技术领域Technical field
本申请属于芯片生产技术领域，尤其涉及一种快速对准方法、快速对准装置、电子设备及计算机可读存储介质。The present application belongs to the field of chip production technology, and in particular relates to a rapid alignment method, rapid alignment device, electronic equipment and computer-readable storage media.
背景技术Background technique
目前芯片生产过程中，随着芯片生产技术节点不断推进，生产中产生的缺陷越来越小，电子束缺陷检测显得尤为重要。目前传统的电子束缺陷检测主要采取“芯片到芯片(Die to Die)”的检测方式，然而这种方式对于系统性缺陷和非周期性区域束手无策，而且检测缺陷率过度依赖于检测图像与参考图像之间的对准效果。为了应对这些问题，基于设计版图的电子束缺陷检测方法越来越重要。In the current chip production process, as chip production technology nodes continue to advance, defects generated in production are getting smaller and smaller, and electron beam defect detection is particularly important. At present, traditional electron beam defect detection mainly adopts the "die to die" detection method. However, this method is unable to deal with systematic defects and non-periodic areas, and the detection defect rate is overly dependent on the detection image and the reference image. alignment effect. In order to deal with these problems, electron beam defect detection methods based on design layout are becoming more and more important.
然而，在电子束缺陷检测中，设计版图与扫描电子显微镜(Scanning ElectronMicroscope，SEM)图像的对准精度关系到后续检测的精准度。目前，设计版图与SEM图像的对准方法耗费时间长，对准误差大。因此，如何实现精准且快速的对准方法已成为当务之急。However, in electron beam defect inspection, the alignment accuracy of the design layout and the scanning electron microscope (SEM) image is related to the accuracy of subsequent inspection. Currently, the alignment method between the design layout and the SEM image takes a long time and has large alignment errors. Therefore, how to achieve accurate and fast alignment methods has become a top priority.
发明内容Contents of the invention
本申请提供一种快速对准方法、快速装置、电子设备及计算机可读存储介质，可以通过初对齐和精准对齐两重对准操作，提高SEM图像与设计版图的对准精度和对准效率，达到精准且快速的对准效果。This application provides a rapid alignment method, rapid device, electronic equipment and computer-readable storage medium, which can improve the alignment accuracy and efficiency of SEM images and design layouts through dual alignment operations of initial alignment and precise alignment. Achieve precise and fast alignment results.
根据本申请的第一方面，提供一种快速对准方法，该快速对准方法包括：According to a first aspect of the present application, a rapid alignment method is provided, which includes:
根据扫描电子显微镜图像，从设计版图中确定出目标区域图；Determine the target area map from the design layout based on the scanning electron microscope image;
对扫描电子显微镜图像进行处理，得到目标格式的第一轮廓图；Process the scanning electron microscope image to obtain the first contour image of the target format;
根据第一轮廓图的第一特征信息和目标区域图的第二特征信息，从目标区域图中确定出多个候选对准区域；Determine a plurality of candidate alignment areas from the target area map according to the first feature information of the first contour map and the second feature information of the target area map;
分别计算多个候选对准区域与所述第一轮廓图之间的第一相似度；Calculate first similarities between the plurality of candidate alignment regions and the first contour map respectively;
根据多个候选对准区域与所述第一轮廓图之间的第一相似度，确定目标对准结果。A target alignment result is determined according to a first similarity between a plurality of candidate alignment areas and the first contour map.
根据本申请的第二方面，提供一种快速对准装置，其包括：According to a second aspect of the present application, a rapid alignment device is provided, which includes:
区域图确定模块，用于根据扫描电子显微镜图像，从设计版图中确定出目标区域图；The area map determination module is used to determine the target area map from the design layout based on the scanning electron microscope image;
轮廓图得到模块，用于对所述扫描电子显微镜图像进行处理，得到目标格式的第一轮廓图；A contour image obtaining module is used to process the scanning electron microscope image and obtain a first contour image in a target format;
候选区域确定模块，用于根据第一轮廓图的第一特征信息和目标区域图的第二特征信息，从目标区域图中确定出多个候选对准区域；A candidate area determination module, configured to determine multiple candidate alignment areas from the target area map based on the first feature information of the first contour map and the second feature information of the target area map;
第一相似度计算模块，用于分别计算多个候选对准区域与第一轮廓图之间的第一相似度；A first similarity calculation module, configured to respectively calculate the first similarity between the plurality of candidate alignment areas and the first contour map;
目标结果确定模块，用于根据多个候选对准区域与第一轮廓图之间的第一相似度，确定目标对准结果。The target result determination module is configured to determine the target alignment result based on the first similarity between the plurality of candidate alignment areas and the first contour map.
根据本申请的第三方面，提供一种电子设备，电子设备包括：处理器以及存储有计算机程序指令的存储器；处理器执行计算机程序指令时实现上述的任一种快速对准方法。According to a third aspect of the present application, an electronic device is provided. The electronic device includes: a processor and a memory storing computer program instructions; when the processor executes the computer program instructions, any one of the above fast alignment methods is implemented.
根据本申请的第四方面，提供一种计算机可读存储介质，其特征在于，计算机可读存储介质上存储有计算机程序指令，计算机程序指令被处理器执行时实现上述的任一种快速对准方法。According to a fourth aspect of the present application, a computer-readable storage medium is provided, which is characterized in that computer program instructions are stored on the computer-readable storage medium. When the computer program instructions are executed by a processor, any of the above-mentioned fast alignments can be achieved. method.
综上所述，本申请实施例提供的一种快速对准方法、快速对准装置、电子设备及计算机可读存储介质，可以根据扫描电子显微镜图像，从设计版图确定出与对应的目标区域图，从而初步确定版图对准范围。通过对扫描电子显微镜图像进行处理，得到目标格式的第一轮廓图，从而将扫描电子显微镜图像转化为第一轮廓图像，便于后续进行对准操作。并且根据第一轮廓图的第一特征信息和目标区域图的第二特征信息，从目标区域图中确定出多个候选对准区域，如此，可以通过特征信息进行初步对准操作，可以从目标区域图中筛选出多个对准概率较大的候选对准区域，筛除无效区域，如此可以减少后续精对准操作中对无效位置进行相似操作计算，显著提高对准效率。以及，分别计算多个所述候选对准区域与所述第一轮廓图之间的第一相似度，根据多个所述候选对准区域与第一轮廓图之间的第一相似度，确定目标对准结果，从而可以通过滑动操作对每个候选区域进行相似度计算，以实现精对准操作，并且根据多个第一相似度来衡量目标对准结果，可以最大程度上保证对准结果的准确性。如此，通过初对齐和精准对齐两重对准操作，提高SEM图像与设计版图的对准精度和对准效率，达到精准且快速的对准效果。To sum up, the fast alignment method, fast alignment device, electronic equipment and computer-readable storage medium provided by the embodiments of the present application can determine the corresponding target area map from the design layout based on the scanning electron microscope image. , thereby initially determining the layout alignment range. By processing the scanning electron microscope image, a first contour image in the target format is obtained, thereby converting the scanning electron microscope image into a first contour image to facilitate subsequent alignment operations. And according to the first feature information of the first contour map and the second feature information of the target area map, a plurality of candidate alignment areas are determined from the target area map. In this way, a preliminary alignment operation can be performed through the feature information, and the target area can be obtained from the target area map. In the area map, multiple candidate alignment areas with high alignment probabilities are screened out, and invalid areas are screened out. This can reduce the calculation of similar operations on invalid locations in subsequent fine alignment operations and significantly improve alignment efficiency. And, calculate first similarities between a plurality of candidate alignment regions and the first contour map respectively, and determine based on the first similarities between a plurality of candidate alignment regions and the first contour map. Target alignment results, so that similarity calculations can be performed on each candidate area through sliding operations to achieve precise alignment operations, and the target alignment results are measured based on multiple first similarities to ensure the alignment results to the greatest extent accuracy. In this way, through the dual alignment operations of initial alignment and precise alignment, the alignment accuracy and efficiency of the SEM image and the design layout are improved, and accurate and fast alignment results are achieved.
附图说明Description of drawings
为了更清楚地说明本申请具体实施方式或现有技术中的技术方案，下面将对具体实施方式或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图是本申请的一些实施方式，对于本领域的技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。In order to more clearly explain the specific embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description The drawings illustrate some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without exerting creative efforts.
图1示出现有技术提供的一种对准方法的流程示意图；Figure 1 shows a schematic flow chart of an alignment method provided by the prior art;
图2示出本申请实施例提供的一种快速对准方法的流程示意图；Figure 2 shows a schematic flow chart of a rapid alignment method provided by an embodiment of the present application;
图3示出本申请实施例提供的一种扫描电子显微镜图像的示意图；Figure 3 shows a schematic diagram of a scanning electron microscope image provided by an embodiment of the present application;
图4示出本申请实施例提供的一种目标区域图的示意图；Figure 4 shows a schematic diagram of a target area map provided by an embodiment of the present application;
图5示出本申请实施例提供的一种目标格式的第一轮廓图的示意图；Figure 5 shows a schematic diagram of a first outline diagram of a target format provided by an embodiment of the present application;
图6示出本申请实施例提供的一种标记第一特征信息的第一轮廓图的示意图；FIG. 6 shows a schematic diagram of a first contour diagram marking first feature information provided by an embodiment of the present application;
图7示出本申请实施例提供的一种标记候选对准位置和候选对准区域的目标区域图的示意图；Figure 7 shows a schematic diagram of a target area map marking candidate alignment positions and candidate alignment areas provided by an embodiment of the present application;
图8示出本申请实施例提供的一种候选对准区域内滑动窗口滑动方式的示意图；Figure 8 shows a schematic diagram of a sliding window sliding method in a candidate alignment area provided by an embodiment of the present application;
图9示出本申请实施例提供的一种对准位置的示意图；Figure 9 shows a schematic diagram of an alignment position provided by an embodiment of the present application;
图10示出本申请实施例提供的另一种快速对准方法的流程示意图；Figure 10 shows a schematic flow chart of another rapid alignment method provided by an embodiment of the present application;
图11示出本申请实施例提供的一种快速对准装置的结构示意图；Figure 11 shows a schematic structural diagram of a rapid alignment device provided by an embodiment of the present application;
图12示出本申请实施例提供的一种电子设备的结构示意图。FIG. 12 shows a schematic structural diagram of an electronic device provided by an embodiment of the present application.
具体实施方式Detailed ways
为了使本申请的上述以及其他特征和优点更加清楚，下面结合附图进一步描述本申请。应当理解，本文给出的具体实施例是出于向本领域的技术人员解释的目的，仅是示例性的，而非限制性的。In order to make the above and other features and advantages of the present application clearer, the present application is further described below in conjunction with the accompanying drawings. It should be understood that the specific embodiments given herein are for the purpose of explanation to those skilled in the art, and are only illustrative and not restrictive.
在以下描述中，阐述了许多具体细节以提供对本申请的透彻理解。然而，对于本领域的技术人员来说，明显的是，不需要采用具体细节来实践本申请。在其他情况下，未详细描述众所周知的步骤或操作，以避免模糊本申请。In the following description, numerous specific details are set forth to provide a thorough understanding of the present application. However, it will be apparent to one skilled in the art that the specific details need not be employed in order to practice the present application. In other instances, well-known steps or operations have not been described in detail so as not to obscure the application.
目前，SEM图像与设计版图间的对准方法是首先需要在指定位置采集SEM图像，将SEM图像轮廓转化为与设计版图相同的格式并保存为模板后，需要在设计版图上SEM图拍摄位置附近确定一定大小的滑动窗口，以在窗口内部滑动模板的方式逐帧计算设计版图与SEM图轮廓之间的相似度，具体为图形之间的面积相似度。当某个滑动位置计算出的相似度指标大于所预设的阈值时，则停止滑动，并输出当前的位置最为最终对准位置。At present, the alignment method between the SEM image and the design layout is to first collect the SEM image at a designated position. After converting the SEM image outline into the same format as the design layout and saving it as a template, it is necessary to locate the SEM image near the shooting position on the design layout. Determine a sliding window of a certain size, and calculate the similarity between the design layout and the outline of the SEM image frame by frame by sliding the template inside the window, specifically the area similarity between the graphics. When the similarity index calculated for a certain sliding position is greater than the preset threshold, the sliding is stopped and the current position is output as the final alignment position.
具体地，图1示出现有技术提供的一种对准方法的流程示意图，如图1所示，该对准方法的具体步骤如下：Specifically, Figure 1 shows a schematic flow chart of an alignment method provided by the prior art. As shown in Figure 1, the specific steps of the alignment method are as follows:
S11，在指定位置采集扫描电子显微镜图像，对SEM图像进行轮廓提取并将SEM图轮廓转化为与设计版图相同的格式。S11, collect a scanning electron microscope image at a designated position, extract the outline of the SEM image, and convert the SEM image outline into the same format as the design layout.
S12，根据采图精度在设计版图上确定一定大小的对准范围。S12: Determine an alignment range of a certain size on the design layout based on the accuracy of the drawing.
S13，在对准范围内，以滑动的方式逐帧计算设计版图与SEM图轮廓图形之间的相似度。S13. Within the alignment range, calculate the similarity between the design layout and the SEM image outline graphic frame by frame in a sliding manner.
S14，判断当前滑动位置所计算出来的相似度指标是否大于预设阈值；若大于，跳转S15。若所有滑动位置面积相似度都不大于预设阈值，跳转S16。S14: Determine whether the similarity index calculated from the current sliding position is greater than the preset threshold; if it is greater, jump to S15. If the area similarities of all sliding positions are not greater than the preset threshold, jump to S16.
S15，认为对准成功，停止滑动，并输出当前位置作为最终对准位置。S15, it is considered that the alignment is successful, stops sliding, and outputs the current position as the final alignment position.
S16，认为对准失败。S16, it is considered that the alignment failed.
然而，上述对准方法中，需要在设置的对准范围内的设计版图上逐帧滑动并计算SEM图像轮廓图形与设计版图图形的相似度，因此当机台stage或ebeam精度较低时，SEM图像拍摄位置距离指定拍摄位置较远，此时的对准范围会较大，如此，需要在更多的滑动位置计算相似度，对准效率明显降低。并且在对准精度要求更高的应用场景中，若要获得更加准确的对准位置，同样也需要在更多位置进行相似度计算，对准效率下降。However, in the above alignment method, it is necessary to slide frame by frame on the design layout within the set alignment range and calculate the similarity between the SEM image outline graphics and the design layout graphics. Therefore, when the machine stage or ebeam accuracy is low, the SEM If the image shooting position is far from the specified shooting position, the alignment range will be larger. In this case, the similarity needs to be calculated at more sliding positions, and the alignment efficiency will be significantly reduced. And in application scenarios that require higher alignment accuracy, to obtain more accurate alignment positions, similarity calculations also need to be performed at more locations, and the alignment efficiency decreases.
同时，即使是在对准范围较小，对准精度要求也不高的场景下，上述对准方法通过使用面积相似度作为相似度指标来判断是否对准也存在失败的风险，尤其在SEM图像轮廓图形或设计版图图形单一，但面积较大时，较高的相似度并不能完全代表图形形状的相似，只考虑面积方面的相似性而忽略了成功对准也要求的形状上的相似性，会导致有些情况下返回错误的对准位置。At the same time, even in scenarios where the alignment range is small and the alignment accuracy requirements are not high, the above alignment method still has the risk of failure by using area similarity as a similarity index to determine alignment, especially in SEM images. When the outline graphics or design layout graphics are single but have a large area, a higher degree of similarity does not completely represent the similarity of the graphics shapes. Only the similarity in area is considered and the similarity in shape is also required for successful alignment. This will cause incorrect alignment positions to be returned in some cases.
此外，上述对准方法中，在某个滑动位置所计算出的相似度大于预设阈值后就会停止对准流程并返回当前位置，预设阈值需要依据不同的设计版图或是设计版图上的不同层进行设定，较低的阈值可能会导致流程提前退出，并且返回的位置并不是最优对准位置，较高的阈值则可能会导致在所有滑动位置完成相似度计算后，正确的对准位置相似度没有达到阈值要求，被误报为对准失败。也就是说阈值的设定严重影响到对准位置的准确性，如此，容易造成误判，降低对准的精准性。In addition, in the above alignment method, when the similarity calculated at a certain sliding position is greater than the preset threshold, the alignment process will be stopped and returned to the current position. The preset threshold needs to be based on different design layouts or the design layout. Different layers are set. A lower threshold may cause the process to exit early, and the returned position is not the optimal alignment position. A higher threshold may cause the correct alignment to be completed after similarity calculations are completed at all sliding positions. The quasi-position similarity does not meet the threshold requirement and is falsely reported as an alignment failure. In other words, the setting of the threshold seriously affects the accuracy of the alignment position, which may easily cause misjudgment and reduce the accuracy of the alignment.
有鉴于此，本申请实施例提供一种快速且精准的对准方法，首先将SEM图像转换为与设计版图格式一致的轮廓图，分别提取轮廓图与设计版图的特征信息并进行特征匹配，如此，得到多个初对齐的候选对准区域。在所有候选对准区域进行更加精确的滑动对准操作，计算每个滑动位置与轮廓图之间的相似度，从而可以根据相似度确定出对准结果，如此，通过初对齐和精准对齐的两次对齐操作，一方面可以减少对准位置的误报，并且将全局最大相似度的位置作为对准位置，从而可以提高对准的精准度，另一方面，可以减少无效位置的相似度计算，显著提高对准效率。In view of this, embodiments of the present application provide a fast and accurate alignment method. First, the SEM image is converted into a contour diagram consistent with the format of the design layout, and the characteristic information of the contour diagram and the design layout is extracted and feature matched, so that , to obtain multiple initially aligned candidate alignment regions. Perform a more precise sliding alignment operation in all candidate alignment areas, calculate the similarity between each sliding position and the contour map, so that the alignment result can be determined based on the similarity. In this way, through both initial alignment and precise alignment, This alignment operation can, on the one hand, reduce false positives of alignment positions and use the position with the greatest global similarity as the alignment position, thereby improving the accuracy of alignment. On the other hand, it can reduce similarity calculations at invalid positions. Significantly improve alignment efficiency.
本申请实施例一方面提供一种快速对准方法，该快速对准方法可以应用于本申请实施例提供的快速对准装置，该快速对准装置可以配置在也本申请实施例提供的电子设备中。图2示出本申请实施例提供的一种快速对准方法的流程示意图，如图2所示，该快速对准方法包括以下步骤。On the one hand, embodiments of the present application provide a fast alignment method. The fast alignment method can be applied to the fast alignment device provided by the embodiments of the present application. The fast alignment device can be configured in the electronic equipment provided by the embodiments of the present application. middle. Figure 2 shows a schematic flowchart of a rapid alignment method provided by an embodiment of the present application. As shown in Figure 2, the rapid alignment method includes the following steps.
S21，根据扫描电子显微镜图像，从设计版图中确定出目标区域图。S21. Determine the target area map from the design layout based on the scanning electron microscope image.
S22，对扫描电子显微镜图像进行处理，得到目标格式的第一轮廓图。S22. Process the scanning electron microscope image to obtain the first contour image in the target format.
S23，根据第一轮廓图的第一特征信息和目标区域图的第二特征信息，从目标区域图中确定出多个候选对准区域。S23: Determine multiple candidate alignment areas from the target area map based on the first feature information of the first contour map and the second feature information of the target area map.
S24，分别计算多个候选对准区域与第一轮廓图之间的第一相似度。S24: Calculate first similarities between multiple candidate alignment areas and the first contour map respectively.
S25，根据多个候选对准区域与第一轮廓图之间的第一相似度，确定目标对准结果。S25: Determine the target alignment result based on the first similarity between the multiple candidate alignment areas and the first contour map.
在上述实施例中，可以根据扫描电子显微镜图像，从设计版图确定出与对应的目标区域图，从而初步确定版图对准范围。通过对扫描电子显微镜图像进行处理，得到目标格式的第一轮廓图，从而将扫描电子显微镜图像转化为第一轮廓图像，便于后续进行对准操作。并且根据第一轮廓图的第一特征信息和目标区域图的第二特征信息，从目标区域图中确定出多个候选对准区域，如此，可以通过特征信息进行初步对准操作，可以从目标区域图中筛选出多个对准概率较大的候选对准区域，筛除无效区域，如此可以减少后续精对准操作中对无效位置进行相似操作计算，显著提高对准效率。以及，分别计算多个所述候选对准区域与所述第一轮廓图之间的第一相似度，根据多个所述候选对准区域与第一轮廓图之间的第一相似度，确定目标对准结果，从而可以通过滑动操作对每个候选区域进行相似度计算，以实现精对准操作，并且根据多个第一相似度来衡量目标对准结果，可以最大程度上保证对准结果的准确性。如此，通过初对齐和精准对齐两重对准操作，提高SEM图像与设计版图的对准精度和对准效率，达到精准且快速的对准效果。In the above embodiment, the corresponding target area map can be determined from the design layout based on the scanning electron microscope image, thereby preliminarily determining the layout alignment range. By processing the scanning electron microscope image, a first contour image in the target format is obtained, thereby converting the scanning electron microscope image into a first contour image to facilitate subsequent alignment operations. And according to the first feature information of the first contour map and the second feature information of the target area map, a plurality of candidate alignment areas are determined from the target area map. In this way, a preliminary alignment operation can be performed through the feature information, and the target area can be obtained from the target area map. In the area map, multiple candidate alignment areas with high alignment probabilities are screened out, and invalid areas are screened out. This can reduce the calculation of similar operations on invalid locations in subsequent fine alignment operations and significantly improve alignment efficiency. And, calculate first similarities between a plurality of candidate alignment regions and the first contour map respectively, and determine based on the first similarities between a plurality of candidate alignment regions and the first contour map. Target alignment results, so that similarity calculations can be performed on each candidate area through sliding operations to achieve precise alignment operations, and the target alignment results are measured based on multiple first similarities to ensure the alignment results to the greatest extent accuracy. In this way, through the dual alignment operations of initial alignment and precise alignment, the alignment accuracy and efficiency of the SEM image and the design layout are improved, and accurate and fast alignment results are achieved.
下面对上述各步骤进行详细描述。Each of the above steps is described in detail below.
在S21中，扫描电子显微镜图像可以是利用高精度扫描电子显微镜对芯片的一个指定位置进行拍摄得到的图像。该指定位置为芯片非空白图案区域的任意位置。图3示出本申请实施例提供的一种扫描电子显微镜图像的示意图。设计版图可以为芯片的设计版图。目标区域图可以为与扫描电子显微镜图像对应的版图区域。图4示出本申请实施例提供的一种目标区域图的示意图。也就是说，目标图像区域对应的芯片范围与扫描电子显微镜图像对应的芯片范围包含指定位置的芯片区域。In S21, the scanning electron microscope image may be an image obtained by photographing a specified position of the chip using a high-precision scanning electron microscope. The specified position is any position in the non-blank pattern area of the chip. Figure 3 shows a schematic diagram of a scanning electron microscope image provided by an embodiment of the present application. The design layout may be the design layout of the chip. The target area map may be a layout area corresponding to the scanning electron microscope image. Figure 4 shows a schematic diagram of a target area map provided by an embodiment of the present application. That is to say, the chip range corresponding to the target image area and the chip range corresponding to the scanning electron microscope image include the chip area at the specified position.
此外，目标图像区域对应的芯片范围比扫描电子显微镜图像对应的芯片范围稍大。目标区域图可以根据扫描电子显微镜的采图精度确定。例如，扫描电子显微镜的采图精度为3um，目标区域图可以为5um～10um。In addition, the chip range corresponding to the target image area is slightly larger than the chip range corresponding to the SEM image. The target area map can be determined based on the mapping accuracy of the scanning electron microscope. For example, the image acquisition accuracy of a scanning electron microscope is 3um, and the target area image can be 5um~10um.
也就是说，快速对准装置可以根据扫描电子显微镜的采图精度在设计版图上确定预设大小的对准区域，将该对准区域作为目标区域图。That is to say, the rapid alignment device can determine an alignment area of a preset size on the design layout based on the imaging accuracy of the scanning electron microscope, and use the alignment area as the target area map.
在本申请实施例中，快速对准装置控制高精度扫描电子显微镜对准芯片的某个指定位置进行拍摄，获取到该指定位置对应的扫描电子显微镜图像，并且快速对准装置从芯片的设计版图中截取包含该指定位置的区域图形，从而获取目标区域图。In the embodiment of the present application, the rapid alignment device controls a high-precision scanning electron microscope to align and photograph a specified position of the chip, and obtains the scanning electron microscope image corresponding to the specified position, and the rapid alignment device obtains the image from the design layout of the chip. Intercept the area graphics containing the specified location to obtain the target area map.
在S22中，处理可以为图像处理，可以包括但不限于轮廓提取与格式转换。目标格式可以为设计版图格式。可选地，目标格式可以为图形设计系统(Graphic Design System，GDS)格式或者开放式图稿系统交换标准(Open Artwork System Interchange Standard，OASIS)格式。第一轮廓图可以为包含扫描电子显微镜图像轮廓的图形。图5示出本申请实施例提供的一种目标格式的第一轮廓图的示意图。In S22, the processing may be image processing, which may include but is not limited to contour extraction and format conversion. The target format can be a design layout format. Optionally, the target format may be a Graphic Design System (GDS) format or an Open Artwork System Interchange Standard (OASIS) format. The first profile graph may be a graph containing the profile of a scanning electron microscope image. FIG. 5 shows a schematic diagram of a first outline diagram of a target format provided by an embodiment of the present application.
在本申请实施例中，快速对准装置对扫描电子显微镜图像进行图像处理，得到与扫描电子显微镜图像对应的第一轮廓图，且第一轮廓图的格式与设计版图的格式一致。In the embodiment of the present application, the rapid alignment device performs image processing on the scanning electron microscope image to obtain a first profile image corresponding to the scanning electron microscope image, and the format of the first profile image is consistent with the format of the design layout.
在S23中，第一特征信息可以为第一轮廓图的特征信息。第二特征信息可以为目标区域图的特征信息。候选对准区域可以为目标区域图中与第一轮廓图具有相同特征的区域。候选对准区域的面积比第一轮廓图的面积大。可选地，候选对准区域的面积可以为第一轮廓图的面积的2倍以上。在本申请实施例中，快速对准装置从第二特征信息中查找与第一特征信息类似的特征信息，并从目标区域图中确定这些特征信息所在的各个区域，将这些区域作为候选对准区域。In S23, the first feature information may be the feature information of the first contour map. The second feature information may be feature information of the target area map. The candidate alignment area may be an area in the target area map that has the same characteristics as the first contour map. The area of the candidate alignment region is larger than the area of the first contour map. Optionally, the area of the candidate alignment region may be more than twice the area of the first contour map. In the embodiment of the present application, the rapid alignment device searches for feature information similar to the first feature information from the second feature information, determines each area where these feature information is located from the target area map, and uses these areas as candidate alignment area.
需要说明的是，候选对准区域可以为目标区域图上第一轮廓图的潜在对准区域。It should be noted that the candidate alignment area may be a potential alignment area of the first contour map on the target area map.
在S24中，第一相似度可以为候选对准区域与第一轮廓图之间的相似度。在本申请实施例中，快速对准装置计算每个候选对准区域与第一轮廓图之间的相似度度，从而得到多个第一相似度。其中，一个第一相似对对应一个候选对准区域。In S24, the first similarity may be the similarity between the candidate alignment area and the first contour map. In the embodiment of the present application, the rapid alignment device calculates the similarity between each candidate alignment area and the first contour map, thereby obtaining multiple first similarities. Among them, a first similar pair corresponds to a candidate alignment region.
在本申请实施例中，计算第一相似度的方式有多种。可选地，第一相似度可以采用面积交并比计算方式得到。In the embodiment of the present application, there are multiple ways to calculate the first similarity. Optionally, the first similarity can be obtained by calculating the area intersection and union ratio.
具体地，第一相似度的计算公式如下：Specifically, the calculation formula of the first similarity is as follows:
Similarity ＝ (Template_Area∩Design_Area)/(Template_Area∪Design_Area) (1)Similarity = (Template_Area∩Design_Area)/(Template_Area∪Design_Area) (1)
其中，Template_Area为第一轮廓图中多边形的面积，Design_Area为后续那对准区域内多边形的面积，Similarity为第一相似度。Among them, Template_Area is the area of the polygon in the first contour map, Design_Area is the area of the polygon in the subsequent alignment area, and Similarity is the first similarity.
需要说明的是，第一轮廓图中的多边形可以为在第一轮廓图中由轮廓构成的多边形。候选对准区域中的多边形可以为在候选对准区域中由轮廓构成的多边形。It should be noted that the polygons in the first contour diagram may be polygons composed of contours in the first contour diagram. The polygons in the candidate alignment area may be polygons composed of outlines in the candidate alignment area.
在S25中，目标对准结果可以包括对准成功以及对准失败。在对准成功的情况下，目标对准结果还可以包括目标对准位置。其中，目标对准位置为目标区域图中与第一轮廓图最匹配的区域。目标对准位置可以为多个候选区域中之一。In S25, the target alignment results may include alignment success and alignment failure. In the case of successful alignment, the target alignment result may also include the target alignment position. The target alignment position is the area in the target area map that best matches the first contour map. The target alignment location may be one of multiple candidate areas.
在一些实施例中，S22，对扫描电子显微镜图像进行处理，得到目标格式的第一轮廓图，可以包括：In some embodiments, S22, process the scanning electron microscope image to obtain the first contour image in the target format, which may include:
对扫描电子显微镜图像进行轮廓提取，得到第二轮廓图；Perform contour extraction on the scanning electron microscope image to obtain a second contour map;
对第二轮廓图进行格式转换，得到目标格式的第一轮廓图。Perform format conversion on the second contour image to obtain the first contour image in the target format.
这里，轮廓提取可以采用现有轮廓提取方法，例如掏空算法以及追踪算法等。第二轮廓图可以为图像格式，如jpg格式。目标格式可以为设计版图格式，如GDS格式或者OASIS格式。第一轮廓图与第二轮廓图均为与扫描电子显微镜图像对应的轮廓图，包含扫描电子显微镜的所有轮廓。Here, existing contour extraction methods can be used for contour extraction, such as hollowing out algorithms and tracking algorithms. The second contour map may be in image format, such as jpg format. The target format can be a design layout format, such as GDS format or OASIS format. The first profile image and the second profile image are both profile images corresponding to the scanning electron microscope image, and include all profiles of the scanning electron microscope.
在本申请实施例中，快速对准装置通过轮廓提取算法对扫描电子显微镜图像进行轮廓提取，得到与扫描电子显微镜图像对应的第二轮廓图。并对该第二轮廓图进行格式转换，将轮廓图的格式从图像格式转换为目标格式，得到第一轮廓图。In the embodiment of the present application, the rapid alignment device performs contour extraction on the scanning electron microscope image through a contour extraction algorithm to obtain a second contour map corresponding to the scanning electron microscope image. And perform format conversion on the second contour map, convert the format of the contour map from the image format to the target format, and obtain the first contour map.
在上述实施例中，对扫描电子显微镜进行轮廓提取和格式转换，可以将扫描电子显微镜转换为能与设计版图进行对准的轮廓图，如此，一方面便于后续对准计算，另一方面由于轮廓图的格式与设计版图格式一致，可以减少由于格式不匹配造成的对准误差，提高对准精度。In the above embodiment, the scanning electron microscope is subjected to contour extraction and format conversion, and the scanning electron microscope can be converted into a contour diagram that can be aligned with the design layout. In this way, on the one hand, it facilitates subsequent alignment calculations, and on the other hand, due to the contour The format of the drawing is consistent with the format of the design layout, which can reduce alignment errors caused by format mismatch and improve alignment accuracy.
在一些实施例中，S23，根据第一轮廓图的第一特征信息和目标区域图的第二特征信息，从目标区域图中确定出多个候选对准区域，可以包括：In some embodiments, S23, determining multiple candidate alignment areas from the target area map based on the first feature information of the first contour map and the second feature information of the target area map may include:
根据第一轮廓图的第一特征信息和目标区域图的第二特征信息，从目标区域图中确定出多个候选对准位置；Determine a plurality of candidate alignment positions from the target area map according to the first feature information of the first contour map and the second feature information of the target area map;
根据每个候选对准位置在目标区域图中的位置，确定每个候选对准位置对应的候选对准区域，以得到多个候选对准区域。According to the position of each candidate alignment position in the target area map, a candidate alignment area corresponding to each candidate alignment position is determined to obtain multiple candidate alignment areas.
这里，第一特征信息可以为第一轮廓图内多边形的特征信息。第二特征信息可以为目标区域图中多个多边形的特征信息。Here, the first feature information may be feature information of polygons in the first outline map. The second feature information may be feature information of multiple polygons in the target area map.
在本申请实施例中，快速对准装置通过特征匹配法，将第一特征信息与第二特征信息进行匹配，从第二特征信息中选取与第一轮廓图内多边形的特征信息匹配的特征信息，并确定这些匹配的特征信息在目标区域图中所在的区域，将这些区域作为候选对准位置。In the embodiment of the present application, the rapid alignment device matches the first feature information with the second feature information through a feature matching method, and selects feature information from the second feature information that matches the feature information of the polygon in the first contour map. , and determine the areas where these matching feature information are located in the target area map, and use these areas as candidate alignment locations.
候选对准位置可以为目标区域图中与第一轮廓图中第一特征信息匹配的位置。候选对准区域可以为包含候选对准位置的区域。可选地，候选对准区域可以为比候选对准位置的外接矩形框稍大的区域。候选对准区域的面积可以为候选对准位置的外接矩形框面积的2倍以上。The candidate alignment position may be a position in the target area map that matches the first feature information in the first contour map. The candidate alignment area may be an area containing the candidate alignment location. Alternatively, the candidate alignment area may be an area slightly larger than the circumscribing rectangular frame of the candidate alignment position. The area of the candidate alignment area may be more than twice the area of the circumscribing rectangular frame of the candidate alignment position.
在上述实施例中，通过使用第一特征信息提前对目标区域图内的候选对准位置进行筛选，从而可以通过特征匹配法从目标区域图中筛选出与第一轮廓图特征匹配的候选对准位置，如此，可以精确确定目标区域图中初步对准位置。In the above embodiment, by using the first feature information to screen the candidate alignment positions in the target area map in advance, candidate alignment positions that match the features of the first contour map can be screened out from the target area map through the feature matching method. position, so that the preliminary alignment position in the target area map can be accurately determined.
并且，相较现有技术通过在设计版图上逐帧滑动轮廓图，并在每一个滑动位置都计算相似度来说，本申请可以提前选取对准概率较大的候选对准区域，以便后续进行相似度计算，从而减少在无效位置的相似度计算，进而显著提高对准效率。Moreover, compared with the existing technology that slides the contour map frame by frame on the design layout and calculates the similarity at each sliding position, this application can select candidate alignment areas with higher alignment probability in advance for subsequent operations. Similarity calculation, thereby reducing similarity calculation at invalid positions, thereby significantly improving alignment efficiency.
在一些实施例中，在S23之前，该快速对准方法还包括：In some embodiments, before S23, the rapid alignment method further includes:
对第一轮廓图和目标区域图分别进行特征分析，得到第一特征信息和第二特征信息。Perform feature analysis on the first contour map and the target area map respectively to obtain first feature information and second feature information.
这里，快速对准装置可以通过图形特征分析法对第一轮廓图进行特征分析，得到第一特征信息。以及，快速对准装置可以采用相同的图形特征分析法对目标区域图进行特征分析得到第二特征信息。其中，特征分析可以包括但不限于对形状、角点、质心、面积等图形特征的分析。Here, the rapid alignment device can perform feature analysis on the first contour map through a graphical feature analysis method to obtain the first feature information. In addition, the rapid alignment device can use the same graphic feature analysis method to perform feature analysis on the target area map to obtain the second feature information. Among them, feature analysis may include but is not limited to analysis of graphical features such as shape, corner points, centroid, area, etc.
第一特征信息和第二特征信息可以包括多边形的角点位置、多边形的质心位置、多边形的外接矩形的长宽比与相对位置、多边形的面积中至少之一。The first feature information and the second feature information may include at least one of the corner point position of the polygon, the centroid position of the polygon, the aspect ratio and relative position of the circumscribed rectangle of the polygon, and the area of the polygon.
在本申请实施例中，快速对准装置对第一轮廓图进行特征分析，可以为快速对准装置从第一轮廓图中确定一个的多边形，对准装置对这个多边形进行特征分析，从而得到第一特征信息。快速对准装置对目标区域图进行特征分析，可以为对准装置可以从目标区域图确定多个多边形，并对每个多边形进行特征分析，从而得到第二特征信息。如此，通过特征分析，可以提取第一特征信息和第二特征信息，从而便于后续进行初步对齐。In the embodiment of the present application, the rapid alignment device performs feature analysis on the first contour map, and can determine a polygon from the first contour map for the rapid alignment device, and the alignment device performs feature analysis on this polygon, thereby obtaining the third polygon. a characteristic information. The rapid alignment device performs feature analysis on the target area map. The alignment device can determine multiple polygons from the target area map and perform feature analysis on each polygon to obtain the second feature information. In this way, through feature analysis, the first feature information and the second feature information can be extracted, thereby facilitating subsequent preliminary alignment.
在一些实施例中，通过特征匹配法将第一特征信息与第二特征信息进行特征匹配，从所述目标区域图中确定与所述第一轮廓图内多边形匹配的候选对准位置，可以包括：In some embodiments, performing feature matching on the first feature information and the second feature information through a feature matching method, and determining candidate alignment positions that match the polygons in the first contour map from the target area map, which may include :
通过特征匹配法，确定第二特征信息中与第一特征信息匹配的第三特征信息，并确定第三特征信息在目标区域图中所在的位置，并将第三特征信息对应的一个或多个位置作为候选对准位置。Through the feature matching method, the third feature information in the second feature information that matches the first feature information is determined, the location of the third feature information in the target area map is determined, and one or more features corresponding to the third feature information are position as a candidate alignment position.
这里，第三特征信息可以为第二特征信息中与第一特征信息匹配的特征信息，第三特征信息与第一特征信息包括的特征种类相同。第三特征信息可以为多边形的角点位置、多边形的质心位置、多边形的外接矩形的长宽比与相对位置、多边形的面积中至少一种。Here, the third feature information may be feature information in the second feature information that matches the first feature information, and the third feature information includes the same feature type as the first feature information. The third feature information may be at least one of the corner point position of the polygon, the centroid position of the polygon, the aspect ratio and relative position of the circumscribed rectangle of the polygon, and the area of the polygon.
在上述实施例中，通过特征匹配法进行初步对准操作，从而可以初步筛选出对准概率较大的区域。In the above embodiment, the feature matching method is used to perform a preliminary alignment operation, so that areas with a high alignment probability can be initially screened out.
在一些实施例中，第三特征信息在目标区域图中所在的位置可以为目标区域图中满足以下至少之一条件的多边形的部分或全部区域：多边形的角点位置与第一轮廓图中多边形的角点位置接近、多边形的质点位置与第一轮廓图中多边形的质点位置接近、多边形的外接矩形与第一轮廓图中多边形的外接矩形框的长宽比与相对位置接近、多边形的面积与第一轮廓图中多边形的面积接近。In some embodiments, the location of the third feature information in the target area map may be part or all of the polygon in the target area map that satisfies at least one of the following conditions: the corner position of the polygon is consistent with the polygon in the first contour map. The position of the corner points of the polygon is close to that of the polygon in the first contour diagram. The aspect ratio and relative position of the circumscribed rectangle of the polygon and the circumscribed rectangle of the polygon in the first contour diagram are close. The area of the polygon is close to that of the polygon in the first contour diagram. The areas of the polygons in the first contour plot are close.
在本申请实施例中，多边形的角点位置与第一轮廓图中多边形的角点位置接近，可以理解为，目标区域图中多边形的角点位置与第一轮廓图中多边形的角点位置之间的误差在极小的第一误差范围内。In the embodiment of the present application, the position of the corner point of the polygon is close to the position of the corner point of the polygon in the first contour diagram. It can be understood that the position of the corner point of the polygon in the target area diagram is the same as the position of the corner point of the polygon in the first contour diagram. The error between them is within the extremely small first error range.
多边形的质点位置与第一轮廓图中多边形的质点位置接近，可以理解为，目标区域图中多边形的质点位置与第一轮廓图中多边形的质点位置之间的误差在极小的第二误差范围内。The particle position of the polygon is close to the particle position of the polygon in the first contour diagram. It can be understood that the error between the particle position of the polygon in the target area diagram and the particle position of the polygon in the first contour diagram is within a very small second error range. Inside.
多边形的外接矩形与第一轮廓图中多边形的外接矩形框的长宽比与相对位置接近，可以理解为，目标区域图中多边形的外接矩形的长宽比与第一轮廓图中多边形的外接矩形框的长宽比之间的误差在极小的第三误差范围内，以及目标区域图中多边形的外接矩形的相对位置与第一轮廓图中多边形的外接矩形框的相对位置之间的误差在极小的第四误差范围内。The aspect ratio and relative position of the circumscribed rectangle of the polygon and the circumscribed rectangle of the polygon in the first outline map are close. It can be understood that the aspect ratio of the circumscribed rectangle of the polygon in the target area map is the same as the circumscribed rectangle of the polygon in the first outline map. The error between the aspect ratios of the boxes is within a very small third error range, and the error between the relative positions of the circumscribed rectangle of the polygon in the target area map and the relative position of the circumscribed rectangle of the polygon in the first contour map is within Within a very small fourth margin of error.
多边形的面积与第一轮廓图中多边形的面积接近，可以理解为，目标区域图中多边形的面积与第一轮廓图中多边形的面积之间的误差在极小的第五误差范围内。The area of the polygon is close to the area of the polygon in the first contour map, which can be understood as the error between the area of the polygon in the target area map and the area of the polygon in the first contour map is within a very small fifth error range.
需要说明的是，第一误差范围、第二误差范围、第三误差范围、第四误差范围以及第五误差范围可以表示极小误差范围，可以根据需求设定。It should be noted that the first error range, the second error range, the third error range, the fourth error range and the fifth error range can represent extremely small error ranges and can be set according to requirements.
在上述实施例中，特征信息包括一个或者多个特征，如此可以使得第一轮廓图与目标区域图进行初步对准时，可以通过考虑面积特征以及图形特征，使得第一轮廓图像与候选对准位置的图形面积和/或图形特征接近，如此，可以在一定程度减少对准位置的误报，并且进一步缩小对准范围。此外，在除面积特征外增加对其它图形特征的匹配流程，可以最大程度保证特征匹配的可靠性，减少对候选对准位置的误报。In the above embodiment, the feature information includes one or more features, so that when the first contour image and the target area map are initially aligned, the area features and graphic features can be considered to align the first profile image with the candidate alignment position. The graphic area and/or graphic features are close to each other. In this way, false alarms of the alignment position can be reduced to a certain extent and the alignment range can be further reduced. In addition, adding a matching process for other graphic features in addition to area features can ensure the reliability of feature matching to the greatest extent and reduce false alarms on candidate alignment positions.
例如，图6示出本申请实施例提供的一种标记第一特征信息的第一轮廓图的示意图，如图6所示，第一特征信息可以包括两个角点的位置，由圆框标记出来。快速对准装置从第二特征信息中查找与这两个角点位置匹配的两个类似角点。图7示出本申请实施例提供的一种标记候选对准位置和候选对准区域的目标区域图的示意图。如图7所示，圆形框内区域的角点特征与第一轮廓图的角点特征相似，因此，将圆形框内区域作为候选对准位置。图7中的方形框表示候选对准区域。其中，每个方形框包含一个圆形框，可以将方形框理解为比圆形框的外接矩形框稍大的区域范围。For example, Figure 6 shows a schematic diagram of a first contour map for marking first feature information provided by an embodiment of the present application. As shown in Figure 6, the first feature information may include the positions of two corner points, marked by circular frames. come out. The rapid alignment device searches for two similar corner points that match the positions of the two corner points from the second feature information. FIG. 7 shows a schematic diagram of a target area map marking candidate alignment positions and candidate alignment areas provided by an embodiment of the present application. As shown in FIG. 7 , the corner point features of the area within the circular frame are similar to the corner point features of the first contour image. Therefore, the area within the circular frame is used as a candidate alignment position. The square boxes in Figure 7 represent candidate alignment areas. Each square frame contains a circular frame, and the square frame can be understood as a slightly larger area than the circumscribed rectangular frame of the circular frame.
在一些实施例中，S24，分别计算多个候选对准区域与第一轮廓图之间的第一相似度，可以包括：In some embodiments, S24, calculating the first similarity between multiple candidate alignment regions and the first contour map respectively may include:
将预设的滑动窗口以预设步长在每个候选对准区域内进行滑动，计算每个滑动位置处滑动窗口覆盖的区域与第一轮廓图之间的相似度，以得到多个滑动位置与第一轮廓图之间的第二相似度；Slide the preset sliding window within each candidate alignment area at a preset step size, and calculate the similarity between the area covered by the sliding window and the first contour map at each sliding position to obtain multiple sliding positions. a second degree of similarity to the first contour;
基于每个候选对准区域中多个滑动位置对应的第二相似度，确定每个候选对准区域与第一轮廓图之间的第一相似度。Based on the second similarities corresponding to the plurality of sliding positions in each candidate alignment area, a first similarity between each candidate alignment area and the first contour map is determined.
这里，预设的滑动窗口的大小与第一轮廓图的大小相同。预设步长可以根据需求设定。需要说明的是，预设步长越小，对准位置越精确。滑动位置可以为滑动窗口在候选对准区域上以预设的步长滑动对应的覆盖位置。Here, the size of the preset sliding window is the same as the size of the first contour map. The default step size can be set according to needs. It should be noted that the smaller the preset step size, the more accurate the alignment position. The sliding position may be a sliding window that slides the corresponding coverage position on the candidate alignment area with a preset step size.
计算每个滑动位置处滑动窗口覆盖的区域与第一轮廓图之间的相似度，可以理解为，基于相似度计算方法计算在候选对准区域内滑动窗口在每个滑动位置覆盖的区域与第一轮廓图之间的相似度。其中，相似度计算方法有多种。可选地，采用公式(1)进行计算相似度，即面积交并比值为相似度。Calculating the similarity between the area covered by the sliding window at each sliding position and the first contour map can be understood as calculating, based on the similarity calculation method, the area covered by the sliding window at each sliding position within the candidate alignment area and the first contour map. Similarity between contour images. Among them, there are many methods for calculating similarity. Optionally, formula (1) is used to calculate the similarity, that is, the area intersection ratio is the similarity.
第二相似度可以是指滑动位置对应的滑动窗口覆盖区域与第一轮廓图之间的相似度。其中，一个第二相似度对应一个滑动位置，也就说滑动位置的数量与第二相似度的数量相同。The second similarity may refer to the similarity between the sliding window coverage area corresponding to the sliding position and the first contour map. Among them, one second degree of similarity corresponds to one sliding position, that is to say, the number of sliding positions is the same as the number of second degrees of similarity.
需要说明的是，一个候选对准区域有多个滑动位置，每个滑动位置对应一个第二相似度。It should be noted that a candidate alignment area has multiple sliding positions, and each sliding position corresponds to a second similarity.
图8示出本申请实施例提供的一种候选对准区域内滑动窗口滑动方式的示意图。如图8所示，箭头表示滑动窗口的滑动方向。滑动窗口可以以预设步长从候选区域的左上角沿水平和竖直方向向右下角滑动，即沿水平方向滑动，一行滑动完毕后，滑动窗口向竖直方向滑动一个步长，然后继续水平方向滑动，直达滑动窗口滑动到右下角。此时，滑动窗口在一个候选对准区域滑动完毕。FIG. 8 shows a schematic diagram of a sliding window sliding method in a candidate alignment area provided by an embodiment of the present application. As shown in Figure 8, the arrow indicates the sliding direction of the sliding window. The sliding window can slide from the upper left corner of the candidate area to the lower right corner in the horizontal and vertical directions at a preset step size, that is, sliding in the horizontal direction. After one row has been slid, the sliding window slides one step length in the vertical direction, and then continues horizontally. Swipe in the direction until the sliding window slides to the lower right corner. At this time, the sliding window has finished sliding in a candidate alignment area.
需要说明的是，滑动窗口滑动方式有多种，如从右上角向左下角滑动，从左下角向右上角滑动，以及右下角向左上角滑动。在本申请实施例中，对滑动窗口的滑动方式不做限制。It should be noted that there are many ways to slide the sliding window, such as sliding from the upper right corner to the lower left corner, sliding from the lower left corner to the upper right corner, and sliding the lower right corner to the upper left corner. In the embodiment of the present application, there is no restriction on the sliding method of the sliding window.
第一相似度可以为候选对准区域与第一轮廓图之间多个第二相似度中之一。第一相似度对应的滑动位置可以为候选对准区域中与第一轮廓图中最类似的位置。The first degree of similarity may be one of a plurality of second degrees of similarity between the candidate alignment region and the first contour map. The sliding position corresponding to the first similarity may be the most similar position in the candidate alignment area to the first contour map.
在上述实施例中，通过滑动窗口以预设步长进行滑动的方式，检测每个候选对准区域内每个滑动位置分别与第一轮廓图之间的相似度，并从中确定出出每个候选对准区域与第一轮廓图第一相似度，如此，可以在每个候选对准区域内进行更加精准的滑动对准，以便后续筛选出全局最佳对准位置，从而提高对准的精准性。In the above embodiment, the similarity between each sliding position in each candidate alignment area and the first contour map is detected by sliding the sliding window with a preset step size, and the similarity between each sliding position and the first contour map is determined. The first similarity between the candidate alignment area and the first contour map. In this way, more precise sliding alignment can be performed in each candidate alignment area, so that the global best alignment position can be subsequently screened, thereby improving the accuracy of alignment. sex.
在一些实施例中，基于每个候选对准区域中多个滑动位置对应的第二相似度，确定每个候选对准区域与第一轮廓图之间的第一相似度，包括：In some embodiments, determining the first similarity between each candidate alignment area and the first contour map based on the second similarity corresponding to the plurality of sliding positions in each candidate alignment area includes:
从每个候选对准区域中多个滑动位置对应的第二相似度中，筛选出最大第二相似度；Filter out the maximum second similarity from the second similarities corresponding to multiple sliding positions in each candidate alignment area;
将每个候选对准区域对应的最大第二相似度确定为每个候选对准区域与第一轮廓图之间的第一相似度。The maximum second similarity corresponding to each candidate alignment area is determined as the first similarity between each candidate alignment area and the first contour map.
这里，第一相似度可以为候选对准区域对应的多个第二相似度中最大的第二相似度。最大第二相似度可以表示该滑动位置与第一轮廓图之间相似程度最大，也就是说最大相似度对应的滑动位置是候选对准区域内与第一轮廓图最相似的位置。Here, the first similarity may be the largest second similarity among multiple second similarities corresponding to the candidate alignment area. The maximum second similarity can indicate the maximum similarity between the sliding position and the first contour map. That is to say, the sliding position corresponding to the maximum similarity is the position most similar to the first contour map in the candidate alignment area.
在上述实施例中，针对每个候选对准区域，均筛选出每个候选对准区域内最大的第二相似度，并将每个候选对准区域内最大第二相似度作为各自对应的第一相似度。如此，可以确定出每个候选对准区域内分别与第一轮廓之间最相似的滑动位置。In the above embodiment, for each candidate alignment region, the maximum second similarity in each candidate alignment region is screened out, and the maximum second similarity in each candidate alignment region is used as the respective corresponding third similarity. One degree of similarity. In this way, the sliding position most similar to the first contour in each candidate alignment area can be determined.
在一些实施例中，S25，根据多个候选对准区域与第一轮廓图之间的第一相似度，确定目标对准结果，包括：In some embodiments, S25, determine the target alignment result based on the first similarity between the plurality of candidate alignment areas and the first contour map, including:
从多个候选对准区域与所述第一轮廓图之间的第一相似度中，筛选出最大第一相似度；Filter out the maximum first similarity from the first similarities between the plurality of candidate alignment regions and the first contour map;
在最大第一相似度大于预设阈值的情况下，确定对准成功，并将最大第一相似度对应的候选对准区域中对应的滑动位置确定为目标对准位置；When the maximum first similarity is greater than the preset threshold, it is determined that the alignment is successful, and the corresponding sliding position in the candidate alignment area corresponding to the maximum first similarity is determined as the target alignment position;
在最大第一相似度不大于预设阈值的情况下，确定对准失败。If the maximum first similarity is not greater than the preset threshold, it is determined that the alignment fails.
这里，最大第一相似度可以为多个第一相似度中最大的一个第一相似度。最大第一相似度可以表示多个候选对准区域与第一轮廓图中最大相似程度。预设阈值可以根据需求确定，如预设阈值可以为大于90％的任意自然数。Here, the maximum first similarity may be the largest first similarity among multiple first similarities. The maximum first similarity may represent the maximum degree of similarity between the multiple candidate alignment regions and the first contour map. The preset threshold can be determined according to requirements. For example, the preset threshold can be any natural number greater than 90%.
在本申请实施例中，为进一步提高对准的精准性，快速对准装置将最大第一相似度与预设阈值进行比较，并通过比较结果确定对准结果，即在最大第一相似度不大于预设阈值的情况下，确定对准失败。在在最大第一相似度大于预设阈值的情况下，确定对准成功，并将最大第一相似度对应的候选对准区域中对应的滑动位置确定为目标对准位置。图9示出本申请实施例提供的一种对准位置的示意图，如图9所示，虚线框所示区域为目标区域图中与第一轮廓图对准的滑动位置。In the embodiment of the present application, in order to further improve the accuracy of alignment, the rapid alignment device compares the maximum first similarity with a preset threshold, and determines the alignment result based on the comparison result, that is, when the maximum first similarity is not If it is greater than the preset threshold, it is determined that the alignment has failed. In the case where the maximum first similarity is greater than the preset threshold, it is determined that the alignment is successful, and the corresponding sliding position in the candidate alignment area corresponding to the maximum first similarity is determined as the target alignment position. Figure 9 shows a schematic diagram of an alignment position provided by an embodiment of the present application. As shown in Figure 9, the area shown in the dotted box is the sliding position aligned with the first contour map in the target area map.
在上述实施例中，首先从多个第一相似度中筛选出最大第一相似度，如此，可以初步确定多个候选区域内与第一轮廓图最匹配的滑动位置，并通过预设阈值，来判断最大第一相似度对应的滑动位置是否为第一轮廓图的对准位置。如此，相较于现有技术中会在滑动过程中根据预设阈值判断是否需要提前提前终止对准流程，所返回的对准结果极易受到阈值影响，且不能保证是全局最优对准位置而言，本申请可以通过在所有候选对准区域内进行更加精确的滑动对准，以使最准返回的对准位置是从全局相似度最大的位置产生，可以进一步提高对准的精准性，并且可以减少由于不合理的预设阈值导致对正确对准位置的误报或漏报。In the above embodiment, the maximum first similarity is first selected from multiple first similarities. In this way, the sliding position that best matches the first contour map in multiple candidate areas can be preliminarily determined, and through the preset threshold, To determine whether the sliding position corresponding to the maximum first similarity is the alignment position of the first contour map. In this way, compared with the existing technology, which determines whether the alignment process needs to be terminated in advance based on a preset threshold during the sliding process, the returned alignment result is easily affected by the threshold and cannot be guaranteed to be the global optimal alignment position. Specifically, this application can further improve the accuracy of alignment by performing more precise sliding alignment in all candidate alignment areas, so that the most accurate returned alignment position is generated from the position with the greatest global similarity. And it can reduce false positives or false negatives on correct alignment positions due to unreasonable preset thresholds.
为了进一步加深快速对准方法的理解，本申请实施例提供另一种快速对准方法，图10示出本申请实施例提供的另一种快速对准方法的流程示意图，如图10所示，该快速对准方法可以包括：In order to further deepen the understanding of the rapid alignment method, the embodiment of the present application provides another rapid alignment method. Figure 10 shows a schematic flow chart of another rapid alignment method provided by the embodiment of the present application. As shown in Figure 10, This quick alignment method can include:
S101，在指定位置采集SEM图像，对SEM图像进行轮廓提取并将SEM图轮廓图转化为与设计版图相同的格式；S101, collect SEM images at designated positions, extract the contours of the SEM images, and convert the SEM image contours into the same format as the design layout;
S102，根据采图精度在设计版图上确定一定大小的目标区域图；S102, determine a target area map of a certain size on the design layout based on the map acquisition accuracy;
S103，使用相同的特征提取算法分别对SEM图像轮廓图与目标区域图的图形特征进行提取；S103, use the same feature extraction algorithm to extract the graphic features of the SEM image contour map and the target area map respectively;
这里，图形特征可以为图形中各个多边形角点与质心所在的位置，多边形外接矩形的长宽比与相对位置，多边形的面积等。Here, the graphic features can be the positions of the corner points and centroids of each polygon in the graphic, the aspect ratio and relative position of the circumscribed rectangle of the polygon, the area of the polygon, etc.
S104，依据提取出的特征信息(即第一特征信息和第二特征信息)，通过特征匹配的方式将SEM图轮廓图与目标区域图进行初步对齐，并获得多个潜在的最终对准位置；S104, based on the extracted feature information (i.e., the first feature information and the second feature information), initially align the SEM image outline map and the target area map through feature matching, and obtain multiple potential final alignment positions;
这里，判断初步对齐的方式可以为以下方式至少之一：SEM图轮廓图形中多边形外接矩形与设计版图图形中多边形外接矩形的大小与相对位置要接近，各个多边形的质心所在位置分布接近等。Here, the method for judging the preliminary alignment can be at least one of the following methods: the size and relative position of the polygonal circumscribed rectangle in the SEM outline graphic and the polygonal circumscribed rectangle in the design layout graphic should be close, the location distribution of the centroid of each polygon should be close, etc.
S105，在所有潜在对准位置附近(即候选对准区域)进行更加精确的滑动对准操作，并在每个滑动位置计算SEM图像轮廓图与目标区域图的相似度，记录最大相似度与对应的滑动位置；S105, perform a more precise sliding alignment operation near all potential alignment positions (i.e., candidate alignment areas), calculate the similarity between the SEM image outline map and the target area map at each sliding position, and record the maximum similarity and correspondence the sliding position;
S106，判断最大相似度是否大于预设阈值，在大于的情况下，跳转S107，在不大于的情况下，跳转S108。S106: Determine whether the maximum similarity is greater than the preset threshold. If it is greater, jump to S107. If it is not greater, jump to S108.
S107，确定对准成功，返回对应的滑动位置作为最终对准位置；S107, determine that the alignment is successful, and return the corresponding sliding position as the final alignment position;
S108，确定对准失败。S108, it is determined that the alignment fails.
在上述实施例中，由于在对准前对SEM图像轮廓图形与设计版图图形进行了分析，通过使用SEM图像图形的特征信息来提前对设计版图中的潜在对准位置进行了筛选，相较现有技术通过在设计版图上逐帧滑动SEM图像图形，并在每一个滑动位置都计算相似度来说，本发明能避免在大部分位置进行的相似度计算，从而显著提高对准效率。In the above embodiment, since the SEM image outline pattern and the design layout pattern are analyzed before alignment, the potential alignment positions in the design layout are screened in advance by using the characteristic information of the SEM image pattern. Compared with the current situation, According to the technology, by sliding the SEM image graphics frame by frame on the design layout and calculating the similarity at each sliding position, the present invention can avoid the similarity calculation at most positions, thereby significantly improving the alignment efficiency.
同时，在计算相似度时，由于提前参考了图形特征信息，能保证在计算出的对准位置，不仅SEM图像图形与设计版图图形面积是接近的，而且SEM图像轮廓图形与设计版图图形的特征也是接近的，从而在一定程度上避免了对准位置的误报。At the same time, when calculating the similarity, since the graphic feature information is referenced in advance, it can be ensured that at the calculated alignment position, not only the area of the SEM image graphic and the design layout graphic are close, but also the characteristics of the SEM image outline graphic and the design layout graphic It is also close, thus avoiding false alarms in the alignment position to a certain extent.
另外，现有技术会在滑动过程中根据预设的阈值判断是否需要提前终止对准流程，所返回的对准结果极易受到阈值影响，且不能保证是全局最优对准位置。而本申请实施例能够在所有的潜在对准位置附近进行更加精确的滑动对准，最终返回的对准位置将从相似度最大的位置产生，提高了对准结果的准确性。In addition, the existing technology will determine whether the alignment process needs to be terminated early according to a preset threshold during the sliding process. The returned alignment result is easily affected by the threshold and cannot be guaranteed to be the global optimal alignment position. The embodiment of the present application can perform more precise sliding alignment near all potential alignment positions, and the final returned alignment position will be generated from the position with the greatest similarity, which improves the accuracy of the alignment results.
本申请实施例另一方面提供一种快速对准装置，图11示出本申请实施例提供的一种快速对准装置的结构示意图，如图所示，该快速对准装置可以包括；On the other hand, the embodiment of the present application provides a rapid alignment device. Figure 11 shows a schematic structural diagram of a rapid alignment device provided by the embodiment of the present application. As shown in the figure, the rapid alignment device may include;
区域图确定模块111，用于根据扫描电子显微镜图像，从设计版图中确定出目标区域图；The area map determination module 111 is used to determine the target area map from the design layout based on the scanning electron microscope image;
轮廓图得到模块112，用于对所述扫描电子显微镜图像进行处理，得到目标格式的第一轮廓图；The contour image obtaining module 112 is used to process the scanning electron microscope image and obtain the first contour image in the target format;
候选区域确定模块113，用于根据第一轮廓图的第一特征信息和目标区域图的第二特征信息，从所述目标区域图中确定出多个候选对准区域；The candidate area determination module 113 is configured to determine multiple candidate alignment areas from the target area map based on the first feature information of the first contour map and the second feature information of the target area map;
第一相似度计算模块114，用于分别计算多个所述候选对准区域与所述第一轮廓图之间的第一相似度；The first similarity calculation module 114 is configured to calculate first similarities between a plurality of candidate alignment areas and the first contour map respectively;
目标结果确定模块115，用于根据多个所述候选对准区域与所述第一轮廓图之间的第一相似度，确定目标对准结果。The target result determination module 115 is configured to determine a target alignment result according to a first similarity between a plurality of candidate alignment areas and the first contour map.
在上述实施例中，可以根据扫描电子显微镜图像，从设计版图确定出与对应的目标区域图，从而初步确定版图对准范围。通过对扫描电子显微镜图像进行处理，得到目标格式的第一轮廓图，从而将扫描电子显微镜图像转化为第一轮廓图像，便于后续进行对准操作。并且根据第一轮廓图的第一特征信息和目标区域图的第二特征信息，从目标区域图中确定出多个候选对准区域，如此，可以通过特征信息进行初步对准操作，可以从目标区域图中筛选出多个对准概率较大的候选对准区域，筛除无效区域，如此可以减少后续精对准操作中对无效位置进行相似操作计算，显著提高对准效率。以及，分别计算多个所述候选对准区域与所述第一轮廓图之间的第一相似度，根据多个所述候选对准区域与第一轮廓图之间的第一相似度，确定目标对准结果，从而可以通过滑动操作对每个候选区域进行相似度计算，以实现精对准操作，并且根据多个第一相似度来衡量目标对准结果，可以最大程度上保证对准结果的准确性。如此，通过初对齐和精准对齐两重对准操作，提高SEM图像与设计版图的对准精度和对准效率，达到精准且快速的对准效果。In the above embodiment, the corresponding target area map can be determined from the design layout based on the scanning electron microscope image, thereby preliminarily determining the layout alignment range. By processing the scanning electron microscope image, a first contour image in the target format is obtained, thereby converting the scanning electron microscope image into a first contour image to facilitate subsequent alignment operations. And according to the first feature information of the first contour map and the second feature information of the target area map, a plurality of candidate alignment areas are determined from the target area map. In this way, a preliminary alignment operation can be performed through the feature information, and the target area can be obtained from the target area map. In the area map, multiple candidate alignment areas with high alignment probabilities are screened out, and invalid areas are screened out. This can reduce the calculation of similar operations on invalid locations in subsequent fine alignment operations and significantly improve alignment efficiency. And, calculate first similarities between a plurality of candidate alignment regions and the first contour map respectively, and determine based on the first similarities between a plurality of candidate alignment regions and the first contour map. Target alignment results, so that similarity calculations can be performed on each candidate area through sliding operations to achieve precise alignment operations, and the target alignment results are measured based on multiple first similarities to ensure the alignment results to the greatest extent accuracy. In this way, through the dual alignment operations of initial alignment and precise alignment, the alignment accuracy and efficiency of the SEM image and the design layout are improved, and accurate and fast alignment results are achieved.
在一些实施例中，轮廓图得到模块112可以包括：In some embodiments, the contour map obtaining module 112 may include:
第二轮廓图得到子模块，用于对扫描电子显微镜图像进行轮廓提取，得到第二轮廓图；The second contour image obtaining submodule is used to extract the contour of the scanning electron microscope image to obtain the second contour image;
第一轮廓图得到子模块，用于对第二轮廓图进行格式转换，得到目标格式的第一轮廓图。The first contour image obtaining submodule is used to convert the format of the second contour image to obtain the first contour image in the target format.
在一些实施例中，第一相似度计算模块114可以包括：In some embodiments, the first similarity calculation module 114 may include:
第二相似度得到子模块，用于将预设的滑动窗口以预设步长在每个候选对准区域内进行滑动，计算每个滑动位置处滑动窗口覆盖的区域与第一轮廓图之间的相似度，以得到多个滑动位置与第一轮廓图之间的第二相似度；The second similarity obtaining submodule is used to slide the preset sliding window in each candidate alignment area at a preset step size, and calculate the difference between the area covered by the sliding window and the first contour map at each sliding position. The degree of similarity to obtain the second degree of similarity between the plurality of sliding positions and the first contour map;
第一相似度确定子模块，用于基于每个候选对准区域中多个滑动位置对应的第二相似度，确定每个候选对准区域与第一轮廓图之间的第一相似度。The first similarity determination sub-module is configured to determine the first similarity between each candidate alignment area and the first contour map based on the second similarity corresponding to the plurality of sliding positions in each candidate alignment area.
在一些实施例中，第一相似度确定子模块，可以包括：In some embodiments, the first similarity determination sub-module may include:
最大相似度筛选单元，用于从每个候选对准区域中多个滑动位置对应的第二相似度中，筛选出最大第二相似度；The maximum similarity screening unit is used to screen out the maximum second similarity from the second similarities corresponding to multiple sliding positions in each candidate alignment area;
第一相似度确定单元，用于将每个所述候选对准区域对应的最大第二相似度确定为每个所述候选对准区域与所述第一轮廓图之间的第一相似度。A first similarity determination unit is configured to determine the maximum second similarity corresponding to each candidate alignment area as the first similarity between each candidate alignment area and the first contour map.
在一些实施例中，目标结果确定模块115，可以包括：In some embodiments, the target result determination module 115 may include:
最大相似度筛选子模块，用于从多个候选对准区域与第一轮廓图之间的第一相似度中，筛选出最大第一相似度；The maximum similarity screening submodule is used to filter out the maximum first similarity from the first similarities between multiple candidate alignment areas and the first contour map;
成功确定子模块，用于在最大第一相似度大于预设阈值的情况下，确定对准成功，并将最大第一相似度对应的候选对准区域中对应的滑动位置确定为目标对准位置；Success determination sub-module, used to determine that the alignment is successful when the maximum first similarity is greater than a preset threshold, and determine the corresponding sliding position in the candidate alignment area corresponding to the maximum first similarity as the target alignment position ;
失败确定子模块，用于在最大第一相似度不大于预设阈值的情况下，确定对准失败。The failure determination submodule is used to determine alignment failure when the maximum first similarity is not greater than a preset threshold.
在一些实施例中，候选区域确定模块113可以包括：In some embodiments, the candidate area determination module 113 may include:
候选位置子模块，用于根据第一轮廓图的第一特征信息和目标区域图的第二特征信息，从目标区域图中确定出多个候选对准位置；The candidate position submodule is used to determine multiple candidate alignment positions from the target area map based on the first feature information of the first contour map and the second feature information of the target area map;
区域得到子模块，用于根据每个候选对准位置在目标区域图中的位置，确定每个候选对准位置对应的候选对准区域，以得到多个候选对准区域。The area obtaining submodule is used to determine the candidate alignment area corresponding to each candidate alignment position according to the position of each candidate alignment position in the target area map, so as to obtain multiple candidate alignment areas.
在一些实施例中，候选位置子模块具体可以用于通过特征匹配法，确定第二特征信息中与第一特征信息匹配的第三特征信息，并确定第三特征信息在目标区域图中所在的位置，并将第三特征信息对应的一个或多个位置作为候选对准位置。In some embodiments, the candidate position sub-module can be used to determine the third feature information in the second feature information that matches the first feature information through a feature matching method, and determine where the third feature information is located in the target area map. position, and use one or more positions corresponding to the third feature information as candidate alignment positions.
在一些实施例中，该快速对准装置还可以包括：In some embodiments, the rapid alignment device may also include:
特征分析模块，用于在根据第一轮廓图的第一特征信息和目标区域图的第二特征信息，从目标区域图中确定出多个候选对准位置之前，对所述第一轮廓图和所述目标区域图分别进行特征分析，得到第一特征信息和第二特征信息，第一特征信息和第二特征信息包括以下至少一种：多边形的角点位置、多边形的质心位置、多边形的外接矩形的长宽比与相对位置、多边形的面积。a feature analysis module, configured to analyze the first outline map and the target area map before determining a plurality of candidate alignment positions from the target area map according to the first feature information of the first outline map and the second feature information of the target area map. The target area map performs feature analysis respectively to obtain first feature information and second feature information. The first feature information and the second feature information include at least one of the following: the corner point position of the polygon, the centroid position of the polygon, and the circumference of the polygon. Aspect ratio and relative position of rectangle, area of polygon.
应理解，本文中前述关于本申请的方法所描述的具体特征、操作和细节也可类似地应用于本申请的装置和系统，或者，反之亦然。另外，上文描述的本申请的方法的每个步骤可由本申请的装置或系统的相应部件或单元执行。It should be understood that the specific features, operations, and details previously described herein with respect to the methods of the present application may be similarly applied to the devices and systems of the present application, or vice versa. In addition, each step of the method of the present application described above can be performed by the corresponding component or unit of the device or system of the present application.
应理解，本申请的装置的各个模块/单元可全部或部分地通过软件、硬件、固件或其组合来实现。各模块/单元各自可以硬件或固件形式内嵌于电子设备的处理器中或独立于处理器，也可以软件形式存储于电子设备的存储器中以供处理器调用来执行各模块/单元的操作。各模块/单元各自可以实现为独立的部件或模块，或者两个或更多个模块/单元可实现为单个部件或模块。It should be understood that each module/unit of the device of the present application can be implemented in whole or in part by software, hardware, firmware or a combination thereof. Each module/unit can be embedded in the processor of the electronic device or independent of the processor in the form of hardware or firmware, or can be stored in the memory of the electronic device in the form of software for the processor to call to execute the operations of each module/unit. Each module/unit may be implemented as a separate component or module, or two or more modules/units may be implemented as a single component or module.
本申请实施例又一方面，提供了一种电子设备。图12示出本申请实施例提供的一种电子设备的结构示意图，如图12所示，电子设备120包括处理器121以及存储有计算机程序指令的存储器122。其中，处理器121执行计算机程序指令时实现上述的快速对准方法的各步骤。该电子设备可以广义地为服务器、终端，或任何其他具有必要的计算和/或处理能力的电子设备。In yet another aspect, embodiments of the present application provide an electronic device. Figure 12 shows a schematic structural diagram of an electronic device provided by an embodiment of the present application. As shown in Figure 12, the electronic device 120 includes a processor 121 and a memory 122 storing computer program instructions. When the processor 121 executes the computer program instructions, the steps of the above-mentioned fast alignment method are implemented. The electronic device may broadly be a server, terminal, or any other electronic device with necessary computing and/or processing capabilities.
在一个实施例中，该电子设备120可包括通过系统总线连接的处理器、存储器、网络接口、通信接口等。该电子设备的处理器可用于提供必要的计算、处理和/或控制能力。该电子设备120的存储器可包括非易失性存储介质和内存储器。该非易失性存储介质可存储有操作系统、计算机程序等。该内存储器可为非易失性存储介质中的操作系统和计算机程序的运行提供环境。该电子设备120的网络接口和通信接口可用于与外部的设备通过网络连接和通信。该计算机程序被处理器执行时执行本申请的快速对准方法的步骤。In one embodiment, the electronic device 120 may include a processor, a memory, a network interface, a communication interface, etc. connected through a system bus. The electronic device's processor may be used to provide the necessary computing, processing and/or control capabilities. The memory of the electronic device 120 may include non-volatile storage media and internal memory. The non-volatile storage medium can store operating systems, computer programs, etc. This internal memory provides an environment for the execution of operating systems and computer programs in non-volatile storage media. The network interface and communication interface of the electronic device 120 can be used to connect and communicate with external devices through the network. The computer program performs the steps of the rapid alignment method of the present application when executed by the processor.
本申请提供了一种计算机可读存储介质，计算机可读存储介质上存储有快速对准程序，快速对准程序被处理器执行时实现上述任一实施例提供的快速对准方法的步骤。The present application provides a computer-readable storage medium. A fast alignment program is stored on the computer-readable storage medium. When the fast alignment program is executed by a processor, the steps of the fast alignment method provided by any of the above embodiments are implemented.
本领域的技术人员可以理解，本申请的方法步骤可以通过计算机程序来指示相关的硬件如电子设备或处理器完成，计算机程序可存储于非暂时性计算机可读存储介质中，该计算机程序被执行时导致本申请的步骤被执行。根据情况，本文中对存储器、存储或其它介质的任何引用可包括非易失性或易失性存储器。非易失性存储器的示例包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)、闪存、磁带、软盘、磁光数据存储装置、光学数据存储装置、硬盘、固态盘等。易失性存储器的示例包括随机存取存储器(RAM)、外部高速缓冲存储器等。Those skilled in the art can understand that the method steps of the present application can be completed by instructing related hardware such as electronic devices or processors through a computer program. The computer program can be stored in a non-transitory computer-readable storage medium, and the computer program is executed. when the steps leading to this application are performed. Any reference herein to memory, storage, or other media may include non-volatile or volatile memory, as appropriate. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data Storage devices, optical data storage devices, hard drives, solid state drives, etc. Examples of volatile memory include random access memory (RAM), external cache memory, and the like.
以上描述的各技术特征可以任意地组合。尽管未对这些技术特征的所有可能组合进行描述，但这些技术特征的任何组合都应当被认为由本说明书涵盖，只要这样的组合不存在矛盾。The technical features described above can be combined arbitrarily. Although not all possible combinations of these technical features have been described, any combination of these technical features should be considered to be covered by this specification, as long as there is no contradiction in such combinations.
最后应说明的是：以上各实施例仅用以说明本申请的技术方案，而非对其限制；尽管参照前述各实施例对本申请进行了详细的说明，本领域的技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分或者全部技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的范围。Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present application, but not to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: The technical solutions described in the foregoing embodiments may be modified, or some or all of the technical features may be equivalently replaced; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to depart from the scope of the technical solutions of the embodiments of the present application. .
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311148803.7ACN117252909A (en) | 2023-09-06 | 2023-09-06 | Quick alignment method, device, equipment and storage medium |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311148803.7ACN117252909A (en) | 2023-09-06 | 2023-09-06 | Quick alignment method, device, equipment and storage medium |
| Publication Number | Publication Date |
|---|---|
| CN117252909Atrue CN117252909A (en) | 2023-12-19 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311148803.7APendingCN117252909A (en) | 2023-09-06 | 2023-09-06 | Quick alignment method, device, equipment and storage medium |
| Country | Link |
|---|---|
| CN (1) | CN117252909A (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119624956A (en)* | 2025-02-12 | 2025-03-14 | 华芯程(杭州)科技有限公司 | Method, device, medium, program product and terminal for determining similarity of curved mask layout |
| CN119887519A (en)* | 2025-03-27 | 2025-04-25 | 合肥国镜仪器科技有限公司 | Image stitching method and device for scanning electron microscope, electronic equipment and storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090039263A1 (en)* | 2007-08-09 | 2009-02-12 | Ryoichi Matsuoka | Pattern measurement apparatus |
| US20150371377A1 (en)* | 2014-06-20 | 2015-12-24 | Taiwan Semiconductor Manufacturing Co., Ltd. | Method and system for inspection of a patterned structure |
| US20210208507A1 (en)* | 2018-06-04 | 2021-07-08 | Asml Netherlands B.V. | Method for improving a process for a patterning process |
| WO2022052303A1 (en)* | 2020-09-14 | 2022-03-17 | 中国科学院深圳先进技术研究院 | Method, apparatus and device for registering ultrasound image and ct image |
| CN115690064A (en)* | 2022-11-09 | 2023-02-03 | 东方晶源微电子科技（北京）有限公司 | Alignment method, device, electronic device and computer readable storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090039263A1 (en)* | 2007-08-09 | 2009-02-12 | Ryoichi Matsuoka | Pattern measurement apparatus |
| US20150371377A1 (en)* | 2014-06-20 | 2015-12-24 | Taiwan Semiconductor Manufacturing Co., Ltd. | Method and system for inspection of a patterned structure |
| US20210208507A1 (en)* | 2018-06-04 | 2021-07-08 | Asml Netherlands B.V. | Method for improving a process for a patterning process |
| WO2022052303A1 (en)* | 2020-09-14 | 2022-03-17 | 中国科学院深圳先进技术研究院 | Method, apparatus and device for registering ultrasound image and ct image |
| CN115690064A (en)* | 2022-11-09 | 2023-02-03 | 东方晶源微电子科技（北京）有限公司 | Alignment method, device, electronic device and computer readable storage medium |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119624956A (en)* | 2025-02-12 | 2025-03-14 | 华芯程(杭州)科技有限公司 | Method, device, medium, program product and terminal for determining similarity of curved mask layout |
| CN119887519A (en)* | 2025-03-27 | 2025-04-25 | 合肥国镜仪器科技有限公司 | Image stitching method and device for scanning electron microscope, electronic equipment and storage medium |
| Publication | Publication Date | Title |
|---|---|---|
| CN117252909A (en) | Quick alignment method, device, equipment and storage medium | |
| CN111679303B (en) | A comprehensive positioning method and device for multi-source positioning information fusion | |
| WO2021196698A1 (en) | Method, apparatus and device for determining reserve of object to be detected, and medium | |
| CN114529837A (en) | Building outline extraction method, system, computer equipment and storage medium | |
| US10762272B2 (en) | Pattern density analysis method | |
| CN110211200B (en) | Dental arch wire generating method and system based on neural network technology | |
| WO2023130664A1 (en) | Angiography image analysis method and apparatus | |
| CN118135261B (en) | Graph matching method and system for ultra-large scale layout | |
| WO2024125434A1 (en) | Regional-consistency-based building principal angle correction method | |
| WO2024130877A1 (en) | High-precision scanning electron microscope image contour extraction method and apparatus, and device | |
| WO2024130878A1 (en) | Scanning electron microscope image contour extraction method and apparatus based on design layout | |
| WO2024108833A1 (en) | Design layout-based scanning electron microscope image defect classification method and apparatus | |
| CN115830049B (en) | Corner point detection method and device | |
| CN108764343B (en) | Method for positioning tracking target frame in tracking algorithm | |
| WO2022193521A1 (en) | Defect characterization method and apparatus | |
| CN112258536B (en) | An integrated positioning and segmentation method of the corpus callosum and cerebellar vermis | |
| CN118429275A (en) | A solder joint defect detection method, device, electronic device and storage medium | |
| CN114677743A (en) | Face rectification method, device, computer equipment and storage medium | |
| CN113160258A (en) | Method, system, server and storage medium for extracting building vector polygon | |
| CN113421278B (en) | Range detection method, device, equipment and storage medium based on edge detection | |
| CN113450311B (en) | Defect detection method and system for screw with pin based on semantic segmentation and spatial relationship | |
| CN115965572B (en) | A method for detecting appearance defects of three-stage tubes based on template comparison | |
| US20250182239A1 (en) | Curvilinear polygon image scaling method, system and electronic apparatus | |
| CN118657816A (en) | A tunnel disease change detection method and system | |
| CN120147629A (en) | Training image processing method, recognition method, related equipment and storage medium |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |