Sem image contour positioning method, contour positioning system and computer medium

Abstract

The present application relates to the technical field of games, and particularly relates to a SEM image contour positioning method, a contour positioning system and a computer medium, the SEM image contour positioning method comprising: acquiring an SEM scanning image and extracting discrete feature points of a contour in the scanning original image; generating an auxiliary line segment connected with each discrete feature point based on an initial position of the discrete feature point; performing translation or rotation of each discrete feature point in a preset direction in a plane where the discrete feature point is located until the auxiliary line segment intersects the original image and a loss value is calculated based on a total motion distance of each discrete point; repeating the motion and loss value calculation a preset number of times, continuously comparing the loss value obtained each time until the preset number of motions is completed; obtaining a final position of each discrete feature point based on a set of motions of the minimum loss value after the preset number of motions; and adjusting the corresponding discrete feature point based on the final position to obtain an optimized contour of the SEM scanning image and perform positioning. The present application reduces the amount of calculation, improves the operation efficiency, and further improves the contour extraction efficiency of the SEM image.

Description

Technical Field

[0001] This invention relates to the field of photolithography, and in particular to a method for contour localization of SEM images, a contour localization system, and a computer medium. Background Technology

[0002] The miniaturization of semiconductor devices continues at an astonishing pace. Advanced imaging and analysis techniques are required for the accurate development, characterization, and testing of these devices. Scanning electron microscopy (SEM) imaging can provide a wealth of critical data to meet the needs of semiconductor manufacturing; extracting the outlines of SEM images of the layout formed on the wafer is a crucial step in realizing this technology. The efficiency of outline extraction directly affects the speed of automatic matching between the simulation image of the design layout and the wafer SEM image. Summary of the Invention

[0003] To improve the efficiency of SEM image contour extraction, this invention provides an SEM image contour localization method, a contour localization system, and a computer medium.

[0004] The present invention provides a method for contour localization in SEM images, comprising the following steps: acquiring an SEM scan image and extracting discrete feature points of the contour in the original scan image; generating auxiliary line segments connected to each discrete feature point based on its initial position; translating or rotating each discrete feature point in a preset direction within its plane until the auxiliary line segment intersects with the original image and calculating a loss value based on the total movement distance of each discrete point; repeating the movement and loss value calculation a preset number of times, continuously comparing the magnitude of the loss value obtained each time until the preset number of movements are completed; obtaining the final position of each discrete feature point based on a set of movements with the minimum loss value after the preset number of movements; adjusting the corresponding discrete feature points based on the final position to obtain an optimized contour of the SEM scan image and perform localization.

[0005] Preferably, the auxiliary line segment is generated by the following steps: selecting a discrete feature point; based on the position of the discrete feature point in the original graphic, generating an auxiliary line segment of a certain length along the normal direction of the original graphic contour.

[0006] Preferably, the preset number of times is less than or equal to 500.

[0007] Preferably, the rotation angle range of the discrete feature points is -15° to 15°.

[0008] Preferably, before calculating the loss value, the method further includes the following steps: determining whether the auxiliary line segment intersects with the original figure; if they intersect, calculating the shortest distance from the midpoint of the auxiliary line segment to the original figure, and using the shortest distance as the movement distance of the auxiliary line segment to calculate the loss value; if they do not intersect, recording the shortest distance from the discrete feature point to the original figure, and using the shortest distance as the movement distance of the discrete feature point to calculate the loss value.

[0009] Preferably, adjusting discrete feature points specifically includes the following steps: taking the motion distance and rotation angle of each discrete feature point in the set of motion results with the smallest loss value, and deriving the transformed feature point coordinates based on a preset model.

[0010] Preferably, the preset model is a transformation matrix, and the transformation matrix is: * Where x and y are the original coordinates, and t x and t y x is the displacement in the x and y directions, and x' and y' are the transformed coordinates.

[0011] To address the aforementioned technical problems, this invention also provides a contour localization system. This system utilizes the SEM image contour localization method described above for contour localization. The system is characterized by comprising a recognition module, a calculation module, and an operation module. The recognition module acquires discrete feature points from an initial image for subsequent operations. The calculation module performs motion calculations on the discrete feature points, records the results, and feeds back the final results to the operation module. The operation module adjusts the acquired discrete feature points according to the final results to obtain an optimized contour of the SEM scan image and performs localization.

[0012] Preferably, the contour positioning system can perform contour positioning on GDS images.

[0013] To solve the above-mentioned technical problems, the present invention also provides a computer medium, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the SEM image contour localization method as described above.

[0014] Compared with the prior art, the SEM image contour localization method of the present invention has the following advantages:

[0015] 1. A SEM image contour localization method according to the present invention includes the following steps: acquiring a SEM scan image and extracting discrete feature points of the contour in the original scan image; generating auxiliary line segments connected to each discrete feature point based on the initial position of each discrete feature point; translating or rotating each discrete feature point in a preset direction within its plane until the auxiliary line segment intersects with the original image and calculating a loss value based on the total movement distance of each discrete point; repeating the movement and loss value calculation a preset number of times, continuously comparing the magnitude of the loss value obtained each time until the preset number of movements is completed; obtaining the final position of each discrete feature point based on a set of movements with the minimum loss value after the preset number of movements; adjusting the corresponding discrete feature points based on the final position to obtain an optimized contour of the SEM scan image and perform localization. This method allows for motion calculation of discrete feature points and finds the optimal contour curve by finding the minimum movement distance relative to the original image. Furthermore, this calculation method effectively reduces the computational load of data processing in conventional methods, improves computational efficiency, and thus improves the contour extraction efficiency of SEM images.

[0016] 2. The method for generating auxiliary line segments in the SEM image contour localization method of the present invention specifically includes the following steps: selecting a discrete feature point; based on the position of the discrete feature point in the original image, generating an auxiliary line segment of a certain length along the normal direction of the original image contour. This design limits the length of the auxiliary line segments, making the results more reliable during the intersection of auxiliary line segments when all discrete feature points move, and reducing accidental results caused by different lengths of the auxiliary line segments.

[0017] 3. In the SEM image contour localization method of this invention, the preset number of calculations is less than or equal to 500. By performing a large number of calculations, the influence of random factors on the experimental results is avoided. Furthermore, the movement patterns of each discrete feature point are not uniform in different calculation processes, resulting in more comprehensive coverage and greater reliability of the results.

[0018] 4. In the SEM image contour localization method of the present invention, the preset angle range is -15° to 15°. The rotation angle is set to facilitate the adjustment of the movement distance of each discrete feature point and to obtain comprehensive data. Through this design, the rotation angle of the discrete feature points is limited. Firstly, it reduces the range of motion, so that the best solution within this range can be obtained in a limited number of calculations. Secondly, if the rotation angle is too large, it may cause the original image to be distorted. To ensure that the calculation result is basically consistent with the original image, a preset rotation angle is provided.

[0019] 5. The SEM image contour localization method of the present invention further includes the following steps before calculating the loss value: determining whether the auxiliary line segment intersects with the original image; if they intersect, calculating the shortest distance from the midpoint of the auxiliary line segment to the original image, and using this shortest distance as the movement distance of the auxiliary line segment for loss value calculation; if they do not intersect, recording the shortest distance from the discrete feature point to the original image, and using this shortest distance as the movement distance of the discrete feature point for loss value calculation. This design defines the cases of intersecting auxiliary line segments as a set of results. Simultaneously, in cases where discrete feature points are far apart, it prevents the addition of meaningless calculations by incorporating the distance from non-intersecting points to the original image into the loss value calculation, further improving computational efficiency and thus enhancing the contour extraction efficiency of SEM images.

[0020] 6. The adjustment of discrete feature points in the SEM image contour localization method of the present invention specifically includes the following steps: The motion distance and rotation angle of each discrete feature point in the set of motion results with the minimum loss value are used to derive the transformed feature point coordinates based on a preset model. This method can quickly input the original coordinates and displacement distance of the discrete feature points into the output transformed coordinates, improving the output efficiency.

[0021] 7. In the SEM image contour localization method of the present invention, the preset model is a transformation matrix, and the transformation matrix is: * Where x and y are the original coordinates, and t x and t y x is the displacement in the x and y directions, and x' and y' are the transformed coordinates.

[0022] 8. This invention also provides a contour localization system, which uses the SEM image contour localization method described above for contour localization. The system comprises a recognition module, a calculation module, and an operation module. The recognition module acquires discrete feature points of the initial image for subsequent operations. The calculation module performs motion calculations on the discrete feature points and records the results, feeding the final results back to the operation module. The operation module adjusts the acquired discrete feature points according to the final results to obtain an optimized contour of the SEM scan image and performs localization. This system has the same beneficial effects as the aforementioned SEM image contour localization method, and will not be elaborated upon here.

[0023] 9. The contour localization system of the present invention can perform contour localization on GDS images. SEM image processing and GDS image processing are common image processing methods. Through this design, the contour localization system can not only analyze and process SEM images but also process GDS images, thus improving its versatility.

[0024] 10. The present invention also provides a storage medium, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the SEM image contour localization method as described above, and has the same beneficial effects as the above-described SEM image contour localization method, which will not be elaborated here. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart of the steps of the SEM image contour localization method provided in the first embodiment of the present invention.

[0027] Figure 2 This is a flowchart of the auxiliary line segment generation process for the SEM image contour localization method provided in the first embodiment of the present invention.

[0028] Figure 3 This is a flowchart before calculating the loss value in the SEM image contour localization method provided in the first embodiment of the present invention.

[0029] Figure 4 This is a flowchart of adjusting discrete feature points in the SEM image contour localization method provided in the first embodiment of the present invention.

[0030] Figure 5 This is a schematic diagram of the contour positioning system provided in the second embodiment of the present invention.

[0031] Explanation of reference numerals in the attached diagram:

[0032] 1. Contour positioning system;

[0033] 11. Recognition module; 12. Calculation module; 13. Operation module. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0035] Please see Figure 1 The first embodiment of the present invention provides a method for contour localization of SEM images, including the following steps:

[0036] S1: Obtain the SEM scan image and extract the discrete feature points of the contour in the original scan image;

[0037] S2: Generate auxiliary line segments connected to each discrete feature point based on its initial position;

[0038] S3: Translate or rotate each discrete feature point in a preset direction within its plane until the auxiliary line segment intersects with the original graphic and calculate the loss value based on the total movement distance of each discrete point.

[0039] S4: Repeat the preset number of movements and loss value calculations, continuously comparing the magnitude of the loss value obtained each time until the preset number of movements is completed;

[0040] S5: The final position of each discrete feature point is obtained from a set of motions based on the minimum loss value after a preset number of motions;

[0041] S6: Adjust the corresponding discrete feature points based on the final position to obtain the optimized contour of the SEM scan image and perform localization.

[0042] It should be noted that discrete feature points are usually discrete feature points of the original graphic contour. When performing motion calculations on each discrete feature point, the process involves simulating the motion of the original graphic contour points, including the translation and rotation of discrete feature points on the plane.

[0043] Furthermore, when the minimum loss value corresponds to a different motion mode, a set of motion results with the minimum loss value is randomly selected as the discrete feature point adjustment result and contour localization is performed.

[0044] Understandably, this design allows for the finding of the optimal contour curve by moving discrete feature points relative to their original positions with minimal distance. Furthermore, this calculation method effectively reduces the computational load of data processing in conventional methods, improves computational efficiency, and thus enhances the contour extraction efficiency of SEM images.

[0045] For further details, please refer to Figure 2 The auxiliary line segments are generated in the following steps:

[0046] S21: Select a discrete feature point;

[0047] S22: Based on the position of the discrete feature point in the original figure, generate an auxiliary line segment of a certain length along the normal direction of the original figure's outline.

[0048] It should be noted that all discrete feature points need to generate auxiliary line segments of equal length. The length of the auxiliary line segments is not limited and can be adjusted according to actual needs. Specifically, in the specific embodiment of the present invention, the length of the auxiliary line segments does not exceed the given line width value.

[0049] Understandably, by limiting the length of the auxiliary line segments through this design, the results of the intersection of the auxiliary line segments during the movement of all discrete feature points are more reliable, and the random results caused by different lengths of the auxiliary line segments are reduced.

[0050] Furthermore, the number of repeated calculations does not exceed 500.

[0051] It should be noted that there is no limit to the number of repetitions, which is approximately 300-500 times and can be adjusted according to actual needs.

[0052] Specifically, in a specific embodiment of the present invention, in order to reduce the amount of computation, improve computational efficiency, and simultaneously achieve the optimal result, the number of repetitions is selected as 500.

[0053] Understandably, by performing a large number of calculations, the influence of random factors on the experimental results can be avoided. Furthermore, the movement patterns of each discrete feature point are not uniform in different calculation processes, which makes the results more comprehensive and reliable.

[0054] Furthermore, the preset angle range is -15° to 15°.

[0055] It should be noted that the rotation angle is used to facilitate the adjustment of the movement distance of each discrete feature point and to obtain comprehensive data. Rotating the discrete feature points by a certain angle allows the auxiliary line segments to intersect with the original graphic contour more quickly, thereby speeding up the efficiency of the first calculation and further improving the contour extraction efficiency of the SEM image.

[0056] Understandably, this design limits the rotation angle of discrete feature points for two reasons: first, to reduce the range of motion, so that the optimal solution within that range can be obtained in a finite number of calculations; second, because an excessively large rotation angle may distort the original image, a preset rotation angle is provided to ensure that the calculation result is basically consistent with the original image.

[0057] Furthermore, the loss value is obtained based on the loss function calculation formula, which is: Cost = , where n is the total number of extracted feature points and k is the feature point number.

[0058] Understandably, by using a loss function, the calculation results are supported by data, making the results more reliable.

[0059] For further details, please refer to Figure 3 Before calculating the loss value using the loss function, the following steps are also included:

[0060] S31: Determine whether the auxiliary line segment intersects with the original figure;

[0061] S32: If they intersect, calculate the shortest distance from the midpoint of the auxiliary line segment to the original figure, and use the shortest distance as the movement distance of the discrete feature point to calculate the loss value.

[0062] S33: If they do not intersect, record the shortest distance from the discrete feature point to the original figure, and use the shortest distance as the movement distance of the discrete feature point to calculate the loss value.

[0063] It should be noted that the generation method of auxiliary line segments is not unique. They can be generated from one side along the normal direction of discrete feature points, or they can be generated from opposite sides along the normal direction. The length of the two ends is not limited. Specifically, in the specific embodiment of the present invention, the auxiliary line segments are generated symmetrically from both ends of discrete feature points along the normal direction, that is, the midpoint of the line segment is the discrete feature point itself. When only a few feature points generate auxiliary line segments that do not intersect with the original figure, the calculation will be stopped, and the actual movement distance of the point will be recorded as the calculation data.

[0064] Optionally, the calculation should be stopped if the number of discrete feature points that do not intersect does not exceed 5% of the total number.

[0065] Understandably, this design defines the intersection of auxiliary line segments as a set of results. At the same time, to prevent meaningless calculations from being added when discrete feature points are far apart, the current coordinates of non-intersecting points are used as the maximum value of motion for calculation, which further improves the computational efficiency and thus improves the contour extraction efficiency of SEM images.

[0066] For further details, please refer to Figure 4 Adjusting discrete feature points specifically includes the following steps:

[0067] S61: The motion distance and rotation angle of each discrete feature point in the set of calculation results with the smallest loss value are used to derive the transformed feature point coordinates based on the preset model.

[0068] Understandably, this method can quickly input the original coordinates and displacement distance of discrete feature points into the transformed coordinates of the output, thereby improving the efficiency of the output results.

[0069] Furthermore, the preset model is a transformation matrix, and the expression for the transformation matrix is: * Where x and y are the original coordinates, and t x and t y x is the displacement in the x and y directions, and x' and y' are the transformed coordinates.

[0070] Furthermore, the expression for the distance from the midpoint of the transformed auxiliary line segment to the original figure is: Distance(k) = , where k is the midpoint of the line segment generated by the feature point.

[0071] Understandably, this expression allows for an intuitive analysis of the shortest movement distance between discrete feature points and the original graphic. Furthermore, the rotation angle of the discrete feature points can be expressed along with the matrix to obtain the result, making the interaction between the various variables and the result more intuitive.

[0072] Please see Figure 5 The present invention also provides a contour positioning system 1, which uses the SEM image contour positioning method described above for contour positioning. The contour positioning system 1 includes a recognition module 11, a calculation module 12, and an operation module 13. The recognition module 11 is used to acquire discrete feature points of the initial image and use them for subsequent operations. The calculation module 12 is used to perform motion calculations on the discrete feature points and record the results, and feed the final results back to the operation module 13. The operation module 13 moves and adjusts the acquired discrete feature points according to the final results to obtain the optimized contour of the SEM scan image and performs positioning. It has the same beneficial effects as the SEM image contour positioning method described above, and will not be elaborated further here.

[0073] Furthermore, the contour localization system 1 can perform contour localization on the GDS image.

[0074] It should be noted that SEM image processing and GDS image processing are common image processing methods.

[0075] Understandably, through this design, the contour positioning system 1 can not only analyze and process SEM images but also process GDS images, thus improving its versatility.

[0076] The present invention also provides a storage medium, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the SEM image contour localization method as described above, and has the same beneficial effects as the above-described SEM image contour localization method, which will not be elaborated here.

[0077] It is understood that, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), it performs the functions defined in the methods of this application. It should be noted that the computer-readable medium described in this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. Computer-readable storage media include, but are not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0078] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0079] In the embodiments provided by this invention, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined based on A. However, it should also be understood that determining B based on A does not mean determining B solely based on A; B can also be determined based on A and / or other information.

[0080] It should be understood that the phrase "one embodiment" or "an embodiment" throughout the specification means that a specific feature, structure, or characteristic related to the embodiment is included in at least one embodiment of the invention. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Those skilled in the art should also recognize that the embodiments described in the specification are optional embodiments, and the actions and modules involved are not necessarily essential to the invention.

[0081] In various embodiments of the present invention, it should be understood that the sequence number of each process does not necessarily imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0082] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It is particularly important to note that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0083] Compared with the prior art, the SEM image contour localization method, contour localization system, and computer medium of the present invention have the following advantages:

[0084] 1. A SEM image contour localization method according to the present invention includes the following steps: acquiring a SEM scan image and extracting discrete feature points of the contour in the original scan image; generating auxiliary line segments connected to each discrete feature point based on the initial position of each discrete feature point; translating or rotating each discrete feature point in a preset direction within its plane until the auxiliary line segment intersects with the original image and calculating a loss value based on the total movement distance of each discrete point; repeating the movement and loss value calculation a preset number of times, continuously comparing the magnitude of the loss value obtained each time until the preset number of movements is completed; obtaining the final position of each discrete feature point based on a set of movements with the minimum loss value after the preset number of movements; adjusting the corresponding discrete feature points based on the final position to obtain an optimized contour of the SEM scan image and perform localization. This method allows for motion calculation of discrete feature points and finds the optimal contour curve by finding the minimum movement distance relative to the original image. Furthermore, this calculation method effectively reduces the computational load of data processing in conventional methods, improves computational efficiency, and thus improves the contour extraction efficiency of SEM images.

[0085] 2. The method for generating auxiliary line segments in the SEM image contour localization method of the present invention specifically includes the following steps: selecting a discrete feature point; based on the position of the discrete feature point in the original image, generating an auxiliary line segment of a certain length along the normal direction of the original image contour. This design limits the length of the auxiliary line segments, making the results more reliable during the intersection of auxiliary line segments when all discrete feature points move, and reducing accidental results caused by different lengths of the auxiliary line segments.

[0086] 3. In the SEM image contour localization method of this invention, the preset number of calculations is less than or equal to 500. By performing a large number of calculations, the influence of random factors on the experimental results is avoided. Furthermore, the movement patterns of each discrete feature point are not uniform in different calculation processes, resulting in more comprehensive coverage and greater reliability of the results.

[0087] 4. In the SEM image contour localization method of the present invention, the preset angle range is -15° to 15°. The rotation angle is set to facilitate the adjustment of the movement distance of each discrete feature point and to obtain comprehensive data. Through this design, the rotation angle of the discrete feature points is limited. Firstly, it reduces the range of motion, so that the best solution within this range can be obtained in a limited number of calculations. Secondly, if the rotation angle is too large, it may cause the original image to be distorted. To ensure that the calculation result is basically consistent with the original image, a preset rotation angle is provided.

[0088] 5. The SEM image contour localization method of the present invention further includes the following steps before calculating the loss value: determining whether the auxiliary line segment intersects with the original image; if they intersect, calculating the shortest distance from the midpoint of the auxiliary line segment to the original image, and using this shortest distance as the movement distance of the auxiliary line segment for loss value calculation; if they do not intersect, recording the shortest distance from the discrete feature point to the original image, and using this shortest distance as the movement distance of the discrete feature point for loss value calculation. This design defines the cases of intersecting auxiliary line segments as a set of results. Simultaneously, in cases where discrete feature points are far apart, it prevents the addition of meaningless calculations by incorporating the distance from non-intersecting points to the original image into the loss value calculation, further improving computational efficiency and thus enhancing the contour extraction efficiency of SEM images.

[0089] 6. The adjustment of discrete feature points in the SEM image contour localization method of the present invention specifically includes the following steps: The motion distance and rotation angle of each discrete feature point in the set of motion results with the minimum loss value are used to derive the transformed feature point coordinates based on a preset model. This method can quickly input the original coordinates and displacement distance of the discrete feature points into the output transformed coordinates, improving the output efficiency.

[0090] 7. In the SEM image contour localization method of the present invention, the preset model is a transformation matrix, and the transformation matrix is: * Where x and y are the original coordinates, and t x and t y x is the displacement in the x and y directions, and x' and y' are the transformed coordinates.

[0091] 8. This invention also provides a contour localization system, which uses the SEM image contour localization method described above for contour localization. The system comprises a recognition module, a calculation module, and an operation module. The recognition module acquires discrete feature points of the initial image for subsequent operations. The calculation module performs motion calculations on the discrete feature points and records the results, feeding the final results back to the operation module. The operation module adjusts the acquired discrete feature points according to the final results to obtain an optimized contour of the SEM scan image and performs localization. This system has the same beneficial effects as the aforementioned SEM image contour localization method, and will not be elaborated upon here.

[0092] 9. The contour localization system of the present invention can perform contour localization on GDS images. SEM image processing and GDS image processing are common image processing methods. Through this design, the contour localization system can not only analyze and process SEM images but also process GDS images, thus improving its versatility.

[0093] 10. The present invention also provides a storage medium, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the SEM image contour localization method as described above, and has the same beneficial effects as the above-described SEM image contour localization method, which will not be elaborated here.

[0094] The SEM image contour localization method, contour localization system, and computer medium disclosed in the embodiments of the present invention have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention. Any modifications, equivalent substitutions, and improvements made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for contour localization in SEM images, characterized in that: Includes the following steps: Obtain the SEM scan image and extract the discrete feature points of the contour in the original scan image; Generate auxiliary line segments connected to each discrete feature point based on its initial position; For each discrete feature point, translate or rotate it in a preset direction within its plane until the auxiliary line segment intersects with the original graphic, and calculate the loss value based on the total movement distance of each discrete feature point. Repeat the preset number of movements and loss value calculations, continuously comparing the magnitude of the loss value obtained each time until the preset number of movements is completed; The final position of each discrete feature point is obtained from a set of motions based on the minimum loss value after a preset number of motions. Based on the final position, the corresponding discrete feature points are adjusted to obtain the optimized contour of the SEM scan image and perform localization. The method for generating auxiliary line segments specifically includes the following steps: Select a discrete feature point; Based on the position of the discrete feature point in the original graphic, generate an auxiliary line segment of a certain length along the normal direction of the outline of the original graphic. All discrete feature points need to generate auxiliary line segments of equal length. Before calculating the loss value, the following steps are also included: determining whether the auxiliary line segment intersects with the original figure; if they intersect, calculating the shortest distance from the midpoint of the auxiliary line segment to the original figure, and using the shortest distance as the movement distance of the auxiliary line segment to calculate the loss value; if they do not intersect, recording the shortest distance from the discrete feature point to the original figure, and using the shortest distance as the movement distance of the discrete feature point to calculate the loss value.

2. The SEM image contour localization method as described in claim 1, characterized in that: The preset number of times is less than or equal to 500.

3. The SEM image contour localization method as described in claim 1, characterized in that: The rotation angle range of the discrete feature points is -15° to 15°.

4. The SEM image contour localization method as described in claim 1, characterized in that: Adjusting discrete feature points specifically includes the following steps: The motion distance and rotation angle of each discrete feature point in the set of motion results with the minimum loss value are used to derive the transformed feature point coordinates based on a preset model.

5. The SEM image contour localization method as described in claim 4, characterized in that: The preset model is a transformation matrix, and the transformation matrix is: * ; Where θ is the rotation angle, x and y are the original coordinates, and t is the rotation angle. x and t y x is the displacement in the x and y directions, and x' and y' are the transformed coordinates.

6. A contour localization system, which uses the SEM image contour localization method as described in any one of claims 1-5 for contour localization, characterized in that: The contour localization system includes a recognition module, a calculation module, and an operation module. The recognition module is used to acquire discrete feature points of the initial image and use them for subsequent operations. The calculation module is used to perform motion calculations on the discrete feature points and record the results, and feed the final results back to the operation module. The operation module moves and adjusts the acquired discrete feature points according to the final results to obtain the optimized contour of the SEM scan image and performs localization.

7. The contour positioning system as described in claim 6, characterized in that: The contour localization system can perform contour localization on GDS images.

8. A computer medium comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the SEM image contour localization method as described in any one of claims 1-5.

Images