Device size measurement method, system, equipment and medium

Abstract

The invention discloses a device size measurement method, system and equipment and a medium, and the method comprises the steps: obtaining the manufacturing parameters of a to-be-measured device, and constructing a measurement template of the to-be-measured device based on the manufacturing parameters; the measurement template is analyzed, detection parameters are obtained, and the detection parameters comprise position information and size detection types; acquiring a shot image of the to-be-measured device, and matching a corresponding region of interest from the shot image based on the measurement template; and based on the detection parameters and the region of interest, obtaining key dimension parameters of the to-be-detected device. The problems that in the prior art, the calculation complexity is high, so that the measurement efficiency is low, meanwhile, the adaptability to different processes and device types is poor, and diversified requirements are difficult to meet are solved.

Description

Background Art

[0002] With the continuous progress of semiconductor technology, device sizes are constantly shrinking, and precisely controlling critical dimensions has become a core challenge in enhancing device performance and reliability. Currently, the measurement of critical dimensions mainly relies on high-precision measurement equipment such as scanning electron microscopes (SEM) and atomic force microscopes (AFM). However, the detection efficiency of these measurement devices is relatively low. Usually, manual measurement has to be carried out one by one. However, manual measurement is slow and has relatively low measurement accuracy, making it impossible to achieve batch and rapid detection, resulting in a slow overall detection process and being difficult to meet the requirements for rapid and accurate detection in mass production.

[0003] In the prior art, although there are already some algorithms for improving the accuracy and efficiency of critical dimension measurement, these algorithms generally have the following problems: First, the computational complexity is high, resulting in relatively low measurement efficiency; second, the adaptability to different processes and device types is poor, making it difficult to meet diverse requirements. Therefore, there is an urgent need for a device size measurement method with high precision, high efficiency, and strong adaptability to solve the above problems. Summary of the Invention

[0004] To overcome the problems in the prior art, such as high computational complexity leading to relatively low measurement efficiency, and poor adaptability to different processes and device types, making it difficult to meet diverse requirements, this application provides a device size measurement method, system, device, and medium.

[0005] In a first aspect, to solve the above technical problems, this application provides a device size measurement method, including:

[0006] Obtain the manufacturing parameters of the device to be measured, and construct a measurement template for the device to be measured based on the manufacturing parameters;

[0007] Analyze the measurement template to obtain detection parameters, where the detection parameters include position information and size detection types;

[0008] Obtain a captured image of the device to be measured, and match the corresponding region of interest from the captured image based on the measurement template;

[0009] Based on the detection parameters and the region of interest, obtain the critical dimension parameters of the device to be measured.

[0010] In a second aspect, this application also provides a device size measurement system, including:

[0011] A construction module, configured to obtain the manufacturing parameters of the device to be measured, and construct a measurement template for the device to be measured based on the manufacturing parameters;

[0012] An analysis module, configured to analyze the measurement template to obtain detection parameters, where the detection parameters include position information and size detection types;

[0013] A matching module, configured to obtain a captured image of a device under test, and match a corresponding region of interest from the captured image based on a measurement template;

[0014] A dimension parameter determination module, configured to obtain key dimension parameters of the device under test based on detection parameters and the region of interest.

[0015] In a third aspect, the present application further provides a computing device, including a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, the steps of a device dimension measurement method as described above are implemented.

[0016] In a fourth aspect, the present application further provides a computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions run on a terminal device, the terminal device is caused to execute the steps of a device dimension measurement method.

[0017] The beneficial effects of the present application are as follows: First, a measurement template is constructed based on the manufacturing parameters of the device under test, and the two-sided template is analyzed to obtain detection parameters. Then, a corresponding region of interest is matched from the captured image of the device under test based on the measurement template, and the key dimension parameters of the device under test are obtained based on the detection parameters and the region of interest. In this way, by using the pre-constructed measurement template to calculate the key dimension parameters of the same type of device under test, the calculation complexity is reduced, thereby improving the measurement efficiency of the device. At the same time, the measurement template is constructed based on the manufacturing parameters of the device during production and manufacturing. By pre-constructing the measurement template, it can adapt to the measurement of device types with different processes, meeting the diverse measurement requirements of devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a schematic flowchart of a device dimension measurement method shown in an exemplary embodiment of the present application;

[0019] Figure 2 is a standard image of a semiconductor device in an exemplary embodiment of the present application;

[0020] Figure 3 is for Figure 2 the image obtained by performing threshold segmentation on the measured region outlined in

[0021] Figure 4 is a contour information diagram in a region of interest of a semiconductor device in an exemplary embodiment of the present application;

[0022] Figure 5 is a schematic structural diagram of a device dimension measurement system shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] The following embodiments are further explanations and supplements to the present application and do not constitute any limitation to the present application.

[0024] A method, system, device, and medium for measuring device size according to an embodiment of the present application will be described below with reference to the accompanying drawings.

[0025] A method for measuring device size provided by an embodiment of the present application can be specifically executed by a server. It should be noted that the server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms. No limitation is imposed here.

[0026] Please refer to Figure 1 , Figure 1 which shows a method for measuring device size according to an exemplary embodiment of the present application. As Figure 1 shown, the present application provides a method for measuring device size, including:

[0027] Step S11: Obtain the manufacturing parameters of the device to be measured and construct a measurement template for the device to be measured based on the manufacturing parameters;

[0028] Step S12: Analyze the measurement template to obtain detection parameters, where the detection parameters include position information and size detection type;

[0029] Step S13: Obtain the captured image of the device to be measured and match the corresponding region of interest from the captured image based on the measurement template;

[0030] Step S14: Obtain the key size parameters of the device to be measured based on the detection parameters and the region of interest.

[0031] In the embodiment provided by the present application, a method for measuring device size first constructs a measurement template based on the manufacturing parameters of the device to be measured, analyzes the two-sided template to obtain detection parameters. Then, based on the measurement template, the corresponding region of interest is matched from the captured image of the device to be measured, and the key size parameters of the device to be measured are obtained based on the detection parameters and the region of interest. In this way, by calculating the key size parameters of the same type of device to be measured through the pre-constructed measurement template, the calculation complexity is reduced, thereby improving the measurement efficiency of the device. At the same time, the measurement template is constructed based on the manufacturing parameters during the production and manufacturing of the device. By pre-constructing the measurement template, it can adapt to the measurement of device types with different processes and meet the diverse measurement requirements of the device.

[0032] Optionally, constructing a measurement template for the device to be measured based on the manufacturing parameters includes:

[0033] Determine the detection target of the device under test based on manufacturing parameters;

[0034] Obtain the standard image of the device under test;

[0035] Select the measurement area corresponding to the detection target in the standard image;

[0036] Form a measurement template for the device under test based on the measurement area.

[0037] In this embodiment provided by the present application, through manufacturing parameters, the detection target representing the critical dimension (CD) in the device under test can be understood. By obtaining the standard image that meets the design standard corresponding to the type of the image to be measured, and selecting the measurement area corresponding to the detection target in the standard image to form the measurement template for the device under test. In this way, through the measurement template, the critical dimensions of the same type of devices under test can be directly and specifically detected, without the need to separately re-plan and detect the critical dimensions of each device under test, thus improving the measurement efficiency of the critical dimensions of the device and achieving accurate positioning and classification of the detection target. Among them, the detection target is a detection object in the device under test with obvious features such as high contrast, and the corresponding pixel arrangement has a certain regularity.

[0038] In another embodiment provided by the present application, if the device under test is a semiconductor device, the steps of constructing the measurement template for the device under test based on manufacturing parameters are as follows:

[0039] First, determine the detection target. According to the manufacturing parameters of the semiconductor device, determine the standard image of the semiconductor device, and remember the critical dimensions of the detection target to be detected, where the critical dimensions include the CD of a single pixel or the specific distance between multiple pixels;

[0040] Second, design the structure of the measurement template for the semiconductor device. The measurement template includes multiple selected areas, and each area corresponds to a specific detection target. The design of the measurement template should consider the layout of the device, the arrangement of pixels, and the characteristics of the detection target;

[0041] Then, select the measurement area corresponding to the detection target in the standard image. Through the visual user interface, according to the preset region of interest (ROI) selection rule corresponding to the manufacturing parameters, directly select the single pixel or the specific area between multiple pixels corresponding to each detection target in the standard image to obtain the measurement area.

[0042] For example, the standard image of the semiconductor device is as Figure 2As shown, a detection target of the semiconductor device is the critical dimension between the center of a certain pixel and the center of the fifth pixel from left to right horizontally. Then, the measurement area of this detection target needs to be obtained by sequentially selecting the following areas in the standard image as shown in Figure 2 shown:

[0043] Select the entire area from the first pixel to the fifth pixel to obtain the first box;

[0044] Select the entire area of the first pixel to obtain the second box;

[0045] Select the entire area of the fifth pixel to obtain the third box;

[0046] Fourth, the selection needs to start from near the center area of the first pixel and extend to near the center area of the fifth pixel. For the specific information of this selected area, the operator can make personalized settings according to the region of interest to be actually measured. Taking the single pixel in Figure 2 as an example, the left side line of the pixel can be defined as type1, the center area as type2, and the right side line as type3.

[0047] During the process of selecting the side lines, the operator should set conditions to ensure that the distance between the selected position and the corresponding side line does not exceed one-fifth of the pixel size. In this way, near the selected position, combined with the coordinate positions of the first to third boxes, it is possible to accurately determine whether the left and right box lines correspond to the left side line, the center area, or the right side line of the pixel, so as to obtain the standardized measurement area of the detection target. In this way, it is possible to ensure the accuracy of the selected measurement area, thereby providing a reliable data basis for subsequent image analysis and processing.

[0048] Optionally, the measurement template includes a measurement area; by analyzing the measurement template, detection parameters are obtained, including:

[0049] Using an adaptive threshold algorithm to perform threshold segmentation on the measurement area to obtain the number of pixels in the measurement area;

[0050] Extract the coordinate information of each pixel in the measurement area to form the position information of the measurement area;

[0051] Based on the number of pixels and the position information, determine the size detection type corresponding to the measurement area;

[0052] Based on the size detection type and the position information, form the detection parameters of the measurement area.

[0053] In this embodiment provided by the present application, an adaptive threshold algorithm is used to perform threshold segmentation on the measurement region to obtain the number of pixels in the measurement region, and the coordinate information of each pixel in the measurement region is extracted to form the position information of the measurement region, providing key data support for the subsequent measurement of critical dimensions. Then, since there are differences in the shape and size between the measurement regions corresponding to different detection targets, the pixel data and position information of different measurement regions are different. Therefore, based on the number of pixels and the position information, the size detection type corresponding to the measurement region can be directly determined from the preset corresponding relationship to form detection parameters composed of the size detection type and the position information, facilitating the subsequent direct determination of the critical dimension parameters of the device to be measured based on the detection parameters as the standard parameters. In this way, when measuring the critical dimensions of different devices of the same type, standard detection parameters can be used for calculation without calculating the detection parameters each time, thereby improving the measurement efficiency of the critical dimensions of the device. Among them, the size detection type includes the critical dimension detection of a single pixel and the critical dimension detection of a pixel group.

[0054] In another embodiment provided by the present application, first, an adaptive threshold algorithm is used to perform threshold segmentation on the measurement region, so that each pixel in the measurement region forms a connected domain. The basic information such as the number of connected domains in the measurement region is counted using a connected domain segmentation algorithm or an edge extraction algorithm to obtain the number of pixels in the measurement region, and then the corresponding measurement region is marked as a single pixel or a pixel group. For example, the image obtained by performing threshold segmentation on the measurement region Figure 2 framed in is as Figure 3 shown.

[0055] Secondly, the central coordinates, corner coordinates and other coordinate information of each connected domain are calculated. According to the horizontal (or vertical) order of the coordinate information, each pixel can also be numbered to form the position information of the measurement region;

[0056] Then, according to the number of pixels and the position information of the measurement region, the size detection type corresponding to the measurement region is directly determined from the preset corresponding relationship to form detection parameters composed of the size detection type and the position information.

[0057] Optionally, based on the measurement template, the corresponding region of interest is matched from the captured image, including:

[0058] Using a preset template matching algorithm, multiple sampling points are constructed in the captured image;

[0059] Using the positional relationship between the preset sampling points and the sampling frames corresponding to the measurement template, sampling images corresponding to the sampling points are obtained by sampling from the captured image;

[0060] Calculate the similarity score between the measurement template and the sampled images, and use the sampled images with similarity scores greater than the threshold as the regions of interest.

[0061] In this embodiment provided by the present application, first, using a preset template matching algorithm, multiple sampling points are constructed in the captured image, and based on the positional relationship between the preset sampling points and the corresponding sampling frames of the measurement template, sampled images corresponding to the sampling points are obtained from the captured image, thereby realizing the traversal of the measurement template in the captured image. Then, calculate the similarity score between the measurement template and the sampled images, and use the sampled images with similarity scores greater than the threshold as the regions of interest, achieving efficient traversal of the measurement template, accurately identifying the regions of interest that meet the corresponding similarity requirements, thereby improving the recognition accuracy of the regions of interest and ensuring the pertinence and accuracy of the detection.

[0062] In another embodiment, first, the matching direction of the measurement template in the captured image can be preset, i.e., horizontal or vertical. For example, horizontal is set to 1 and vertical is set to 2, so that the algorithm can correctly identify the arrangement of pixels. In this way, providing the function of setting the matching direction ensures that the algorithm can perform adaptive detection according to the layouts of different devices and achieve flexible image matching.

[0063] Second, use a preset template matching algorithm, such as the normalized cross-correlation matching algorithm, etc. The algorithm will give the similarity score between the sampled image corresponding to each sampling point in the captured image and the measurement template. The sampling point with the similarity score being the maximum value and the score exceeding a certain threshold is the point successfully matched with the measurement template, and then the position of each region of interest is located to ensure the alignment of the measurement template with the detection target in the captured image.

[0064] Optionally, based on the detection parameters and the regions of interest, obtain the key dimension parameters of the device under test, including:

[0065] Use a preset image processing technique to process the region of interest to obtain the key dimension values of the pixels in the region of interest;

[0066] When the key dimension detection type is the key dimension detection of a single pixel, use the key dimension value as the key dimension parameter of the device under test;

[0067] When the key dimension detection type is the key dimension detection of a pixel group, based on the position information and a preset distance measurement method, obtain the distance values between every two pixels in the region of interest;

[0068] Form the key dimension parameters of the device under test based on the key dimension values and the distance values.

[0069] In this embodiment provided by the present application, a preset image processing technique is used to process the region of interest to obtain the critical dimension value of the pixels in the region of interest. When the dimension detection type is the critical dimension detection of a single pixel, the critical dimension value is used as the critical dimension parameter of the device under test. When the dimension detection type is the critical dimension detection of a pixel group, based on the position information and a preset distance metric method, the distance value between every two pixels in the region of interest is obtained, and the critical dimension parameter of the device under test is formed based on the critical dimension value and the distance value. In this way, the region of interest is classified and recognized based on the dimension detection type. When there is only one pixel in the region of interest, only the critical dimension value of the single pixel needs to be measured to obtain the critical dimension parameter. Only when there are multiple pixels in the region of interest, the critical dimension value of each pixel and the distance value between every two pixels are measured to obtain the critical dimension parameter. Therefore, it is not necessary to calculate the distance value for each region of interest, which can reduce the data processing volume in the process of obtaining the critical dimension parameter of the region of interest, thereby improving the measurement efficiency of the device.

[0070] Meanwhile, through the preset image processing technique, the critical dimension parameters of different regions of interest can be automatically recognized simultaneously, ensuring that the critical dimensions of each device under test can be accurately measured, thereby realizing the rapid measurement of the batch critical dimension parameters of the devices under test.

[0071] Optionally, using the preset image processing technique to process the region of interest to obtain the critical dimension value of the pixels in the region of interest includes:

[0072] Performing gray-scale processing on the region of interest to obtain a gray-scale image;

[0073] Performing binarization processing on the gray-scale image to generate a binarized image of the region of interest;

[0074] Extracting the contour information of the pixels in the binarized image and using the contour information as the critical dimension value of the corresponding pixels.

[0075] In this embodiment provided by the present application, gray-scale processing and binarization processing are performed on the region of interest to generate a binarized image of the region of interest. The binarized image highlights the contour information such as the edges and contours in the region of interest, making it easier to directly extract the contour information of the pixels from the binarized image subsequently. This contour information is the critical dimension value of the corresponding pixels, thereby improving the determination efficiency of the critical dimension value and further improving the measurement efficiency of the device.

[0076] In another embodiment provided by the present application, performing binarization processing on the gray-scale image to generate a binarized image of the region of interest, and the specific steps are as follows:

[0077] Perform Gaussian blur processing and conventional blur processing on the grayscale image to obtain a Gaussian blurred image and a conventionally blurred image;

[0078] Calculate the image difference between the Gaussian blurred image and the conventionally blurred image to obtain a difference image;

[0079] Process the difference image based on a preset difference threshold to generate a defect adaptive grayscale mask to identify the defect area in the difference image and obtain a binary image.

[0080] In another embodiment provided by the present application, perform binary processing on the grayscale image to generate a binary image of the region of interest, and the specific steps are as follows:

[0081] Extract the grayscale of the grayscale image and the region of interest to obtain a first image grayscale histogram and a second image grayscale histogram;

[0082] Perform iterative calculation on the first image grayscale histogram and the second image grayscale histogram to obtain an average grayscale value;

[0083] Update the initial grayscale change threshold based on the average grayscale value to obtain a new grayscale change threshold until the new grayscale change threshold is less than the preset grayscale change value, implement automatic threshold segmentation based on the image grayscale histogram, generate an iterative grayscale image, and use the iterative grayscale image as the binary image of the region of interest.

[0084] All pixel contour information in the image can be directly extracted through the binary image obtained above. For example, the contour information in a region of interest of a semiconductor device is as Figure 4 shown.

[0085] Optionally, the method further includes:

[0086] Output the critical dimension parameters as tabular data;

[0087] Send the tabular data to the corresponding production management system for storage.

[0088] In this embodiment provided by the present application, outputting the critical dimension parameters as tabular data and storing them in the corresponding production management system facilitates the unified management of the measurement data of the device and improves the convenience of data management.

[0089] In another embodiment provided by the present application, the tabular data output by the critical dimension parameters can be in various formats, such as tables, charts, or integrated data strings. And it is easy to integrate into the production management system, which can improve the production efficiency and quality control level of the corresponding device under test.

[0090] In an exemplary embodiment provided by the present application, for different types of semiconductor devices, an operator can adjust the selected area and detection parameters of the measurement template according to the manufacturing parameters of the device to be measured. For example, for some semiconductor devices that need to detect a specific angle between pixels, a corresponding selected area can be added to the measurement template, and an angle parameter can be added to the detection parameters.

[0091] A device size measurement method of the present application constructs a measurement template based on the manufacturing parameters of the device to be measured, analyzes both templates to obtain detection parameters, then matches a corresponding region of interest from the captured image of the device to be measured based on the measurement template, and obtains the key size parameters of the device to be measured based on the detection parameters and the region of interest, which has high efficiency, accuracy, flexibility, ease of use, traceability, and a high degree of automation.

[0092] The high efficiency is reflected in: realizing the batch and rapid detection of the key sizes of the device, significantly improving the detection speed, greatly shortening the production cycle compared with the traditional method, and improving the production efficiency.

[0093] The accuracy is reflected in: by adopting a high-precision template matching technology, the accuracy of the detection result is ensured. In practical applications, the measurement error of the algorithm is controlled within the range of ±0.12 micrometers, effectively reducing the measurement deviation caused by human operation errors.

[0094] The flexibility is reflected in: the template design has high flexibility and can be customized according to the types and detection requirements of different devices, thus having a wide range of adaptability.

[0095] The ease of use is reflected in: the user only needs to complete the establishment of the template and the detection process through simple steps, without the need to have professional technical knowledge, which greatly facilitates the use of the operator.

[0096] The high degree of automation is reflected in: the detection process realizes a high degree of automation, reduces manual intervention, not only reduces the labor intensity, but also reduces the possibility of operation errors and improves the reliability of the detection.

[0097] The traceability is reflected in: the generated detection results are traceable, which is convenient for quality control and problem analysis, and provides strong support for quality control in the production process.

[0098] Please refer to Figure 5 , Figure 5 which shows a device size measurement system according to an exemplary embodiment of the present application. As Figure 5 shown, the present application provides a device size measurement system 500, including:

[0099] The building module 501 is configured to obtain the manufacturing parameters of the device under test and construct a measurement template for the device under test based on the manufacturing parameters;

[0100] The parsing module 502 is configured to parse the measurement template to obtain detection parameters, where the detection parameters include position information and size detection types;

[0101] The matching module 503 is configured to obtain a captured image of the device under test and match a corresponding region of interest from the captured image based on the measurement template;

[0102] The size parameter determination module 504 is configured to obtain the key size parameters of the device under test based on the detection parameters and the region of interest.

[0103] In this embodiment provided by the present application, for a device size measurement system, first, the building module 501 constructs a measurement template based on the manufacturing parameters of the device under test, and the parsing module 502 parses the two-sided template to obtain detection parameters. Then, the matching module 503 matches a corresponding region of interest from the captured image of the device under test based on the measurement template, and the size parameter determination module 504 obtains the key size parameters of the device under test based on the detection parameters and the region of interest. In this way, by calculating the key size parameters of the devices under test of the same type through the pre-constructed measurement template, the calculation complexity is reduced, thereby improving the measurement efficiency of the device. At the same time, the measurement template is constructed based on the manufacturing parameters during the production and manufacturing of the device. By pre-constructing the measurement template, it can adapt to the measurement of device types with different processes and meet the diverse measurement requirements of the devices.

[0104] Optionally, the building module is specifically configured to:

[0105] Determine the detection target of the device under test based on the manufacturing parameters;

[0106] Obtain a standard image of the device under test, and frame a measurement area corresponding to the detection target in the standard image;

[0107] Form a measurement template for the device under test based on the measurement area.

[0108] Optionally, the measurement template includes a measurement area; the parsing module is specifically configured to:

[0109] Use an adaptive threshold algorithm to perform threshold segmentation on the measurement area to obtain the number of pixels in the measurement area;

[0110] Extract the coordinate information of each pixel in the measurement area to form the position information of the measurement area;

[0111] Determine the size detection type corresponding to the measurement area based on the number of pixels and the position information;

[0112] Detection parameters for forming a measurement region based on the size detection type and position information.

[0113] Optionally, a matching module, specifically used for:

[0114] Using a preset template matching algorithm to construct multiple sampling points in the captured image;

[0115] Using the positional relationship between the preset sampling points and the sampling frames corresponding to the measurement templates to sample the captured image to obtain sampling images corresponding to the sampling points;

[0116] Calculating the similarity score between the measurement template and the sampling images, and taking the sampling images with similarity scores greater than the threshold as the regions of interest.

[0117] Optionally, a size parameter determination module, specifically used for:

[0118] Using a preset image processing technique to process the region of interest to obtain the critical dimension values of the pixels in the region of interest;

[0119] When the size detection type is the critical dimension detection of a single pixel, taking the critical dimension value as the critical dimension parameter of the device under test;

[0120] When the size detection type is the critical dimension detection of a pixel group, based on the position information and a preset distance measurement method, obtaining the distance values between every two pixels in the region of interest;

[0121] Forming the critical dimension parameters of the device under test based on the critical dimension values and the distance values.

[0122] Optionally, a size parameter determination module, specifically used for:

[0123] Performing grayscale processing on the region of interest to obtain a grayscale image;

[0124] Performing binarization processing on the grayscale image to generate a binarized image of the region of interest;

[0125] Extracting the contour information of the pixels in the binarized image and taking the contour information as the critical dimension value of the corresponding pixel.

[0126] Optionally, the system further includes a storage module, and the storage module is specifically used for:

[0127] Outputting the critical dimension parameters as tabular data;

[0128] Sending the tabular data to the corresponding production management system for storage.

[0129] It should be noted that a device size measurement system provided by the above embodiments and a device size measurement method provided by the above embodiments belong to the same concept. The specific ways in which each module and unit perform operations have been described in detail in the method embodiments, and will not be elaborated here. In actual application, the device size measurement system provided by the above embodiments can, according to needs, allocate the above functions to different functional modules, that is, divide the internal structure of the system into different functional modules to complete all or part of the functions described above. This will not be limited here either.

[0130] A computing device according to an embodiment of the present application includes a memory, a processor, and a program stored on the memory and running on the processor. When the processor executes the program, it implements some or all of the steps of the above device size measurement method.

[0131] Among them, the computing device can be a computer. Correspondingly, its program is computer software, and the parameters and steps in the above computing device of the present application can refer to the parameters and steps in the embodiments of the device size measurement method in the above text, and will not be elaborated here.

[0132] A computer-readable storage medium according to an embodiment of the present application stores instructions that, when running, execute the steps of the above device size measurement method.

[0133] Among them, the computer-readable storage medium can be a transient computer-readable storage medium or a non-transient computer-readable storage medium.

[0134] The technical solution of the embodiment of the present disclosure can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes one or more instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method of the embodiment of the present disclosure. The aforementioned computer-readable storage medium can be a non-transient computer-readable storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc, etc., which are various media that can store program codes, or it can also be a transient computer-readable storage medium.

[0135] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Among them, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0136] Those skilled in the art know that the present application can be implemented as a system, a method, or a computer program product. Therefore, the present disclosure can be specifically implemented in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, which is generally referred to as a "module" or "system" in this article. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable media, which contains computer-readable program code. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above.

[0137] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0138] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limitations on the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for measuring device size, characterized in that, Including: Obtain the manufacturing parameters of the device under test, and construct a measurement template for the device under test based on the manufacturing parameters; Analyze the measurement template to obtain detection parameters, where the detection parameters include position information and size detection type; Obtain a captured image of the device under test, and match a corresponding region of interest from the captured image based on the measurement template; Based on the detection parameters and the region of interest, obtain the critical dimension parameters of the device under test.

2. The method according to claim 1, characterized in that, Constructing the measurement template for the device under test based on the manufacturing parameters includes: Determine the detection target of the device under test based on the manufacturing parameters; Obtain a standard image of the device under test, and frame a measurement region corresponding to the detection target in the standard image; Form the measurement template for the device under test based on the measurement region.

3. The method according to claim 1, characterized in that The measurement template includes a measurement region; analyzing the measurement template to obtain detection parameters includes: Use an adaptive threshold algorithm to perform threshold segmentation on the measurement region to obtain the number of pixels in the measurement region; Extract the coordinate information of each pixel in the measurement region to form the position information of the measurement region; Based on the number of pixels and the position information, determine the size detection type corresponding to the measurement region; Form the detection parameters of the measurement region based on the size detection type and the position information.

4. The method according to claim 1, characterized in that The matching of the corresponding region of interest from the captured image based on the measurement template includes: Use a preset template matching algorithm to construct multiple sampling points in the captured image; Use the position relationship between the preset sampling points and the corresponding sampling frames of the measurement template to sample a sampling image corresponding to the sampling points from the captured image; Calculate the similarity score between the measurement template and the sampling image, and use the sampling image with the similarity score greater than the threshold as the region of interest.

5. The method according to claim 1, characterized in that, Based on the detection parameters and the region of interest, obtaining the critical dimension parameters of the device under test includes: Use a preset image processing technique to process the region of interest to obtain the critical dimension values of the pixels in the region of interest; When the size detection type is the critical dimension detection of a single pixel, use the critical dimension value as the critical dimension parameter of the device under test; When the size detection type is the critical dimension detection of a pixel group, based on the position information and a preset distance measurement method, obtain the distance values between every two pixels in the region of interest; Form the critical dimension parameters of the device under test based on the critical dimension values and the distance values.

6. The method according to claim 5, characterized in that, The use of a preset image processing technique to process the region of interest to obtain the critical dimension values of the pixels in the region of interest includes: Perform grayscale processing on the region of interest to obtain a grayscale image; Perform binarization processing on the grayscale image to generate a binarized image of the region of interest; Extract the contour information of the pixels in the binarized image, and use the contour information as the critical dimension value of the corresponding pixel.

7. The method according to any one of claims 1 to 6, characterized in that The method further includes: Output the critical dimension parameters as tabular data; Send the table data to the corresponding production management system for storage.

8. A device size measurement system, characterized in that, Including: A construction module, configured to obtain manufacturing parameters of a device to be measured, and construct a measurement template of the device to be measured based on the manufacturing parameters; An analysis module, configured to analyze the measurement template to obtain detection parameters, where the detection parameters include position information and a dimension detection type; A matching module, configured to obtain a captured image of the device to be measured, and match a corresponding region of interest from the captured image based on the measurement template; A dimension parameter determination module, configured to obtain key dimension parameters of the device to be measured based on the detection parameters and the region of interest.

9. A computing device, comprising a memory, a processor, and a program stored on the memory and running on the processor, characterized in that, When the processor executes the program, it implements the steps of a device dimension measurement method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Instructions are stored in the computer-readable storage medium, and when the instructions run on a terminal device, the terminal device is caused to execute the steps of a device dimension measurement method according to any one of claims 1 to 7.

Images