja) * 2008-09-25 2013-07-17 横河電機株式会社 プロセス推定システムおよびプロセス推定方法
JP5439106B2 (ja) * 2009-09-30 2014-03-12 株式会社日立ハイテクノロジーズ 走査荷電粒子顕微鏡を用いたパターン形状評価装置およびその方法
JP5874398B2 (ja) * 2012-01-05 2016-03-02 オムロン株式会社 画像検査装置の検査領域設定方法
JP6004956B2 (ja) * 2013-01-29 2016-10-12 株式会社日立ハイテクノロジーズ パターン評価装置、及び、パターン評価装置を備えた外観検査装置
CN105308947B (zh) * 2013-06-13 2018-10-02 核心光电有限公司 双孔径变焦数字摄影机
JP6207893B2 (ja) * 2013-06-25 2017-10-04 株式会社日立ハイテクノロジーズ 試料観察装置用のテンプレート作成装置
US9785752B1 (en) * 2014-02-25 2017-10-10 Flagship Biosciences, Inc. Method for stratifying and selecting candidates for receiving a specific therapeutic approach
CN104881868B (zh) * 2015-05-14 2017-07-07 中国科学院遥感与数字地球研究所 植物群落空间结构提取方法
US10163061B2 (en) * 2015-06-18 2018-12-25 International Business Machines Corporation Quality-directed adaptive analytic retraining
JP6388613B2 (ja) * 2016-02-24 2018-09-12 三菱電機ビルテクノサービス株式会社 画像処理装置、設計支援システム及びプログラム
JP6912890B2 (ja) * 2017-01-13 2021-08-04 キヤノン株式会社 情報処理装置、情報処理方法、システム
US10671881B2 (en) * 2017-04-11 2020-06-02 Microsoft Technology Licensing, Llc Image processing system with discriminative control
JP6487493B2 (ja) * 2017-05-18 2019-03-20 ファナック株式会社 画像処理システム
JP7091635B2 (ja) * 2017-11-15 2022-06-28 大日本印刷株式会社 対象物検出器、画像解析装置、対象物検出方法、画像解析方法、プログラム、及び、学習データ
JP2019125116A (ja) * 2018-01-15 2019-07-25 キヤノン株式会社 情報処理装置、情報処理方法、およびプログラム
JP7015001B2 (ja) * 2018-03-14 2022-02-02 オムロン株式会社 欠陥検査装置、欠陥検査方法、及びそのプログラム
JP7144244B2 (ja) 2018-08-31 2022-09-29 株式会社日立ハイテク パターン検査システム
DE102019124809A1 (de) * 2018-09-21 2020-03-26 Fanuc Corporation Bildgebungsvorrichtung und Bildgebungssystem

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170148226A1 (en) * 2015-11-19 2017-05-25 Kla-Tencor Corporation Generating simulated images from design information
US20170191948A1 (en) * 2016-01-04 2017-07-06 Kla-Tencor Corporation Optical Die to Database Inspection
JP2018028636A (ja) * 2016-08-19 2018-02-22 株式会社ニューフレアテクノロジー マスク検査方法
US20180293721A1 (en) * 2017-04-07 2018-10-11 Kla-Tencor Corporation Contour based defect detection

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023127081A1 (ja) * 2021-12-28 2023-07-06 株式会社日立ハイテク 画像検査装置、画像処理方法
JPWO2023127081A1 (https=) * 2021-12-28 2023-07-06
TWI827393B (zh) * 2021-12-28 2023-12-21 日商日立全球先端科技股份有限公司 圖像檢查裝置，圖像處理方法
JP7636586B2 (ja) 2021-12-28 2025-02-26 株式会社日立ハイテク 画像検査装置、画像処理方法
CN115242982A (zh) * 2022-07-28 2022-10-25 业成科技（成都）有限公司 镜头调焦方法及其系统
CN115242982B (zh) * 2022-07-28 2023-09-22 业成科技（成都）有限公司 镜头调焦方法及其系统
KR20250143803A (ko) 2023-06-21 2025-10-02 주식회사 히타치하이테크 화상 검사 장치 및 화상 처리 방법

Also Published As

Publication number Publication date
JP7390486B2 (ja) 2023-12-01
KR20230004819A (ko) 2023-01-06
CN115698690A (zh) 2023-02-03
JPWO2021255819A1 (https=) 2021-12-23
TWI777612B (zh) 2022-09-11
KR102780234B1 (ko) 2025-03-14
US20230222764A1 (en) 2023-07-13
TW202201347A (zh) 2022-01-01

Similar Documents

Publication Publication Date Title
US10937146B2 (en) Image evaluation method and image evaluation device
JP7427744B2 (ja) 画像処理プログラム、画像処理装置、画像処理方法および欠陥検出システム
JP7390486B2 (ja) 画像処理方法、形状検査方法、画像処理システム及び形状検査システム
JP7144244B2 (ja) パターン検査システム
JP5604067B2 (ja) マッチング用テンプレートの作成方法、及びテンプレート作成装置
US8767038B2 (en) Method and device for synthesizing panorama image using scanning charged-particle microscope
JP5525421B2 (ja) 画像撮像装置および画像撮像方法
JP4982544B2 (ja) 合成画像形成方法及び画像形成装置
WO2014208202A1 (ja) パターン形状評価装置及び方法
JP5286337B2 (ja) 半導体製造装置の管理装置、及びコンピュータプログラム
US10558127B2 (en) Exposure condition evaluation device
TWI567789B (zh) A pattern measuring condition setting means, and a pattern measuring means
JP5396496B2 (ja) 合成画像形成方法及び画像形成装置
CN121488320A (zh) 具有检查测量模型的扫描型电子显微镜及检查测量模型的修正方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20940484

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022531135

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 20227041722

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20940484

Country of ref document: EP

Kind code of ref document: A1