Scanning electron microscope image graphic grouping methods and related products

Abstract

This invention provides a method for grouping graphic elements in scanning electron microscope (SEM) images and related products. The method includes: acquiring the SEM image to be grouped and the corresponding design layout; extracting the contours of the graphic elements in the SEM image to obtain an overall image contour comprising multiple graphic contours; establishing a correspondence between the graphic contours and the design elements in the design layout; and grouping the graphic contours according to the feature values ​​of the design elements. This invention utilizes the one-to-one correspondence between the design elements in the design layout and the graphic contours in the SEM image, and groups them using the feature values ​​of the design elements, rather than directly using the features of the graphic contours themselves. This achieves automatic grouping of graphic contours and solves the problem of low efficiency in manual grouping.

Description

Technical Field

[0001] This invention relates to the field of semiconductor technology, and in particular to a method for graphic grouping of scanning electron microscope images and related products. Background Technology

[0002] The manufacturing process of semiconductor integrated circuits generates a large number of scanning electron microscope (SEM) images. These SEM images need to be analyzed to assess and evaluate various processes in the manufacturing process. Among various SEM image analysis methods, contour extraction and analysis of shapes in SEM images are widely used in defect detection, critical dimension measurement, and simulation and modeling of optical proximity correction (OPC).

[0003] SEM images generated during semiconductor integrated circuit manufacturing often contain significant image noise, resulting in overly coarse contours extracted from them, which may not meet the requirements of some applications. Therefore, it is essential to smooth the contours of SEM images to remove burrs and noise and reduce image errors caused by optical proximity effects.

[0004] Silicon wafers contain regions with numerous periodically repeating patterns (patterns or design layouts), such as SRAM (Static Random Access Memory) regions. SEM images of these regions appear as composed of similar, periodically repeating patterns. Grouping the patterns in the SEM image and utilizing the similarities between these patterns can help smooth the contours of the SEM image. Therefore, it is necessary to group the patterns in existing SEM images.

[0005] In existing technologies, SEM images composed of periodically repeating similar patterns are typically processed in two ways: The first method selects an SEM image containing only one type of periodically repeating pattern, thus generally eliminating the need for grouping. The location of the complete pattern outline in the SEM image is determined using a given gauge file. The second method, for SEM images containing periodically repeating patterns, typically employs a manual approach, manually specifying and grouping the complete pattern outline within the SEM image.

[0006] In existing technologies, when identifying complete graphics in a SEM image using a given gauge file, it is necessary to ensure that the SEM image contains only one type of periodically repeating graphic and only supports translation operations. This method becomes unsuitable when the SEM image contains multiple periodically repeating graphics, or when the graphics exhibit rotation, mirroring, or other similar phenomena. When grouping graphics in a SEM image using manually specified methods, the limited human recognition capabilities make it impossible to distinguish the corresponding graphics in the SEM image for polygons that are distinct in the design layout, leading to incorrect grouping and reduced accuracy. Furthermore, manual recognition and grouping are also limited in efficiency, as they cannot quickly process multiple SEM images. Summary of the Invention

[0007] In view of the above problems, the present invention is proposed to provide a method for graphic grouping of scanning electron microscope images that overcomes or at least partially solves the above problems.

[0008] One objective of this invention is to automatically group graphics, especially for graphics with multiple periodic repetitions, or graphics that exhibit rotation, mirroring, or other phenomena.

[0009] A further objective of this invention is to improve the success rate and efficiency of component assembly.

[0010] Another further objective of this invention is to avoid incorrect grouping caused by the difficulty in reflecting minute differences between polygons in the design layout on the SEM image.

[0011] Another further objective of the present invention is to avoid the influence of incomplete graphic outlines at the image edges on grouping.

[0012] Another further objective of the present invention is to reduce the number of groups, thereby increasing the number of graphic outlines within each group, so as to effectively group the images even when the number of graphics in the SEM image is small.

[0013] In particular, the present invention provides a method for graphic grouping of scanning electron microscope images, comprising:

[0014] Acquire scanning electron microscope (SEM) images to be grouped and the corresponding design layouts;

[0015] The contours of the graphics in the scanning electron microscope image are extracted to obtain the overall image contour including multiple graphic contours;

[0016] Establish the correspondence between the graphic outline and the design graphic in the design layout;

[0017] The graphic contours are grouped according to the feature values ​​of the designed graphic.

[0018] Optionally, the characteristic value of the design graphic is the hash value of the design graphic;

[0019] The step of grouping the graphic contours according to the feature values ​​of the designed graphic includes:

[0020] Obtain the hash value for each of the design graphics;

[0021] The design graphics are grouped according to the hash value;

[0022] The graphic contours are grouped according to the correspondence.

[0023] Optionally, the step of obtaining the hash value of each of the design graphics includes:

[0024] Select the origin of the coordinate system on each of the design graphics;

[0025] Geometric transformations are performed on the corresponding design graphics based on the selected coordinate origin;

[0026] The design graphic after geometric transformation is calculated using hash encoding to obtain the hash value of the design graphic.

[0027] Optionally, the step of obtaining the hash value of each of the design graphics includes:

[0028] The design graphic is rotated and / or mirrored to obtain an auxiliary graphic;

[0029] Select the origin of the coordinate system on both the design drawing and the auxiliary drawing;

[0030] Geometric transformations are performed on the corresponding design graphics and auxiliary graphics based on the selected coordinate origin.

[0031] The design drawing and the auxiliary drawing after geometric transformation are calculated using hash encoding to obtain multiple calculated values;

[0032] The smallest calculated value is selected as the hash value of the design graphic.

[0033] Optionally, the method for grouping scanning electron microscope images further includes, before the step of grouping the graphic contours according to the feature values ​​of the designed graphic:

[0034] Obtain the graphic contours that need to be grouped from the overall contour of the image;

[0035] Based on the correspondence, determine the design graphics corresponding to the graphic outlines that need to be grouped;

[0036] The step of grouping the graphic contours according to the feature values ​​of the design graphics specifically involves grouping the graphic contours that need to be grouped according to the feature values ​​of the design graphics corresponding to the graphic contours that need to be grouped.

[0037] Optionally, the step of obtaining the graphic contours that need to be grouped in the overall contour of the image includes:

[0038] Overlay the graphic outline and the corresponding design graphic together;

[0039] Determine whether the outline of the graphic is completely within the corresponding design graphic;

[0040] If so, determine that the graphic contour is a graphic contour that needs to be grouped.

[0041] Optionally, the method for grouping patterns in scanning electron microscope images further includes, after the step of extracting the contours of the patterns in the scanning electron microscope images:

[0042] Output the overall outline of the image and the design layout in OASIS format.

[0043] According to another aspect of the present invention, a computer-readable storage medium is also provided, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the graphic grouping method for scanning electron microscope images described above.

[0044] According to another aspect of the present invention, a computer program product is also provided, comprising a computer program that, when executed by a processor, implements the steps of the graphic grouping method for scanning electron microscope images described above.

[0045] According to another aspect of the present invention, a computer device is also provided, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the graphic grouping method for scanning electron microscope images described above.

[0046] The graphic grouping method for scanning electron microscope (SEM) images of the present invention utilizes the one-to-one correspondence between the design graphics in the design layout and the graphic contours in the SEM image, and groups the graphics using the feature values ​​of the design graphics, rather than directly using the features of the graphic contours themselves. This achieves automatic grouping of graphic contours and solves the problem of low efficiency in manual grouping. Furthermore, since the shapes of the design graphics are relatively standard, even minor differences between the design graphic bounding boxes can be correctly identified, preventing grouping errors caused by the inability to distinguish minor differences between graphic contours when directly grouping graphics. In other words, the embodiments of the present invention can avoid erroneous grouping caused by minor differences between polygons in the design layout that are difficult to reflect in the SEM image. Clearly, the embodiments of the present invention improve the grouping success rate.

[0047] Furthermore, in the image grouping method for scanning electron microscope (SEM) images of the present invention, for hash calculation, if the inputs are different, i.e., the designed images are different, the resulting hash values ​​will be completely different; if the inputs are the same, the resulting hash values ​​will definitely be the same, which provides accuracy for grouping. At the same time, hash value calculation is relatively efficient, which also improves the efficiency of image grouping. Grouping by obtaining hash values ​​through hash calculation does not require guaranteeing that the SEM image contains only one type of periodically repeating pattern. Grouping can also be performed when the SEM image contains only multiple periodically repeating patterns. That is, the embodiments of the present invention can also quickly and efficiently group images even when there are multiple periodically repeating patterns, or when the images exhibit rotation, mirroring, or other phenomena.

[0048] The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments of the invention in conjunction with the accompanying drawings. Attached Figure Description

[0049] The following sections will describe some specific embodiments of the invention in detail by way of example and not limitation, with reference to the accompanying drawings. The same reference numerals in the drawings denote the same or similar parts or portions. Those skilled in the art should understand that these drawings are not necessarily drawn to scale. In the drawings:

[0050] Figure 1 This is a schematic diagram of a SEM image according to an embodiment of the present invention;

[0051] Figure 2 This is a flowchart illustrating a method for graphical grouping of scanning electron microscope images according to an embodiment of the present invention;

[0052] Figure 3 This is a flowchart illustrating a method for graphical grouping of scanning electron microscope images according to an embodiment of the present invention;

[0053] Figure 4This is a partial flowchart illustrating a method for graphical grouping of scanning electron microscope images according to an embodiment of the present invention;

[0054] Figure 5 It is to utilize Figure 4 The diagram shows the grouping results obtained by the graphic grouping method for scanning electron microscope images.

[0055] Figure 6 This is a partial flowchart illustrating a method for graphical grouping of scanning electron microscope images according to an embodiment of the present invention;

[0056] Figure 7 It is to utilize Figure 6 The diagram shows the grouping results obtained by the graphic grouping method for scanning electron microscope images.

[0057] Figure 8 This is a partial flowchart illustrating a method for graphical grouping of scanning electron microscope images according to an embodiment of the present invention;

[0058] Figure 9 This is a flowchart illustrating a method for graphical grouping of scanning electron microscope images according to an embodiment of the present invention;

[0059] Figure 10 This is a schematic diagram illustrating the relationship between graphic outlines and corresponding design graphics in a graphic grouping method for scanning electron microscope images according to an embodiment of the present invention.

[0060] Figure 11 This is a schematic diagram illustrating the overlap relationship between graphic outlines and corresponding design graphics in a graphic grouping method for scanning electron microscope images according to an embodiment of the present invention.

[0061] Figure 12 This is a schematic diagram illustrating the overlap relationship between graphic outlines and corresponding design graphics in a graphic grouping method for scanning electron microscope images according to an embodiment of the present invention.

[0062] Figure 13 This is a schematic diagram of a computer program product according to an embodiment of the present invention;

[0063] Figure 14 This is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention; and

[0064] Figure 15 This is a schematic diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0065] This embodiment provides a scheme for graphic grouping of scanning electron microscope images. Figure 2This is a flowchart illustrating a method for graphical grouping of scanning electron microscope images according to an embodiment of the present invention. The method generally includes:

[0066] Step S100: Obtain the scanning electron microscope (SEM) images to be grouped and the corresponding design layouts. The scanning electron microscope (SEM) images are also known as SEM images, such as... Figure 1 As shown. SEM images typically have multiple graphics, each with a corresponding graphic outline. SEM images have corresponding design layouts 40, such that each graphic outline 42 corresponds one-to-one with a design graphic 41 in the design layout 40.

[0067] Step S200: Extract the contours of the graphics in the scanning electron microscope image to obtain the overall image contour including multiple graphic contours 42.

[0068] Step S300: Establish the correspondence between the graphic outline 42 and the design graphic 41 in the design layout 40. By establishing the correspondence, each graphic outline 42 is associated with its corresponding design graphic 41.

[0069] Step S400: Group the graphic contours 42 according to the feature values ​​of the design graphic 41. In this step, the features of the graphic contours 42 are not used directly for grouping; instead, the feature values ​​of the design graphic 41 corresponding to the graphic contours are used for grouping. The design graphic 41 is relatively standard, which helps to improve the accuracy of grouping.

[0070] In this embodiment of the invention, by utilizing the one-to-one correspondence between the design graphics 41 in the design layout 40 and the graphics in the scanning electron microscope image, and by grouping the design graphics 41 using their feature values ​​instead of directly using the features of the graphic contours themselves, automatic grouping of graphic contours is achieved, solving the problem of low efficiency in manual grouping. Furthermore, since the shapes of the design graphics 41 are relatively standard, even minor differences between the design graphic bounding boxes can be correctly identified, preventing grouping errors caused by the inability to distinguish minor differences between graphic contours when directly grouping graphics. In other words, this embodiment of the invention avoids erroneous grouping caused by minor differences between polygons in the design layout that are difficult to reflect in the SEM image. Clearly, this embodiment of the invention improves the grouping success rate.

[0071] In some embodiments of the present invention, such as Figure 3 As shown, the characteristic value of the design graphic is the hash value of the design graphic. Step S400, the step of grouping the graphic outline according to the characteristic value of the design graphic, specifically includes:

[0072] Step S410: Obtain the hash value of each design graphic 41.

[0073] Step S420: Group the design graphics 41 according to their hash values. Specifically, design graphics 41 with the same hash value can be grouped together.

[0074] Step S430: Group the graphic outlines 42 according to the correspondence.

[0075] Hash, also known as hashing, is a process of converting input data of arbitrary length (pre-mapped) into a fixed-length output (hash value) using a specific algorithm. Hash has the following characteristics: efficiency – hash algorithms can quickly calculate the hash value of input data, maintaining high efficiency even when processing large amounts of data. determinism – identical input data always produces the same hash value, ensuring the consistency and predictability of the algorithm. Collision resistance – finding two different input data that produce the same hash value (i.e., a collision) is very difficult. Therefore, for hash calculation, if the inputs are different (i.e., different design patterns), the resulting hash values ​​will be completely different; if the inputs are the same, the resulting hash values ​​will definitely be the same, providing accuracy for grouping. At the same time, the relatively efficient hash value calculation also improves the efficiency of pattern grouping. Grouping based on hash values ​​obtained through hash calculation does not require guaranteeing that the SEM image contains only one type of periodically repeating pattern. Grouping can also be performed when the SEM image contains only multiple periodically repeating patterns. That is, this embodiment of the invention can quickly and efficiently group patterns even when there are multiple periodically repeating patterns or when patterns exhibit rotation, mirroring, or other phenomena. Grouping results can be as follows Figure 5 and Figure 7 As shown, the numbers in the figure represent the grouping of the graphics. Design graphics 41 with the same number are in the same group.

[0076] Moreover, since the design graphics 41 in the design layout 40 correspond to the graphic outlines that need to be grouped, the grouping result of the design graphics 41 to be grouped is the grouping result of the graphics in the scanning electron microscope image, that is, the grouping result of the graphic outlines in the scanning electron microscope image.

[0077] In some embodiments of the present invention, such as Figure 4 As shown, step S410 involves obtaining the hash value of each design graphic, including:

[0078] Step S411: Select the origin of the coordinate system on each design graphic 41.

[0079] Step S412: Perform a geometric transformation on the corresponding design graphic 41 based on the selected coordinate origin.

[0080] Step S413: Calculate the hash value of the geometrically transformed design graphic 41 using hash encoding.

[0081] In this embodiment of the invention, by selecting a new coordinate origin and transforming the coordinate system, it is possible to prevent two design graphics 41 belonging to the same group from having different coordinate origin positions, leading to different inputs during hash calculation. Therefore, it prevents grouping errors caused by different calculation results. This embodiment of the invention, by changing the coordinate origin, ensures the consistency of input data during hash calculation, improves the accuracy of graphic grouping, and the obtained grouping results are as follows: Figure 5 As shown. For example, the lower left corner of each design graphic 41 can be used as the new origin of the coordinate system.

[0082] In other embodiments of the invention, such as Figure 6 As shown, step S410 involves obtaining the hash value of each design graphic, including:

[0083] Step S414: Rotate and / or mirror the design graphic 41 to obtain an auxiliary graphic.

[0084] Step S415: Select the origin of the coordinate system on the design graphic 41 and the auxiliary graphic respectively.

[0085] Step S416: Perform geometric transformations on the corresponding design graphic 41 and auxiliary graphic based on the selected coordinate origin.

[0086] Step S417: Use hash encoding to calculate the geometrically transformed design graphic 41 and auxiliary graphic to obtain multiple calculated values.

[0087] Step S418: Select the smallest calculated value as the hash value of the design graphic 41.

[0088] In this embodiment of the invention, when the SEM image contains graphics that exhibit rotation, mirroring, or other phenomena, these graphics are essentially the same type of scanning electron microscope image, belonging to the same group. However, directly performing hash calculations and grouping them into different groups increases the number of groups, and the graphics in these two groups cannot be used simultaneously to aid in the smoothing operation of the SEM image contour. Therefore, to reduce the number of groups, each graphic to be grouped undergoes a geometric transformation to form a graphic group based on the graphic to be grouped. When two essentially identical graphics form two graphic groups, the minimum hash value in the two graphic groups will definitely be the same, thus grouping the two graphics into one group. This reduces the number of groups and increases the number of graphic contours within each group, which helps in the smoothing operation of the scanning electron microscope image contour. Furthermore, it effectively groups graphics even when the number of graphics in the SEM image is small, preventing the number of graphic contours within each group from being too small. Moreover, this embodiment of the invention also considers the situation where such design graphics 41 appear in the design layout 40. The obtained grouping results can be as follows... Figure 7 As shown, there are obviously fewer groups, and the number of graphic outlines within a certain group is significantly higher.

[0089] In some embodiments of the present invention, after the step of extracting the outline of the pattern in the scanning electron microscope image, the method further includes: outputting the overall outline of the image and the design layout as a file in OASIS format. OASIS (Open Artwork System Interchange Standard) format files play a crucial role in integrated circuit design, as they can be used to represent photolithographic layouts that record photolithographic patterns, and are beneficial for improving design and manufacturing efficiency.

[0090] In some embodiments of the present invention, such as Figure 8 As shown, the method for grouping images in scanning electron microscope images, before the step of grouping the image contours according to the feature values ​​of the designed images, also includes:

[0091] Step S500: Obtain the graphic contours 42 that need to be grouped in the overall image contour;

[0092] Step S600: Determine the design graphics 41 corresponding to the graphic contours 42 that need to be grouped according to the correspondence relationship. Specifically, group the graphic contours 42 according to the feature values ​​of the design graphics 41.

[0093] In this embodiment of the invention, given the characteristics of the graphic contours themselves, some graphic contours are meaningless to group, and some graphic contours do not need to be grouped. Only the graphic contours that need to be grouped and the design graphics corresponding to the graphic contours that need to be grouped can be selected, thereby reducing the amount of calculation and improving the grouping efficiency.

[0094] In some embodiments of the present invention, such as Figure 9 As shown, step S500 involves obtaining the graphic contours that need to be grouped within the overall image contour, including:

[0095] Step S510: Overlap the graphic outline 42 and the corresponding design graphic 41 together; as shown Figure 10 , Figure 11 , Figure 12 As shown.

[0096] Step S520: Determine whether the graphic outline 42 is completely within the corresponding design graphic 41.

[0097] If so, proceed to step S530 to determine that the graphic outline 42 is a graphic outline that needs to be grouped. Then, the design graphic 41 corresponding to the graphic outline 42 is the design graphic 41 that needs to be grouped. For example... Figure 11 The graphic outline 42 and the design graphic 41 are shown in the figure.

[0098] If not, proceed to step S540 and discard the graphic outline 42, which also means discarding the design graphic 41 corresponding to the graphic outline 42. Figure 12 The graphic outline 42 and the design graphic 41 are shown in the figure.

[0099] In this embodiment of the invention, the graphic outline 42 is completely within the corresponding design graphic 41, such as... Figure 11 As shown, the surface outline 42 belongs to a complete graphic outline, and selecting such a graphic is beneficial for performing other operations on the scanning electron microscope image. If the graphic outline 42 is partially or entirely within the corresponding design graphic 41, such as Figure 12 As shown, these graphic contours can be considered as graphic contours with incomplete edges in scanning electron microscope images. They are not graphic contours that need to be grouped, that is, they do not need to be grouped and should be discarded. Therefore, the embodiments of the present invention can avoid the influence of graphic contours 42 with incomplete edges in scanning electron microscope images on grouping.

[0100] In the graphic grouping method for scanning electron microscope images according to this embodiment of the invention, the complete graphic outline 42 in the SEM image is identified using the design layout 40 information, the correspondence between the graphic outline 42 and the design graphic 41 (also referred to as a polygon) in the design layout 40 is established, and grouping is performed using a hash value-based method. Using this method will have the following beneficial effects:

[0101] High accuracy: This method utilizes the information of the design layout 40, avoiding incorrect grouping caused by the small differences between polygons in the design layout 40 being difficult to reflect in the SEM image; This method identifies complete graphic contours 42 in the SEM image outline, avoiding the influence of incomplete graphic contours 42 on the grouping.

[0102] Fully automated: The entire process of recognizing and grouping complete graphic contours in SEM images is achieved through automated algorithms, making it faster and more efficient than manual methods when processing large numbers of SEM images.

[0103] Wide applicability: This method enables the grouping of similar patterns in SEM images, making it applicable to regions on silicon wafers with multiple periodic repeating patterns. The method considers rotation and mirroring during grouping, reducing the number of groups and increasing the number of graphic outlines within each group, thus enabling effective grouping even when the number of graphics in the SEM image is small.

[0104] The flowchart provided in this embodiment is not intended to indicate that the operations of the method will be performed in any particular order, or that all operations of the method are included in every case. Furthermore, the method may include additional operations. Within the scope of the technical concept provided by the method in this embodiment, additional variations can be made to the above method.

[0105] It should be understood that in some embodiments, the components may be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods may be implemented using software or firmware stored in memory and executed by a suitable instruction execution system.

[0106] This embodiment also provides a computer program product 10, a computer-readable storage medium 20, and a computer device 30. Figure 13 This is a schematic diagram of a computer program product 10 according to an embodiment of the present invention. Figure 14 This is a schematic diagram of a computer-readable storage medium 20 according to an embodiment of the present invention. Figure 15 This is a schematic diagram of a computer device 30 according to an embodiment of the present invention. The computer program product 10 includes a computer program 11, which, when executed by the processor 32, implements the steps of the graphic grouping method for scanning electron microscope images described above. A computer-readable storage medium 20 stores the computer program 11 thereon, which, when executed by the processor 32, implements the steps of the graphic grouping method for scanning electron microscope images described above. The computer device 30 may include a memory 31, a processor 32, and the computer program 11 stored in the memory 31 and running on the processor 32.

[0107] The computer program 11 used to perform the operations of this invention may be assembly instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, integrated circuit configuration data, or source code or object code written in any combination of one or more programming languages ​​and procedural programming languages. The computer program 11 may execute 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 the latter case, the remote computer may 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 may be connected to an external computer. In some embodiments, to perform aspects of this invention, electronic circuits, including, for example, programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), may execute computer-readable program instructions using status information from computer-readable program instructions to personalize the electronic circuits.

[0108] For the purposes of this embodiment, computer program product 10 is a related product that includes computer program 11.

[0109] For the purposes of this embodiment, the computer-readable storage medium 20 is a tangible device capable of holding and storing a computer program 11. It can be any device capable of containing, storing, communicating, propagating, or transmitting the computer program 11 for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable storage medium 20 include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable optical disc read-only memory (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical encoding device, and any suitable combination thereof.

[0110] Computer device 30 can be, for example, a server, desktop computer, laptop computer, tablet computer, or smartphone. In some examples, computer device 30 can be a cloud computing node. Computer device 30 can be described in the general context of computer system executable instructions (such as program modules) executed by a computer system. Typically, program modules can include routines, programs, object programs, components, logic, data structures, etc., that perform specific tasks or implement specific abstract data types. Computer device 30 can be implemented in a distributed cloud computing environment where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can reside on local or remote computing system storage media, including storage devices.

[0111] Computer device 30 may include a processor 32 adapted to execute stored instructions and a memory 31 that provides temporary storage space for the operation of instructions during operation. The processor 32 may be a single-core processor, a multi-core processor, a computing cluster, or any other configuration. The memory 31 may include random access memory (RAM), read-only memory, flash memory, or any other suitable storage system.

[0112] Computer device 30 may also include a network adapter / interface and an input / output (I / O) interface. The I / O interface allows external devices that can be connected to the computer device to input and output data. The network adapter / interface provides communication between the computer device and a network, typically represented as a communication network.

[0113] Therefore, those skilled in the art should recognize that although numerous exemplary embodiments of the present invention have been shown and described in detail herein, many other variations or modifications conforming to the principles of the present invention can be directly determined or derived from the disclosure of the present invention without departing from the spirit and scope of the invention. Thus, the scope of the present invention should be understood and construed as covering all such other variations or modifications.

Claims

1. A method for graphic grouping of scanning electron microscope images, characterized in that, include: Acquire scanning electron microscope (SEM) images to be grouped and the corresponding design layouts; The contours of the graphics in the scanning electron microscope image are extracted to obtain the overall image contour including multiple graphic contours; Establish the correspondence between the graphic outline and the design graphic in the design layout; The graphic outlines are grouped according to the feature values ​​of the designed graphic. Before the step of grouping the graphic contours according to the feature values ​​of the design graphic, the method further includes: Obtain the graphic contours that need to be grouped from the overall contour of the image; Based on the correspondence, determine the design graphics corresponding to the graphic outlines that need to be grouped; The step of grouping the graphic contours according to the feature values ​​of the design graphics specifically involves grouping the graphic contours that need to be grouped according to the feature values ​​of the design graphics corresponding to the graphic contours that need to be grouped. The step of obtaining the graphic contours that need to be grouped in the overall contour of the image includes: Overlay the graphic outline and the corresponding design graphic together; Determine whether the outline of the graphic is completely within the corresponding design graphic; If so, determine that the graphic contour is a graphic contour that needs to be grouped.

2. The method for graphic grouping of scanning electron microscope images according to claim 1, characterized in that, The characteristic value of the design graphic is the hash value of the design graphic; The step of grouping the graphic contours according to the feature values ​​of the designed graphic includes: Obtain the hash value for each of the design graphics; The design graphics are grouped according to the hash value; The graphic contours are grouped according to the correspondence.

3. The method for graphic grouping of scanning electron microscope images according to claim 2, characterized in that, The step of obtaining the hash value of each design graphic includes: Select the origin of the coordinate system on each of the design graphics; Geometric transformations are performed on the corresponding design graphics based on the selected coordinate origin; The design graphic after geometric transformation is calculated using hash encoding to obtain the hash value of the design graphic.

4. The method for graphic grouping of scanning electron microscope images according to claim 2, characterized in that, The step of obtaining the hash value of each design graphic includes: The design graphic is rotated and / or mirrored to obtain an auxiliary graphic; Select the origin of the coordinate system on both the design drawing and the auxiliary drawing; Geometric transformations are performed on the corresponding design graphics and auxiliary graphics based on the selected coordinate origin. The design drawing and the auxiliary drawing after geometric transformation are calculated using hash encoding to obtain multiple calculated values; The smallest calculated value is selected as the hash value of the design graphic.

5. The method for graphic grouping of scanning electron microscope images according to claim 1, characterized in that, Following the step of contour extraction of the pattern in the scanning electron microscope image, the method further includes: Output the overall outline of the image and the design layout in OASIS format.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the graphic grouping method for scanning electron microscope images according to any one of claims 1 to 5.

7. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the graphic grouping method for scanning electron microscope images as described in any one of claims 1 to 5.

8. A computer device, characterized in that, The method includes a memory, a processor, and a computer program stored on the memory, wherein the processor executes the computer program to implement the steps of the graphic grouping method for scanning electron microscope images according to any one of claims 1 to 5.

Images