Image conversion method, device, computer storage medium and program product

Abstract

The application discloses an image conversion method and device, a computer storage medium and a program product, and relates to the technical field of semiconductors. The method comprises the following steps: obtaining a target binary image, the target binary image comprising N closed graphics; according to binary assignment information of pixel points in the target binary image, each target pixel point located on a graphic edge contour of a target closed graphic is determined by sequentially traversing the pixel points in the target binary image; based on each target pixel point, edge contour coordinates corresponding to the target closed graphic are extracted until edge contour coordinates of the N closed graphics are obtained; and the target binary image is converted into corresponding target artwork based on the edge contour coordinates of the N closed graphics. According to the embodiment of the application, the image conversion can be more efficient and accurate, and the overall image conversion efficiency, algorithm performance and accuracy are effectively improved.

Description

Technical Field

[0001] This application belongs to the field of semiconductor technology, and in particular relates to an image conversion method, device, computer storage medium and program product. Background Technology

[0002] In OPC (Optical Proximity Correction) algorithms, graph-based optimization algorithms often offer higher degrees of freedom and accuracy, significantly improving OPC performance. They are widely used in OPC models, graph-based optimization, and ILT (Inverse Lithography Technology). In this process, the mutual conversion between GDS (Graphic Data System) / OASIS (Open Artwork System Interchange Standard) layouts and images is a common fundamental step. A fast, accurate, and complete image conversion scheme plays a crucial role in the algorithm's performance and accuracy. Currently, in existing technologies, when converting an image to a GDS / OASIS layout, the process typically involves locating pixels on the image, generating a square based on the pixel size, placing it on the GDS / OASIS layout according to its positional relationship, and finally merging the GDS / OASIS images to eliminate internal edges, preserving only the outer contour.

[0003] However, the aforementioned image-to-GDS / OASIS layout conversion process often suffers from low conversion accuracy, poor stability, and low conversion efficiency, making it difficult to apply to mature graphics optimization workflows. Therefore, the industry urgently needs a new image conversion scheme to achieve fast, accurate, and complete conversion between images and layouts. Summary of the Invention

[0004] This application provides an image conversion method, device, computer storage medium, and program product, which can realize image conversion more efficiently and accurately, thereby effectively improving the overall image conversion efficiency and enhancing algorithm performance and accuracy.

[0005] In a first aspect, embodiments of this application provide an image conversion method, which includes:

[0006] Obtain the target binarized image, which contains N closed shapes, where N is a positive integer;

[0007] Based on the binarization assignment information of the pixels in the target binarized image, the target pixels located on the edge contour of the target closed shape are determined by sequentially traversing the pixels in the target binarized image. The target closed shape is any closed shape among N closed shapes whose edge contour coordinates have not been extracted.

[0008] Based on each target pixel, the edge contour coordinates corresponding to the target closed shape are extracted until the edge contour coordinates of N closed shapes are obtained.

[0009] Based on the edge contour coordinates of N closed shapes, the target binarized image is converted into the corresponding target map.

[0010] In some possible implementations, based on the binarization assignment information of pixels in the target binarized image, each target pixel located on the edge contour of the target closed shape is determined by sequentially traversing the pixels in the target binarized image, including:

[0011] Based on the binarization assignment information of pixels in the target binarized image, the first target pixel located on the edge contour of the target closed shape is determined by traversing the pixels in the target binarized image in turn.

[0012] Repeatedly execute the steps of determining the next target pixel based on the local edge contour of the target closed shape under the target pixel and the binarized assignment information of at least some surrounding pixels corresponding to the target pixel, and updating the target pixel to the next target pixel, until each target pixel located on the graphic edge contour of the target closed shape is determined.

[0013] In some possible implementations, the binarization assignment information of pixels in the target binarized image includes either a first assignment or a second assignment, where the first assignment indicates that the pixel is located in a graphic region, and the second assignment indicates that the pixel is located in a non-graphic region. Based on the binarization assignment information of pixels in the target binarized image, the first target pixel located on the graphic edge contour of the target closed graphic is determined by sequentially traversing the pixels in the target binarized image, including:

[0014] The pixels in the target binarized image are traversed sequentially, and the binarization assignment information of the currently traversed pixel and its corresponding multiple neighboring pixels are detected.

[0015] If the currently traversed pixel has the first assigned value, and multiple adjacent pixels simultaneously contain both the first assigned value and the second assigned value, then the currently traversed pixel is determined as the first target pixel located on the edge contour of the target closed shape.

[0016] In some possible implementations, the image transformation method further includes the following steps before updating the target pixel to the next target pixel:

[0017] Add a marker indicating that the coordinate extraction of the target pixel has been successful;

[0018] After identifying each target pixel on the edge contour of the target closed shape, the image conversion method further includes:

[0019] Based on the binarization assignment information of pixels in the target binarized image, the first target pixel located on the edge contour of the next target closed shape is determined by traversing the pixels in the target binarized image in turn. The target pixel is the one that does not have a corresponding coordinate extraction effective identifier.

[0020] In some possible implementations, the next target pixel is determined based on the local edge contour of the target closed shape under the target pixel and the binarized assignment information of at least some of the surrounding pixels corresponding to the target pixel, including:

[0021] Based on the binarized assignment information of multiple adjacent pixels of the target pixel, the local edge contour of the target closed shape under the target pixel is determined;

[0022] Based on the local edge contour of the target closed shape under the target pixel and the binarized assignment information of at least some of the surrounding pixels corresponding to the target pixel, the next target pixel is determined from at least some of the surrounding pixels corresponding to the target pixel according to the preset contour search direction.

[0023] In some possible implementations, the edge contour coordinates corresponding to the closed shape of the target are extracted based on each target pixel, including:

[0024] The local edge contour coordinates corresponding to each target pixel are merged to obtain the edge contour coordinates corresponding to the target closed shape. The edge contour coordinates corresponding to the target closed shape are the key vertex information of the target closed shape.

[0025] In some possible implementations, the local edge contour coordinates corresponding to each target pixel are merged to obtain the edge contour coordinates corresponding to the target closed shape. The edge contour coordinates corresponding to the target closed shape are the key vertex information of the target closed shape, including:

[0026] Once the next target pixel is determined, the extracted edge contour coordinates of the target closed shape are merged with the local edge contour coordinates of the next target pixel to obtain the updated extracted edge contour coordinates of the target closed shape. This process continues until each target pixel located on the edge contour of the target closed shape is determined, and the corresponding edge contour coordinates of the target closed shape are obtained.

[0027] In the case where the target pixel is the first determined target pixel located on the edge contour of the target closed shape, the extracted edge contour coordinates of the target closed shape are the local edge contour coordinates of the target pixel.

[0028] In some possible implementations, this process continues until each target pixel point located on the graphic edge contour of the target closed graphic is determined, including:

[0029] Until the contour termination coordinates and contour start coordinates of the edge contour corresponding to the target closed shape coincide, it is determined that each target pixel point on the edge contour of the target closed shape has been determined.

[0030] The starting coordinates of the contour are: the starting coordinates of the local edge contour of the first determined target pixel point located on the edge contour of the target closed shape.

[0031] In some possible implementations, the image transformation method further includes, before acquiring the target binarized image:

[0032] Based on the original map, determine the edges of each graphic in the original map;

[0033] Map the edges of each graphic in the original layout to the pixel boundaries in the initial binarized image;

[0034] The binarized assignment information of pixels within the pixel boundary is set as the first assignment, and the binarized assignment information of pixels outside the pixel boundary is set as the second assignment to obtain the initial binarized image. The first assignment indicates that the pixel is located in the graphic region, and the second assignment indicates that the pixel is located in the non-graphic region.

[0035] The initial binarized image is subjected to optical proximity effect correction processing to obtain the target binarized image.

[0036] In some possible implementations, the initial binarization assignment information for each pixel in the initial binarized image is a third assignment; the binarization assignment information for pixels within the pixel boundaries is set to a first assignment, and the binarization assignment information for pixels outside the pixel boundaries is set to a second assignment, resulting in the initial binarized image, including:

[0037] The binarization assignment information of the pixels inside the pixel boundary and adjacent to the pixel boundary is changed from the third assignment to the first assignment, and the binarization assignment information of the pixels outside the pixel boundary and adjacent to the pixel boundary is changed from the third assignment to the second assignment.

[0038] Traverse the pixels in the initial binarized image whose binarization assignment information is the third assignment. If there are pixels with the first assignment among the multiple neighboring pixels of the currently traversed pixel, change the binarization assignment information of the currently traversed pixel from the third assignment to the first assignment.

[0039] If a pixel with a second assigned value exists among multiple neighboring pixels of the currently traversed pixel, the binarization assignment information of the currently traversed pixel is modified from the third assignment to the second assignment, until the traversal of the initial binarized image is completed, and the initial binarized image is obtained.

[0040] Based on the same inventive concept, in a second aspect, embodiments of this application provide an image conversion apparatus, which includes:

[0041] The first acquisition module is used to acquire the target binarized image, which includes N closed shapes, where N is a positive integer;

[0042] The first determining module is used to determine each target pixel on the edge contour of the target closed shape by sequentially traversing the pixels in the target binary image based on the binary assignment information of the pixel in the target binary image. The target closed shape is any closed shape among N closed shapes whose edge contour coordinates have not been extracted.

[0043] The first extraction module is used to extract the edge contour coordinates of the target closed shape based on each target pixel point, until the edge contour coordinates of N closed shapes are obtained.

[0044] The first conversion module is used to convert the target binarized image into the corresponding target map based on the edge contour coordinates of N closed graphics.

[0045] Thirdly, embodiments of this application provide an image conversion apparatus, which includes:

[0046] Processor and memory storing computer program instructions;

[0047] When the processor executes the computer program instructions, it implements the image conversion method provided in any of the embodiments of this application described above.

[0048] Fourthly, embodiments of this application provide a computer storage medium storing computer program instructions, which, when executed by a processor, implement the image conversion method provided in any of the embodiments of this application described above.

[0049] Fifthly, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform an image conversion method as provided in any of the embodiments of this application described above.

[0050] This application provides an image conversion method, device, computer storage medium, and program product. It acquires a target binarized image containing N closed shapes, and then, based on the binarized pixel values ​​in the target binarized image, sequentially traverses the pixels to determine each target pixel located on the edge contour of the target closed shapes. Based on each target pixel, it extracts the corresponding edge contour coordinates of the target closed shapes until all pixels in the target binarized image have been traversed, obtaining the edge contour coordinates of the N closed shapes. Finally, based on the edge contour coordinates of the N closed shapes, the target binarized image can be quickly and accurately converted into a corresponding target layout.

[0051] As described above, the image conversion method, device, computer storage medium, and program product of this application, in the process of image conversion coordinate extraction, combine the binary assignment information of pixels in the target binary image, and extract the edge contour coordinates of the corresponding closed shape by traversing through each target pixel on the edge contour of the closed shape in the target binary image. This allows for rapid and accurate image conversion based on the edge contour information, improving the stability of the image conversion. This application embodiment extracts only the edge contour coordinates of the closed shape in the target binary image during the image conversion process, making the image conversion process more stable and faster, thereby significantly improving the overall image conversion efficiency and enhancing algorithm performance and accuracy. Attached Figure Description

[0052] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a schematic flowchart of an image conversion method provided in an embodiment of this application;

[0054] Figure 2This is a schematic diagram of a scenario flow of an image conversion method provided in an embodiment of this application;

[0055] Figure 3 This is a schematic diagram of the structure of an image conversion device provided in an embodiment of this application;

[0056] Figure 4 This is a schematic diagram of the structure of an image conversion device provided in an embodiment of this application. Detailed Implementation

[0057] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0058] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0059] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0060] As described in the background section, currently, when converting an image into a GDS / OASIS layout, the usual method is to locate the pixels on the image, generate a square for each pixel according to its pixel size, place it on the GDS / OASIS layout according to its positional relationship, and finally perform a merge operation on the GDS / OASIS to eliminate the edges inside the graphic so that only the outer contour is preserved.

[0061] However, the aforementioned methods for converting images to GDS / OASIS layouts often use scripts to integrate existing functions. These functions are typically not designed for graphics optimization, their operations are coarse, and they are difficult to repeat indefinitely. After converting from GDS / OASIS to an image and back to a GDS / OASIS layout, there are often significant errors at the edges, making them unsuitable for mature graphics optimization workflows. Furthermore, the iterative merging process, which involves traversing pixel squares and checking surrounding edges, results in a large amount of useless redundant edge calculations within pixels that are not actually edges. This prevents efficient and stable graphics conversion, leading to instability and slow speed in iterative graphics optimization.

[0062] In view of the above, in order to solve the problems of the prior art, embodiments of this application provide an image conversion method, apparatus, computer storage medium, and program product. It should be noted that the embodiments provided in this application are not intended to limit the scope of this application.

[0063] The image conversion method provided in the embodiments of this application will be described below. Figure 1 A schematic flowchart of an image conversion method provided in an embodiment of this application is shown. Figure 1 As shown, the image conversion method includes the following steps:

[0064] S110, Obtain the target binarized image, which includes N closed shapes, where N is a positive integer;

[0065] S120, based on the binarization assignment information of the pixels in the target binarized image, by sequentially traversing the pixels in the target binarized image, each target pixel located on the edge contour of the target closed shape is determined. The target closed shape is any closed shape among N closed shapes whose edge contour coordinates have not been extracted.

[0066] S130: Based on each target pixel, extract the edge contour coordinates corresponding to the target closed shape, until the edge contour coordinates of N closed shapes are obtained.

[0067] S140 converts the target binarized image into the corresponding target map based on the edge contour coordinates of N closed shapes.

[0068] This application provides an image conversion method that acquires a target binarized image containing N closed shapes. Then, based on the binarized pixel values ​​in the target binarized image, it sequentially traverses the pixels to determine each target pixel located on the edge contour of the target closed shapes. Based on each target pixel, it extracts the corresponding edge contour coordinates of the target closed shapes until all pixels in the target binarized image have been traversed, resulting in the edge contour coordinates of the N closed shapes. Finally, based on the edge contour coordinates of the N closed shapes, the target binarized image can be quickly and accurately converted into a corresponding target map.

[0069] As described above, the image conversion method of this application, during the coordinate extraction process, combines the binarized assignment information of pixels in the target binarized image and iterates through each target pixel on the edge contour of a closed shape within the target binarized image to extract the corresponding edge contour coordinates. This allows for rapid and accurate image conversion based on edge contour information, improving the stability of the image conversion. This application embodiment extracts only the edge contour coordinates of closed shapes in the target binarized image during the image conversion process, making the image conversion process more stable and faster, thereby significantly improving the overall image conversion efficiency and enhancing algorithm performance and accuracy.

[0070] The specific implementation methods of steps 110 to 140 above are described in detail below.

[0071] In S110, specifically, a target binarized image is acquired, which includes N closed shapes. In the semiconductor layout design process, the aforementioned target binarized image can typically be a graphical representation of the layout design. The closed shapes in the target binarized image can correspond to graphical representations such as transistors, interconnects, and contact holes, without strict limitations.

[0072] Optionally, in this embodiment, the target binarized image includes multiple pixels, and these pixels are binarized according to the distribution of multiple closed shapes in the image. For example, the binarization assignment information corresponding to pixels located in the shape area is set to 1, and the binarization assignment information corresponding to pixels located in the non-shape area is set to 0.

[0073] In S120, specifically, based on the binarized assignment information of pixels in the target binarized image, the target pixels located on the edge contour of the target closed shape are determined by sequentially traversing the pixels in the target binarized image. The target closed shape is any closed shape among N closed shapes whose edge contour coordinates have not been extracted. It should be noted that in the target binarized image, the smallest closed shape is a single pixel.

[0074] When performing the above traversal, row priority, column priority, spiral traversal or random traversal can be used to traverse the pixels in the target binarized image in turn.

[0075] The binarized assignment information of the aforementioned pixels can be, for example, a first assignment or a second assignment. The first assignment, for example, is 1, indicating that the pixel is located in a graphic area; the second assignment, for example, is 0, indicating that the pixel is located in a non-graphic area.

[0076] Optionally, when determining each target pixel on the edge contour of the closed shape during traversal based on the binarization assignment information of pixels in the target binarized image, specifically, the currently traversed pixel whose own binarization assignment information is the first assignment and which also has adjacent pixels with both the first and second assignments can be determined as the target pixel. In actual image processing scenarios, the adjacent pixels of the target pixel typically include at least one pixel that is directly in contact with it in the four directions of top, bottom, left, and right.

[0077] In this embodiment, by traversing the pixels in the target binarized image to determine each target pixel on the graphic edge contour of different closed images, image data can be effectively manipulated and analyzed, thereby providing the necessary data support for the subsequent conversion of the target binarized image into a layout.

[0078] Optionally, in a feasible embodiment of this application, in order to more quickly locate and confirm each target pixel on the edge contour of the graphic, the above-mentioned S120, based on the binarization assignment information of the pixels in the target binarized image, determines each target pixel located on the edge contour of the target closed graphic by sequentially traversing the pixels in the target binarized image, may specifically include:

[0079] Based on the binarization assignment information of pixels in the target binarized image, the first target pixel located on the edge contour of the target closed shape is determined by traversing the pixels in the target binarized image in turn.

[0080] Repeatedly execute the steps of determining the next target pixel based on the local edge contour of the target closed shape under the target pixel and the binarized assignment information of at least some surrounding pixels corresponding to the target pixel, and updating the target pixel to the next target pixel, until each target pixel located on the graphic edge contour of the target closed shape is determined.

[0081] In this embodiment, after determining the first target pixel on the edge contour of the closed target graphic that has not been subjected to coordinate extraction based on the binarization assignment information of (at least some) pixels in the target binarized image, the next target pixel is determined by directly searching from the surrounding pixels of the target pixel by determining the local edge contour corresponding to the target pixel.

[0082] By analogy, the current target pixel is updated to the determined next target pixel, and the above steps of determining the next target pixel based on the local edge contour of the target closed shape under the target pixel and the binarized assignment information of at least some of the surrounding pixels corresponding to the target pixel are repeated for the new target pixel until each target pixel located on the graphic edge contour of the target closed shape is determined.

[0083] In this way, by identifying the first target pixel on the edge contour of the target closed shape, and then quickly finding the next target pixel from its surrounding pixels based on the local edge contour corresponding to the current target pixel, it is possible to quickly and accurately find and confirm each target pixel in the entire target closed shape, thereby significantly improving the extraction efficiency of the edge contour of the closed shape in the target binarized image.

[0084] It should be added that, in actual image processing scenarios, the surrounding pixels of the target pixel usually include at least one pixel that is adjacent to it in eight directions: top, bottom, left, right, upper left, lower left, upper right, and lower right (considering the diagonal direction).

[0085] Furthermore, the process of determining each target pixel located on the edge contour of the target closed shape can, for example, mean that all target pixels on the edge contour of the target closed shape have been found if the determined next target pixel coincides with the first target pixel located on the edge contour of the target closed shape. In this case, the traversal of pixels outside the image edge contour of the target closed shape can continue to switch to extracting the edge contour coordinates of the next target closed shape; this is not strictly limited.

[0086] Optionally, in a feasible embodiment of this application, in order to reasonably determine the first target pixel located on the graphic edge contour of the target closed graphic, the binarization assignment information of the pixel in the target binarized image may include the pixel being assigned a first value or a second value, where the first value indicates that the pixel is located in the graphic region, and the second value indicates that the pixel is located in the non-graphic region; the determination of the first target pixel located on the graphic edge contour of the target closed graphic by sequentially traversing the pixels in the target binarized image based on the binarization assignment information of the pixel in the target binarized image may include:

[0087] The pixels in the target binarized image are traversed sequentially, and the binarization assignment information of the currently traversed pixel and its corresponding multiple neighboring pixels are detected.

[0088] If the currently traversed pixel has the first assigned value, and multiple adjacent pixels simultaneously contain both the first assigned value and the second assigned value, then the currently traversed pixel is determined as the first target pixel located on the edge contour of the target closed shape.

[0089] In a specific implementation, the target pixel can be determined by identifying the currently traversed pixel whose own binarized assignment information is the first assignment and which simultaneously contains adjacent pixels with the first assignment and adjacent pixels with the second assignment. The adjacent pixels of the target pixel typically include at least one pixel that is directly in contact with it in the four directions of top, bottom, left, and right.

[0090] For example, taking a first assignment value of 1 and a second assignment value of 0 as an example, the binarized assignment information of the target pixel is 1. The currently traversed pixel has four adjacent pixels in the four directions of up, down, left, and right. The binarized assignment information of the four adjacent pixels in the four directions of up, down, left, and right are 0, 0, 0, and 1, respectively. In this case, it is indicated that the boundary between the currently traversed pixel and its right-adjacent pixel is the edge contour of the graphic, and the currently traversed pixel is determined as the aforementioned target pixel.

[0091] It should be noted that the number of adjacent pixels varies depending on the position of the currently traversed pixel in the target binarized image. For example, a pixel located at the center of the target binarized image has four adjacent pixels in the top, bottom, left, and right directions; while pixels located at the edges of the target binarized image often have only two or three adjacent pixels.

[0092] Optionally, in a feasible embodiment of this application, considering that during the traversal process, it is necessary to fully ensure that the target closed shape is any closed shape among the N closed shapes whose edge contour coordinates have not been extracted, so as to effectively improve the contour coordinate extraction efficiency and avoid redundant calculation and analysis of pixels, the image conversion method may further include the following before updating the target pixel to the next target pixel:

[0093] Add a marker indicating that the coordinate extraction of the target pixel has been successful;

[0094] After identifying each target pixel on the edge contour of the target closed shape, the image conversion method may further include:

[0095] Based on the binarization assignment information of pixels in the target binarized image, the first target pixel located on the edge contour of the next target closed shape is determined by traversing the pixels in the target binarized image in turn. The target pixel is the one that does not have a corresponding coordinate extraction effective identifier.

[0096] The aforementioned coordinate extraction validity identifier can be identified, for example, by a fixed-format field, a numerical code, or a custom label. The coordinate extraction validity identifiers for different target pixels can be the same or have a one-to-one correspondence; this application does not impose strict restrictions on this.

[0097] In practice, after determining the target pixel, the target pixel is marked by adding the coordinates corresponding to the target pixel to extract the effective identifier, so as to indicate that the target pixel has been effectively processed.

[0098] In this way, when traversing the pixels in the target binary image, the system checks whether a corresponding coordinate extraction valid identifier exists for the currently traversed pixel. If no valid identifier is detected, the pixel can be analyzed and processed; if a valid identifier is detected, the pixel is skipped without processing. This method effectively avoids repetitive processing of already analyzed pixels during the traversal phase, significantly improving pixel search efficiency.

[0099] It should also be added that, in order to accelerate the traversal process of pixels in the target binarized image, after determining each target pixel on the edge contour of the target closed shape, the pixels inside the target closed shape can be bypassed in the subsequent traversal process without traversal, thereby further improving the extraction speed of the edge contour of the closed shape in the target binarized image.

[0100] Optionally, in a feasible embodiment of this application, more specifically, in order to determine the next target pixel more quickly and effectively based on the target pixel, the above-mentioned determination of the next target pixel based on the local edge contour of the target closed shape under the target pixel and the binarized assignment information of at least some of the surrounding pixels corresponding to the target pixel may include:

[0101] Based on the binarized assignment information of multiple adjacent pixels of the target pixel, the local edge contour of the target closed shape under the target pixel is determined;

[0102] Based on the local edge contour of the target closed shape under the target pixel and the binarized assignment information of at least some of the surrounding pixels corresponding to the target pixel, the next target pixel is determined from multiple surrounding pixels corresponding to the target pixel according to the preset contour search direction.

[0103] In this embodiment, the local edge contour corresponding to the target pixel is first determined based on the binarized assignment information of multiple adjacent pixels. For example, if the binarized assignment information of the target pixel is 1, and the currently traversed pixel has four adjacent pixels in the four directions of up, down, left, and right, with corresponding binarized assignment information of 0, 0, 0, and 1 respectively, then the boundary between the currently traversed pixel and its right-side adjacent pixel is considered the local edge contour of the target closed shape below the target pixel.

[0104] After determining the local edge contour, the next target pixel is determined from at least a portion of the surrounding pixels of the target pixel according to a preset contour search direction (e.g., counterclockwise or clockwise). The preset contour search direction determines the search priority order for the surrounding pixels of the target pixel under the local edge contour, making the search for the next target pixel more orderly and stable. At the same time, the preset contour search direction also ensures the uniqueness of the determined next target pixel through the above search priority order, avoiding search chaos.

[0105] When performing the search and analysis of surrounding pixels, in conjunction with the aforementioned embodiments, the pixel whose own binary assignment information is first determined from the surrounding pixels and which is also the neighboring pixel with the first assignment and the neighboring pixel with the second assignment can be determined as the next target pixel.

[0106] In order to more quickly determine the next target pixel, considering the continuity of the graphic edge contour, the surrounding pixels in the selection range can be further filtered. Specifically, at least some of the surrounding pixels corresponding to the target pixel can specifically refer to the surrounding pixels that intersect with the aforementioned local edge contour.

[0107] In S130, in specific implementation, the edge contour coordinates corresponding to the target closed shape are extracted based on each target pixel point, until the edge contour coordinates of N closed shapes are obtained.

[0108] In this embodiment, after determining each target pixel on the target closed shape, the local edge contour coordinates corresponding to the target pixels are extracted and summarized to obtain the edge contour coordinates of the completed target closed shape. Alternatively, the local edge contour coordinates of the target pixels determined sequentially can be extracted one by one during the aforementioned traversal process to finally obtain the edge contour coordinates of the complete target closed shape.

[0109] By analogy, after the edge contour coordinates of the target closed shape are extracted, the target pixels on the edge contour of the next target closed shape are found by continuing to traverse, thus completing the extraction of the edge contour coordinates of the next target closed shape, until the pixels that need to be traversed in the target binarized image are traversed, and the edge contour coordinates of N closed shapes are obtained.

[0110] Optionally, in a feasible embodiment of this application, in order to facilitate a more efficient conversion of the above-mentioned target binarized image, the extraction of the edge contour coordinates corresponding to the target closed shape based on each target pixel may include:

[0111] The local edge contour coordinates corresponding to each target pixel are merged to obtain the edge contour coordinates corresponding to the target closed shape. The edge contour coordinates corresponding to the target closed shape are the key vertex information of the target closed shape.

[0112] In practice, the local edge contour coordinates corresponding to each target pixel can be merged, retaining only the key vertex information of the closed target shape. Specifically, this key vertex information can be the coordinates of the endpoints of the corners of the closed shape. Using the merged edge contour coordinates can accurately represent the edges of the shape, helping to enhance the detail of the image and thus achieving a smoother, more natural transition during the conversion process.

[0113] Furthermore, when converting the target binarized image into the target layout using the key vertex information of each closed shape, the amount of data to be processed is significantly reduced, thus effectively improving the algorithm's execution efficiency. This merging strategy is particularly effective in improving the overall conversion efficiency when processing large-scale image data.

[0114] Optionally, in a feasible embodiment of this application, in conjunction with the foregoing embodiments, the above-described merging process can be integrated into the stepwise search process of the target pixels to more efficiently extract the edge contour coordinates of the target closed shape. Specifically, merging the local edge contour coordinates corresponding to each target pixel to obtain the edge contour coordinates corresponding to the target closed shape, where the edge contour coordinates of the target closed shape are the key vertex information of the target closed shape, may include:

[0115] Once the next target pixel is determined, the extracted edge contour coordinates of the target closed shape are merged with the local edge contour coordinates of the next target pixel to obtain the updated extracted edge contour coordinates of the target closed shape. This process continues until each target pixel located on the edge contour of the target closed shape is determined, and the corresponding edge contour coordinates of the target closed shape are obtained.

[0116] In the case where the target pixel is the first determined target pixel located on the edge contour of the target closed shape, the extracted edge contour coordinates of the target closed shape are the local edge contour coordinates of the target pixel.

[0117] In this embodiment, the local edge contour coordinates of the determined next target pixel are continuously merged with the extracted edge contour coordinates of the target closed shape to obtain updated extracted edge contour coordinates.

[0118] Furthermore, during the merging process, the endpoints of the corners on the existing edge contours of the target closed shape, the starting coordinates of the existing edge contours, and the ending coordinates of the contours can be mainly retained, thereby achieving effective merging and simplification of the edge contour coordinates.

[0119] Optionally, in a feasible embodiment of this application, in order to more efficiently and accurately determine that all target pixels on the graphic edge contour of the target closed shape have been extracted, the above-mentioned determination of each target pixel on the graphic edge contour of the target closed shape may include:

[0120] Until the contour termination coordinates and contour start coordinates of the edge contour corresponding to the target closed shape coincide, it is determined that each target pixel point on the edge contour of the target closed shape has been determined.

[0121] The starting coordinates of the contour are: the starting coordinates of the local edge contour of the first determined target pixel point located on the edge contour of the target closed shape.

[0122] Specifically, the determination is made by comparing whether the contour termination coordinates and contour start coordinates in the extracted edge contour coordinates of the target closed shape coincide. If the contour termination coordinates and contour start coordinates coincide, it indicates that all target pixels on the shape's edge contour have been found; otherwise, the search for the next target pixel continues.

[0123] In this embodiment, it is not necessary to determine whether all target pixels on the edge contour of the target closed shape have been found by comparing the next target pixel with the first target pixel. By using the start and end coordinates of the extracted edge contour of the target closed shape, the determination can be made during the current target pixel analysis process, thereby effectively saving implementation steps and improving algorithm efficiency.

[0124] In S140, specifically, based on the edge contour coordinates of N closed shapes, the target binarized image is converted into the corresponding target layout. The target layout can be in GDS or OASIS layout file format, depending on the actual image conversion requirements; no strict limitation is imposed here.

[0125] Optionally, in a feasible embodiment of this application, considering the actual layout design scenario, the image conversion method may further include the following before obtaining the target binarized image:

[0126] Based on the original map, determine the edges of each graphic in the original map;

[0127] Map the edges of each graphic in the original layout to the pixel boundaries in the initial binarized image;

[0128] The binarized assignment information of pixels within the pixel boundary is set as the first assignment, and the binarized assignment information of pixels outside the pixel boundary is set as the second assignment to obtain the initial binarized image. The first assignment indicates that the pixel is located in the graphic region, and the second assignment indicates that the pixel is located in the non-graphic region.

[0129] The initial binarized image is subjected to optical proximity effect correction processing to obtain the target binarized image.

[0130] In practice, the original layout can be in GDS or OASIS format. The original layout details the chip or circuit placement design and can be customized based on the actual layout requirements and conditions; no strict limitations are imposed here. The original and target layouts can share the same file format to ensure data stability during image and layout conversions.

[0131] In this embodiment, edge detection algorithms, deep learning methods, or scanning electron microscopy (SEM) measurements can be used to identify and extract the graphic edges in the original layout. These graphic edges can specifically be represented by the vertex coordinates of various graphics in the layout, and are not strictly limited here.

[0132] After determining the graphic edges of each graphic in the original layout, the graphic edges of each graphic in the original layout are mapped to the pixel boundaries in the initial binarized image according to certain size mapping rules, etc. The properties of the pixel boundaries can be similar to the graphic edge contours of the aforementioned closed graphics.

[0133] Next, given that the pixel boundaries have already been mapped in the initial binarized image, pixels within the pixel boundaries are all assigned a first value, such as 1, to indicate that the pixels are located in the graphic region. Pixels outside the pixel boundaries are all assigned a second value, such as 0, to indicate that the pixels are located in the non-graphic region. In this way, the process of converting the original layout into the initial binarized image is accurately and completely achieved.

[0134] Furthermore, considering that graph-based optimization algorithms often have higher degrees of freedom and accuracy, after obtaining the initial binarized image, the target binarized image can be obtained by performing OPC correction processing on the initial binarized image, thereby enabling effective optimization of the specific layout design content.

[0135] Optionally, in a feasible embodiment of this application, in order to more efficiently perform pixel assignment processing on pixels inside and outside the pixel boundary, the initial binarization assignment information of each pixel in the initial binarized image is a third assignment; setting the binarization assignment information of pixels inside the pixel boundary to a first assignment and setting the binarization assignment information of pixels outside the pixel boundary to a second assignment to obtain the initial binarized image may include:

[0136] The binarization assignment information of the pixels inside the pixel boundary and adjacent to the pixel boundary is changed from the third assignment to the first assignment, and the binarization assignment information of the pixels outside the pixel boundary and adjacent to the pixel boundary is changed from the third assignment to the second assignment.

[0137] Traverse the pixels in the initial binarized image whose binarization assignment information is the third assignment. If there are pixels with the first assignment among the multiple neighboring pixels of the currently traversed pixel, change the binarization assignment information of the currently traversed pixel from the third assignment to the first assignment.

[0138] If a pixel with a second assigned value exists among multiple neighboring pixels of the currently traversed pixel, the binarization assignment information of the currently traversed pixel is modified from the third assignment to the second assignment, until the traversal of the initial binarized image is completed, and the initial binarized image is obtained.

[0139] In this embodiment, the initial binarization assignment information for each pixel in the initial binarized image is defaulted to the third assignment. When converting the original map into the initial binarized image, pixels adjacent to the inner and outer sides of the pixel boundary are marked. Inner pixels adjacent to the pixel boundary are modified to the first assignment, and outer pixels adjacent to the pixel boundary are modified to the second assignment. When assigning values ​​to the inner and outer sides of the pixel boundary, values ​​can be assigned sequentially according to a pre-defined contour search direction to ensure the orderly processing of pixel assignments.

[0140] Thus, after assigning values ​​around the pixel boundary, the remaining pixels can be filled by traversing the entire initial binarized image and considering the values ​​of the adjacent pixels of the third-valued pixel, thereby converting the original map into the initial binarized image.

[0141] The following example illustrates this: In the initial binarized image, pixels are initially marked with a value of 2. After determining the pixel boundaries, the pixels immediately adjacent to the inner edge of the boundary are marked with a value of 1, and the pixels immediately adjacent to the outer edge of the boundary are marked with a value of 0.

[0142] In this case, the process involves iterating through all pixels in the initial binarized image that are still marked as 2, and checking the values ​​of adjacent pixels. Based on the values ​​of neighboring pixels in the up, down, left, and right directions, it can be determined whether the current pixel should be assigned a value of 0 or 1. This completes the binarization filling of pixels in the initial binarized image.

[0143] In this embodiment, firstly, the adjacent pixels on both sides of the pixel boundary are assigned a first value or a second value. Then, the entire image is traversed. The remaining pixels are assigned and modified according to the situation of the neighboring pixels. This allows for a faster and more efficient conversion from the layout to a binarized image.

[0144] To facilitate understanding of the image conversion method provided in the above embodiments, the following describes the method using a specific scenario embodiment. Figure 2 This is a schematic flowchart of a scenario embodiment of the image conversion method provided in this application.

[0145] The application scenario of this example is as follows: In a real-world layout design optimization scenario, the original layout to be corrected is first obtained, and then binarized to obtain the corresponding initial binarized image. Next, an image-based optimization algorithm is used to perform OPC correction processing on the initial binarized image to obtain the target binarized image. Then, this target binarized image needs to be quickly, accurately, and completely converted into the target layout for subsequent layout operations.

[0146] This scenario embodiment will describe in detail the conversion process from a target binarized image to a target map, specifically including the following steps:

[0147] Step 1: Iterate through the pixels in the target binarized image in sequence until a target pixel is found on the edge contour of the closed shape. This target pixel is the first assigned pixel and has adjacent pixels of the first assigned pixel and adjacent pixels of the second assigned pixel.

[0148] Step 2: Extract the local edge contour of the target pixel and determine the coordinates of the local edge contour corresponding to the target pixel based on the local edge contour.

[0149] Step 3: Combining Figure 2 As shown, along the local edge contour and the preset contour search direction, the next target pixel is found from at least some of the surrounding pixels corresponding to the target pixel. The local edge contour coordinates of the next target pixel are extracted and merged with the extracted edge contour coordinates of the current closed shape, and the extracted pixels are marked.

[0150] Step 4: Repeat step 3 until the target pixels on the edge contour of the current closed shape are determined, and extract the edge contour coordinates of the current closed shape.

[0151] Step 5: Continue to traverse the pixels in the target binarized image, skipping pixels outside the shape's edge contour, inside the shape's edge contour, and pixels that have already been extracted and have been marked, until the next target pixel on the shape's edge contour of a closed shape that has not been extracted is found. Repeat steps 2 to 4.

[0152] Step Six: Repeat Step Five until the edge contour coordinates of all closed shapes in the target binarized image have been extracted, obtaining the edge contour coordinates of each closed shape. It should be noted that, through the coordinate merging operation in Step Three, the edge contour coordinates of the closed shapes are actually the key vertex information of the simplified closed shapes.

[0153] Step 7: Based on the edge contour coordinates of each closed shape, convert the target binarized image into a target map. The target map can be a GDS / OASIS map.

[0154] This embodiment extracts and transforms the edge coordinates of a binary image directly by extracting along the image's edges, achieving accurate, complete, and high-speed conversion between binary images and layout files. Designed for a graph-based optimization process, this solution can accurately and completely convert between various scenarios, maintaining stability through repeated transformations, thus laying the foundation for precise iterative optimization based on graphs.

[0155] Meanwhile, in the process of extracting coordinates from a binarized image to a layout, this embodiment performs the extraction calculation along the edge of the graphic, eliminating the unnecessary calculation and analysis of the center pixel of the graphic in the traditional merge method. This makes the image conversion process more stable and faster, thereby significantly improving the overall image conversion efficiency and enhancing the algorithm's performance and accuracy.

[0156] Based on the image conversion method provided in the above embodiments, and with the same inventive concept, this application also provides an image conversion apparatus corresponding to the above image conversion method. The following describes... Figure 3 A detailed introduction to the image conversion device is provided.

[0157] Figure 3 A schematic diagram of the structure of an image conversion apparatus provided in an embodiment of this application is shown. Figure 3 The image conversion device 300 shown includes:

[0158] The first acquisition module 310 is used to acquire a target binarized image, which includes N closed shapes, where N is a positive integer;

[0159] The first determining module 320 is used to determine each target pixel on the edge contour of the target closed shape by sequentially traversing the pixels in the target binary image based on the binary assignment information of the pixel in the target binary image. The target closed shape is any closed shape among N closed shapes whose edge contour coordinates have not been extracted.

[0160] The first extraction module 330 is used to extract the edge contour coordinates of the target closed shape based on each target pixel point until the pixel points in the target binary image are traversed to obtain the edge contour coordinates of N closed shapes.

[0161] The first conversion module 340 is used to convert the target binarized image into the corresponding target map based on the edge contour coordinates of N closed graphics.

[0162] This application provides an image conversion device that, by setting corresponding functional modules, acquires a target binarized image containing N closed shapes. Then, based on the binarized assignment information of pixels in the target binarized image, it sequentially traverses the pixels in the target binarized image to determine each target pixel located on the edge contour of the target closed shape. Based on each target pixel, it extracts the edge contour coordinates corresponding to the target closed shape until all pixels in the target binarized image have been traversed, obtaining the edge contour coordinates of the N closed shapes. Finally, based on the edge contour coordinates of the N closed shapes, the target binarized image can be quickly and accurately converted into a corresponding target map.

[0163] As described above, the image conversion apparatus of this application, during the coordinate extraction process of image conversion, combines the binarized assignment information of pixels in the target binarized image and iterates through each target pixel on the edge contour of a closed shape within the target binarized image to extract the corresponding edge contour coordinates of the closed shape. This allows for rapid and accurate image conversion based on the edge contour information, improving the stability of the image conversion. This application embodiment extracts only the edge contour coordinates of closed shapes in the target binarized image during the image conversion process, making the image conversion process more stable and faster, thereby significantly improving the overall image conversion efficiency and enhancing algorithm performance and accuracy.

[0164] Optionally, in one feasible embodiment of this application, the first determining module 320 described above may include:

[0165] The first determination submodule can be used to determine the first target pixel on the edge contour of the target closed shape by sequentially traversing the pixels in the target binary image based on the binary assignment information of the pixels in the target binary image.

[0166] The repeat execution submodule can be used to repeatedly execute the steps of determining the next target pixel based on the local edge contour of the target closed shape under the target pixel and the binarized assignment information of at least some of the surrounding pixels corresponding to the target pixel, and updating the target pixel to the next target pixel, until each target pixel located on the graphic edge contour of the target closed shape is determined.

[0167] Optionally, in a feasible embodiment of this application, the binarization assignment information of pixels in the target binarized image may include a pixel being assigned a first value or a pixel being assigned a second value, where the first value indicates that the pixel is located in a graphic region, and the second value indicates that the pixel is located in a non-graphic region; the first determination submodule may include:

[0168] The first detection unit can be used to sequentially traverse the pixels in the target binarized image and detect the binarization assignment information of the currently traversed pixel and the binarization assignment information of its multiple adjacent pixels.

[0169] The first determining unit can be used to determine the currently traversed pixel as the first target pixel located on the graphic edge contour of the target closed graphic when the currently traversed pixel is assigned a first value and multiple adjacent pixels simultaneously contain pixels with the first value and pixels with the second value.

[0170] Optionally, in one feasible embodiment of this application, before updating the target pixel to the next target pixel, the image conversion device may further include:

[0171] The identifier addition module can be used to add an effective identifier for the coordinates of the target pixel.

[0172] After determining each target pixel point located on the edge contour of the target closed shape, the image conversion device may further include:

[0173] The second determining module can be used to continue to determine the first target pixel on the edge contour of the next target closed shape by traversing the pixels in the target binary image in turn, based on the binary assignment information of the pixels in the target binary image. The target pixel is the target pixel that does not have a corresponding coordinate extraction effective identifier.

[0174] Optionally, in a feasible embodiment of this application, the above-mentioned determination of the next target pixel based on the local edge contour of the target closed shape under the target pixel and the binarized assignment information of at least some of the surrounding pixels corresponding to the target pixel may include:

[0175] Based on the binarized assignment information of multiple adjacent pixels of the target pixel, the local edge contour of the target closed shape under the target pixel is determined;

[0176] Based on the local edge contour of the target closed shape under the target pixel and the binarized assignment information of at least some of the surrounding pixels corresponding to the target pixel, the next target pixel is determined from at least some of the surrounding pixels corresponding to the target pixel according to the preset contour search direction.

[0177] Optionally, in one feasible embodiment of this application, the first extraction module 330 described above may specifically include:

[0178] The local edge contour coordinates corresponding to each target pixel are merged to obtain the edge contour coordinates corresponding to the target closed shape. The edge contour coordinates corresponding to the target closed shape are the key vertex information of the target closed shape.

[0179] Optionally, in a feasible embodiment of this application, the local edge contour coordinates corresponding to each target pixel are merged to obtain the edge contour coordinates corresponding to the target closed shape. The edge contour coordinates corresponding to the target closed shape are the key vertex information of the target closed shape, which may include:

[0180] Once the next target pixel is determined, the extracted edge contour coordinates of the target closed shape are merged with the local edge contour coordinates of the next target pixel to obtain the updated extracted edge contour coordinates of the target closed shape. This process continues until each target pixel located on the edge contour of the target closed shape is determined, and the corresponding edge contour coordinates of the target closed shape are obtained.

[0181] In the case where the target pixel is the first determined target pixel located on the edge contour of the target closed shape, the extracted edge contour coordinates of the target closed shape are the local edge contour coordinates of the target pixel.

[0182] Optionally, in a feasible embodiment of this application, the above-mentioned determination of each target pixel point located on the graphic edge contour of the target closed graphic may include:

[0183] Until the contour termination coordinates and contour start coordinates of the edge contour corresponding to the target closed shape coincide, it is determined that each target pixel point on the edge contour of the target closed shape has been determined.

[0184] The starting coordinates of the contour are: the starting coordinates of the local edge contour of the first determined target pixel point located on the edge contour of the target closed shape.

[0185] Optionally, in one feasible embodiment of this application, before acquiring the target binarized image, the image conversion device may further include:

[0186] The third determining module can be used to determine the graphic edges of each graphic in the original map based on the original map.

[0187] The first mapping module can be used to map the graphic edges of each graphic in the original layout to the pixel boundaries in the initial binarized image;

[0188] The first assignment module can be used to set the binarized assignment information of pixels within the pixel boundary as the first assignment, and set the binarized assignment information of pixels outside the pixel boundary as the second assignment to obtain an initial binarized image. The first assignment indicates that the pixel is located in the graphic area, and the second assignment indicates that the pixel is located in the non-graphic area.

[0189] The first correction module can be used to perform optical proximity effect correction processing on the initial binarized image to obtain the target binarized image.

[0190] Optionally, in a feasible embodiment of this application, the initial binarization assignment information of each pixel in the initial binarized image is the third assignment; the aforementioned first assignment module may include:

[0191] The first assignment submodule can be used to modify the binarization assignment information of pixels inside the pixel boundary and adjacent to the pixel boundary from the third assignment to the first assignment, and to modify the binarization assignment information of pixels outside the pixel boundary and adjacent to the pixel boundary from the third assignment to the second assignment.

[0192] The second assignment submodule can be used to traverse the pixels in the initial binarized image whose binarization assignment information is the third assignment. If there are pixels with the first assignment among the multiple adjacent pixels of the currently traversed pixel, the binarization assignment information of the currently traversed pixel is modified from the third assignment to the first assignment.

[0193] The third assignment submodule can be used to modify the binarization assignment information of the currently traversed pixel from the third assignment to the second assignment when there are pixels with the second assignment among multiple adjacent pixels of the currently traversed pixel, until the traversal of the initial binarized image is completed and the initial binarized image is obtained.

[0194] Based on the image conversion method provided in the above embodiments, and with the same inventive concept, this application also provides an image conversion device corresponding to the above image conversion method. The following describes... Figure 4 A detailed introduction to image conversion equipment is provided.

[0195] Please see below. Figure 4 , Figure 4 This is a schematic diagram of the structure of an image conversion device provided in an embodiment of this application.

[0196] The image conversion device may include a processor 401 and a memory 402 storing computer program instructions.

[0197] Specifically, the processor 401 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0198] Memory 402 may include mass storage for data or instructions. For example, and not limitingly, memory 402 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 402 may include removable or non-removable (or fixed) media. Where appropriate, memory 402 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 402 is non-volatile solid-state memory.

[0199] Memory may include read-only memory (ROM), random access memory (RAM), disk storage media devices, optical storage media devices, flash memory devices, and electrical, optical, or other physical / tangible memory storage devices. Therefore, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the methods according to one aspect of this disclosure.

[0200] The processor 401 implements any of the image conversion methods described in the above embodiments by reading and executing computer program instructions stored in the memory 402.

[0201] In one example, the data image conversion device may further include a communication interface 403 and a bus 410. Wherein, as... Figure 4 As shown, the processor 401, memory 402, and communication interface 403 are connected through bus 410 and complete communication with each other.

[0202] The communication interface 403 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0203] Bus 410 includes hardware, software, or both, that couples components of an image conversion device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 410 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0204] The image conversion device executes the image conversion method in the embodiments of this application, thereby realizing the image conversion method described in the embodiments of this application.

[0205] Furthermore, in conjunction with the image conversion methods described in the above embodiments, this application embodiment can provide a computer storage medium for implementation. This computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the image conversion methods described in the above embodiments.

[0206] Based on the image conversion methods in the above embodiments, this application provides a computer program product. When the instructions in the computer program product are executed by the processor of an electronic device, the electronic device performs the image conversion method provided in any one of the above embodiments of this application.

[0207] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0208] The functional blocks shown in the above-described structural diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0209] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0210] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0211] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. An image conversion method, characterized in that, The method includes: Obtain a target binarized image, wherein the target binarized image includes N closed shapes, where N is a positive integer; Based on the binarization assignment information of the pixels in the target binarized image, each target pixel located on the edge contour of the target closed shape is determined by sequentially traversing the pixels in the target binarized image. The target closed shape is any closed shape among the N closed shapes whose edge contour coordinates have not been extracted. Based on each target pixel, the edge contour coordinates corresponding to the target closed shape are extracted until the edge contour coordinates of the N closed shapes are obtained. Based on the edge contour coordinates of the N closed shapes, the target binarized image is converted into a corresponding target map; the step of determining each target pixel located on the edge contour of the target closed shape by sequentially traversing the pixels in the target binarized image according to the binarized assignment information of the pixels in the target binarized image includes: Based on the binarization assignment information of the pixels in the target binarized image, the first target pixel located on the edge contour of the target closed shape is determined by sequentially traversing the pixels in the target binarized image. Repeatedly execute the steps of determining the next target pixel based on the local edge contour of the target closed shape under the target pixel and the binarized assignment information of at least some surrounding pixels corresponding to the target pixel; and updating the target pixel to the next target pixel, until each target pixel located on the graphic edge contour of the target closed shape is determined; Before updating the target pixel to the next target pixel, the method further includes: Add a coordinate extraction activation flag corresponding to the target pixel; After determining each target pixel point located on the graphic edge contour of the target closed graphic, the method further includes: Continuing to determine the first target pixel located on the edge contour of the next target closed shape by sequentially traversing the pixels in the target binarized image based on the binarized pixel information of the target binarized image, the target pixel is the one that does not have a corresponding coordinate extraction effective identifier.

2. The method according to claim 1, characterized in that, The binarization assignment information of pixels in the target binarized image includes either a first assignment or a second assignment, where the first assignment indicates that the pixel is located in a graphic region, and the second assignment indicates that the pixel is located in a non-graphic region; the step of determining the first target pixel located on the graphic edge contour of the target closed graphic by sequentially traversing the pixels in the target binarized image based on the binarization assignment information of pixels in the target binarized image includes: The pixels in the target binarized image are traversed sequentially, and the binarization assignment information of the currently traversed pixel and the binarization assignment information of its multiple adjacent pixels are detected. If the currently traversed pixel has the first assigned value, and both the first assigned value and the second assigned value exist among the plurality of adjacent pixels, then the currently traversed pixel is determined as the first target pixel located on the graphic edge contour of the target closed graphic.

3. The method according to claim 1, characterized in that, The step of determining the next target pixel based on the local edge contour of the target closed shape under the target pixel and the binarized assignment information of at least some of the surrounding pixels corresponding to the target pixel includes: Based on the binarized assignment information of multiple adjacent pixels of the target pixel, the local edge contour of the target closed shape under the target pixel is determined; Based on the local edge contour of the target closed shape under the target pixel and the binarized assignment information of at least some surrounding pixels corresponding to the target pixel, the next target pixel is determined from at least some surrounding pixels corresponding to the target pixel according to the preset contour search direction.

4. The method according to claim 1, characterized in that, The step of extracting the edge contour coordinates corresponding to the target closed shape based on each target pixel includes: The local edge contour coordinates corresponding to each target pixel are merged to obtain the edge contour coordinates corresponding to the target closed shape. The edge contour coordinates corresponding to the target closed shape are the key vertex information of the target closed shape.

5. The method according to claim 4, characterized in that, The step of merging the local edge contour coordinates corresponding to each target pixel to obtain the edge contour coordinates corresponding to the target closed shape, wherein the edge contour coordinates corresponding to the target closed shape are the key vertex information of the target closed shape, including: Once the next target pixel is determined, the extracted edge contour coordinates of the target closed shape are merged with the local edge contour coordinates of the next target pixel to obtain the updated extracted edge contour coordinates of the target closed shape, until each target pixel located on the graphic edge contour of the target closed shape is determined, and the edge contour coordinates corresponding to the target closed shape are obtained. Wherein, if the target pixel is the first determined target pixel located on the edge contour of the target closed shape, the extracted edge contour coordinates of the target closed shape are the local edge contour coordinates of the target pixel.

6. The method according to claim 5, characterized in that, The process of determining each target pixel point located on the graphic edge contour of the target closed graphic includes: Until the contour termination coordinates and contour start coordinates of the edge contour corresponding to the target closed shape coincide, it is determined that each target pixel point located on the graphic edge contour of the target closed shape has been determined. The starting coordinates of the contour are: the starting coordinates of the local edge contour coordinates of the first determined target pixel point located on the graphic edge contour of the target closed graphic.

7. The method according to any one of claims 1-6, characterized in that, Before acquiring the target binarized image, the method further includes: Based on the original map, determine the graphic edges of each graphic in the original map; The graphic edges of each graphic in the original layout are mapped to pixel boundaries in the initial binarized image; The binarized assignment information of pixels within the pixel boundary is set as the first assignment, and the binarized assignment information of pixels outside the pixel boundary is set as the second assignment to obtain the initial binarized image. The first assignment indicates that the pixel is located in the graphic area, and the second assignment indicates that the pixel is located in the non-graphic area. The initial binarized image is subjected to optical proximity correction processing to obtain the target binarized image.

8. The method according to claim 7, characterized in that, The initial binarization assignment information of each pixel in the initial binarized image is a third assignment; the step of setting the binarization assignment information of pixels within the pixel boundary to a first assignment and setting the binarization assignment information of pixels outside the pixel boundary to a second assignment to obtain the initial binarized image includes: The binarization assignment information of the pixels inside the pixel boundary and adjacent to the pixel boundary is modified from the third assignment to the first assignment, and the binarization assignment information of the pixels outside the pixel boundary and adjacent to the pixel boundary is modified from the third assignment to the second assignment. The pixels in the initial binarized image whose binarization assignment information is the third assignment are traversed. If there are pixels with the first assignment among the multiple neighboring pixels of the currently traversed pixel, the binarization assignment information of the currently traversed pixel is modified from the third assignment to the first assignment. If a pixel with the second assigned value exists among multiple adjacent pixels of the currently traversed pixel, the binarization assignment information of the currently traversed pixel is modified from the third assignment to the second assignment until the traversal of the initial binarized image is completed, and the initial binarized image is obtained.

9. An image conversion device, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the image conversion method as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement the image conversion method as described in any one of claims 1-8.

11. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device performs the image conversion method as described in any one of claims 1-8.

Images