Photoetching plate detection method and system based on CAD (Computer Aided Design) generated mask

Abstract

The invention discloses a photoetching plate detection method and system based on a CAD generated mask, and the method comprises the steps: splicing all local images to form a complete picture, and obtaining a template drawing; reading a CAD profile drawing, and performing affine transformation on the CAD profile drawing according to a matching point selected transformation area corresponding template drawing to obtain a CAD mapping effect drawing; correspondingly generating a standard mask binary image from the CAD mapping effect image according to the inclusion relation among the contour lines in the CAD contour image; identifying a mark area of the template drawing to create a matching template; matching a mark area in a detection image, and performing affine transformation on the standard mask binary image into the detection image according to a matching result to obtain a comparison difference image; and carrying out difference processing on the corresponding contours in the comparison difference graph so as to judge the defect type. According to the method, the detection universality is effectively improved, and the defect type is judged through affine transformation processing and difference processing, so that the detection effect is better.

Description

Technical Field

[0001] The present invention relates to the technical field of semiconductor integrated circuit manufacturing, and in particular to a photomask detection method and system based on CAD-generated masks. Background Art

[0002] The manufacturing process for semiconductor integrated circuits (ICs), or semiconductor chips, involves multiple steps, including material preparation, platemaking, photolithography, cleaning, etching, doping, and chemical mechanical polishing. The photolithography process is particularly critical. The photolithography process requires a complete set (several or up to a dozen) of photoetching masks, known as photomasks, that are precisely aligned with one another and have specific geometric patterns. The photomask is essentially the "print negative" of the photoresist (commonly known as photoresist, also known as photoresist) layer used in the photolithography process, onto which the geometric patterns of the original integrated circuit design are printed. In other words, the transition from the original integrated circuit design to the formation of the circuit pattern on the wafer requires platemaking, which involves the production of a set of photomasks, each bearing the original integrated circuit design pattern, as the "print negative." The photolithography process involves transferring the geometric patterns from this "print negative" to the wafer, forming the circuit pattern on the wafer.

[0003] The photomask making process is as follows: First, a photosensitive material, chromium nitride-chromium oxynitride, is deposited on a smooth, flat glass (or quartz) substrate via DC magnetron sputtering to form a chromium film substrate. Next, a layer of photoresist or electron beam resist is evenly coated on the chromium film substrate to form a chrome plate. This chrome plate is the photomask substrate, an ideal photosensitive blank for producing miniature geometric patterns. Finally, a miniature geometric pattern, derived from the original integrated circuit design, is printed on the photomask substrate via a photolithography process, completing the photomask making process. Each miniature geometric pattern on the photomask corresponds to an original integrated circuit design layout, and this miniature geometric pattern is called a mask pattern. In this way, the photomask is printed with millions of mask patterns that are completely identical to the original integrated circuit design layout.

[0004] The chip manufacturing process often involves dozens or even millions of photolithography steps, each of which requires a photomask. The quality of each photomask directly impacts the quality of the photolithography patterns on the wafer, and thus the chip yield. Therefore, the mask pattern on the photomask must be intact to fully represent the original integrated circuit design. Transferring an incomplete mask pattern to the wafer will result in substandard wafers, making defect detection on photomasks particularly important.

[0005] Traditional photolithography mask inspection includes morphological analysis and template subtraction methods. The morphological analysis method is difficult to complete the analysis and inspection of complex patterns and has poor applicability, while the template subtraction method is difficult to be compatible with product color differences and small pattern differences, and therefore cannot meet the inspection needs of large-scale integrated circuits. Summary of the Invention

[0006] In order to overcome the deficiencies of the prior art, the present invention aims to provide a method and system for detecting a photoresist plate based on a CAD-generated mask, which has the advantages of good versatility and strong compatibility.

[0007] The purpose of the present invention is achieved by adopting the following technical solutions: According to a first aspect of an embodiment of the present disclosure, a method for inspecting a reticle based on a CAD-generated mask is provided, comprising: According to a predetermined splicing rule, the acquired partial images are spliced ​​together to form a complete image to obtain a template image; Reading a CAD contour image corresponding to the photoresist plate to be tested, and performing an affine transformation on the CAD contour image according to the template image corresponding to the transformation area selected by the matching points to obtain a CAD mapping effect image; Generate a standard mask binary image corresponding to the CAD mapping effect image according to the inclusion relationship between the contour lines in the CAD contour image; Identifying a mark area of ​​the template image to create a matching template; Matching the mark area in the detection image acquired in real time, and affine transforming the standard mask binary image into the detection image according to the matching result so that the two completely overlap to obtain a comparison difference image; The corresponding contours in the comparison difference image are subjected to difference processing to determine the defect type.

[0008] To implement the above technical solution, since a standard mask binary image is generated by accessing a CAD contour image, the requirements for the template image are relatively low. When there are small differences in the image, single-area adaptation can also be achieved, which has high flexibility. At the same time, it can adapt to the analysis and detection of complex patterns, improve the versatility of detection, and determine the defect type through affine transformation processing and difference processing, so as to achieve better detection effect.

[0009] In some exemplary embodiments, the step of stitching the acquired partial images into a complete image according to a predetermined stitching rule to obtain a template image specifically includes: Obtain all product partial images in order from top to bottom or from left to right; Identify the edge positions of the product parts in each product part image to determine the splicing parts; According to the position order of the product partial diagram, each splicing part is spliced ​​together to form a complete picture to obtain a template diagram.

[0010] Implementing the above technical solution makes the spliced ​​template image more accurate.

[0011] In some exemplary embodiments, performing affine transformation on the CAD contour image according to the selected transformation area corresponding to the template image based on the matching points to obtain the CAD mapping effect image specifically includes: Determining a corresponding matching point on the CAD outline drawing and the template drawing respectively; Selecting a first transformation area and a second transformation area on the CAD contour image and the template image respectively based on the matching points for mapping matching; Affine transformation processing is performed on the CAD contour image so that the first transformation area and the second transformation area are completely mapped and corresponded to obtain a CAD mapping effect image, wherein the affine transformation processing includes scaling transformation, rotation transformation and translation transformation.

[0012] Implement the above technical solution to achieve mutual mapping between the CAD outline drawing and the template drawing.

[0013] In some exemplary embodiments, when generating a standard mask binary image corresponding to the CAD mapping effect image according to the inclusion relationship between the contour lines in the CAD contour image: The contour levels are divided according to the inclusion relationship between the contour lines in the CAD contour image to determine the background lines and foreground lines, and then the CAD contour effect image is correspondingly generated into a standard mask binary image according to the background lines and foreground lines.

[0014] Implementing the above technical solution improves the accuracy of generating the standard mask binary image.

[0015] In some exemplary embodiments, identifying the mark area of ​​the template image to create a matching template specifically includes: The corresponding recognition pattern set on the photolithography plate is used as the mark area, the corresponding recognition pattern on the template image is recognized to determine the mark area of ​​the template image, and a matching template is created based on the template image and the mark area.

[0016] In some exemplary embodiments, the detection image is obtained by stitching together reticle images captured in real time during the detection process.

[0017] In some exemplary embodiments, when performing subtraction processing on the corresponding contours in the comparison subtraction image to determine the defect type, the subtraction area is highlighted.

[0018] Implementing the above technical solution makes defect judgment more convenient and accurate.

[0019] According to a second aspect of an embodiment of the present disclosure, a photomask inspection system based on CAD-generated masks is provided, comprising: A template stitching unit is used to stitch the acquired partial images together according to a predetermined stitching rule to form a complete image to obtain a template image; A mapping processing unit is used to read a CAD contour image corresponding to the photoresist plate to be tested, and perform an affine transformation on the CAD contour image according to the template image corresponding to the transformation area selected by the matching points to obtain a CAD mapping effect image; A mask generating unit, configured to generate a standard mask binary image corresponding to the CAD mapping effect image according to the inclusion relationship between the contour lines in the CAD contour image; an identification and creation unit, configured to identify a mark area of ​​the template image to create a matching template; A matching mapping unit is used to match the mark area in the detection image obtained in real time, and according to the matching result, affine transform the standard mask binary image into the detection image so that the two completely overlap to obtain a comparison difference image; The defect judgment unit is used to perform difference processing on the corresponding contours in the comparison difference image to judge the defect type.

[0020] According to a third aspect of an embodiment of the present disclosure, a computer device is provided, comprising a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the photolithography plate detection method for generating a mask based on CAD as described in the first aspect.

[0021] According to a fourth aspect of an embodiment of the present disclosure, a storage medium storing computer-readable instructions is provided. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the photolithography plate detection method for generating a mask based on CAD as described in the first aspect.

[0022] In summary, compared with the prior art, the present invention has the following beneficial effects: An embodiment of the present invention provides a photomask detection method and system based on CAD-generated masks, wherein the method includes: splicing acquired local images into a complete image according to predetermined splicing rules to obtain a template image; reading a CAD contour image corresponding to the photomask to be tested, and performing an affine transformation on the CAD contour image according to a selected transformation area corresponding to the template image based on matching points to obtain a CAD mapping effect image; generating a standard mask binary image corresponding to the CAD mapping effect image according to the inclusion relationship between the contour lines in the CAD contour image; identifying a mark area of ​​the template image to create a matching template; matching the mark area in a detection image acquired in real time, and performing an affine transformation on the standard mask binary image into the detection image according to the matching result so that the two completely overlap to obtain a comparison difference image; performing difference processing on the corresponding contours in the comparison difference image to determine the defect type. Since the standard mask binary image is generated by accessing the CAD contour image, the requirements for the template image are relatively low. When there are small differences in the image, single-area adaptation can also be achieved, which has high flexibility. At the same time, it can adapt to the analysis and detection of complex patterns, improve the versatility of detection, and judge the defect type through affine transformation processing and difference processing, so as to achieve better detection effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 4 is a flow chart of a method for detecting a photoresist plate based on a CAD-generated mask according to an embodiment of the present invention.

[0024] Figure 2 This is a partial image of a product obtained in a photomask inspection method based on CAD-generated mask in an embodiment of the present invention.

[0025] Figure 3 This is a template image that has been spliced ​​together in a photomask inspection method based on CAD-generated masks in an embodiment of the present invention.

[0026] Figure 4 The CAD outline map and template map of the selected transformation area in the reticle inspection method based on CAD-generated mask in an embodiment of the present invention are shown.

[0027] Figure 5 This is a diagram showing the effect of a local CAD mapping in a photomask inspection method based on CAD generation in an embodiment of the present invention.

[0028] Figure 6 It is a local CAD outline diagram of a specific example of the photomask inspection method based on CAD generation of a mask in an embodiment of the present invention.

[0029] Figure 7 This is a comparison diagram of a standard mask binary image and a template image in a photoresist inspection method based on CAD-generated mask according to an embodiment of the present invention.

[0030] Figure 8 This is the mark area position and mark local map in the photomask inspection method based on CAD generated mask in an embodiment of the present invention.

[0031] Figure 9 This is a comparison diagram for a photomask inspection method based on CAD-generated masks according to an embodiment of the present invention.

[0032] Figure 10 This is a diagram showing the effect of the difference area in the photomask inspection method based on CAD generated mask in an embodiment of the present invention.

[0033] Figure 11 This is the full-image detection effect in the photomask detection method based on CAD-generated masks in an embodiment of the present invention.

[0034] Figure 12 This is a diagram showing a partial inspection effect in a photomask inspection method based on CAD-generated masks according to an embodiment of the present invention.

[0035] Figure 13 This is another partial inspection effect diagram of the photomask inspection method based on CAD-generated mask in an embodiment of the present invention.

[0036] Figure 14 Schematic diagram of the structure of a photoresist inspection system based on CAD-generated masks in an embodiment of the present invention.

[0037] Figure 15 2 is a basic structural block diagram of a computer device in an embodiment of the present invention.

[0038] The numbers and letters in the figure represent the corresponding component names: 10. Template splicing unit; 20. Mapping processing unit; 30. Mask generation unit; 40. Identification creation unit; 50. Matching mapping unit; 60. Defect judgment unit. DETAILED DESCRIPTION

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0040] like Figure 1 As shown, the first aspect of the present invention provides a method for detecting a photomask based on a CAD-generated mask, comprising: S100: splicing the acquired partial images into a complete image according to a predetermined splicing rule to obtain a template image.

[0041] Specifically, step S100 includes: S101. Obtain all product partial images in sequence according to the position order of the products from top to bottom or from left to right. It can be understood that since each product partial image shows a part of the product, obtaining the product partial images in sequence can make the splicing process more convenient. In actual operation, it is not limited to first from top to bottom or from left to right. For example, it can be considered that the completed template image includes multiple product partial images distributed in an array. When obtaining product partial images, you can first obtain the first row of product partial images at the top in sequence from left to right, and then obtain the second row and the third row in sequence until all product partial images are obtained. You can also first obtain the first column of product partial images at the leftmost in sequence from top to bottom, and then obtain the second column and the third column as needed, until all product partial images are obtained. At the same time, in some embodiments, each product partial image is usually numbered as needed to facilitate the sorting of product partial images. The obtained product partial images are as follows: Figure 2 shown.

[0042] S102. Identify the edge positions of the product parts in each product partial image to determine the splicing parts. During splicing, it is sufficient to ensure that the corresponding edge positions are spliced. If there is a certain range of repeated areas at the edge positions, the repeated areas can be completely overlapped. Therefore, determining the edge positions can provide a basis for the splicing process and make the spliced ​​template image more accurate.

[0043] S103, according to the position order of the product partial map, each splicing part is spliced ​​together to form a complete picture to obtain a template map, and the splicing parts can be completely aligned during splicing. The template map obtained by splicing is as follows: Figure 3 shown.

[0044] S200, reading a CAD contour image corresponding to the photoresist plate to be tested, and performing an affine transformation on the CAD contour image according to a template image corresponding to a transformation region selected by matching points to obtain a CAD mapping effect image; Specifically, step S200 includes: S201. Determine a corresponding matching point on the CAD contour image and the template image respectively. The selection of the matching point can be random, as long as the matching point on the CAD contour image and the template image is guaranteed to be corresponding.

[0045] S202, based on the matching points, select a first transformation area and a second transformation area on the CAD outline image and the template image respectively for mapping matching, and the CAD outline image and the template image of the selected transformation area are as follows: Figure 4 shown.

[0046] S203, performing affine transformation on the CAD outline drawing so that the first transformation area and the second transformation area are completely mapped to each other to obtain a CAD mapping effect drawing, wherein the affine transformation includes scaling transformation, rotation transformation and translation transformation. The ultimate goal is to make the size, angle and position of the CAD outline drawing consistent with the template drawing, realize mutual mapping between the CAD outline drawing and the template drawing, and establish a connection between the two. For details of the CAD mapping effect drawing, please refer to Figure 5 , Figure 5 A local CAD mapping rendering is shown.

[0047] S300 , generating a standard mask binary image corresponding to the CAD mapping effect image according to the inclusion relationship between the contour lines in the CAD contour image.

[0048] Specifically, the contour levels are first divided according to the inclusion relationship between the contour lines in the CAD contour image to determine the background line and the foreground line, for example Figure 6 As shown, Figure 6 A specific example of a local CAD contour drawing is shown, where the yellow contour contains a red contour line and a surrounding small circle contour. In this case, the yellow contour line can be used as the background line, while the inner red contour line and the surrounding small circle contour belong to the parallel contour level and can be used as the foreground line. Then, the CAD contour effect image is correspondingly generated into a standard mask binary image according to the background line and the foreground line, thereby improving the accuracy of generating the standard mask binary image. The comparison diagram between the standard mask binary image and the template image is shown in FIG. Figure 7 As shown, Figure 7 The left part is the template image and the right part is the standard mask binary image.

[0049] S400, identifying the mark area of ​​the template image to create a matching template, which is specifically: using the corresponding recognition pattern set on the photomask as the mark area, identifying the corresponding recognition pattern on the template image to determine the mark area of ​​the template image, and creating a matching template based on the mark area according to the template image, wherein the recognition pattern is set at a fixed position on the photomask, and the mark area position and the mark local image are as follows: Figure 8 shown.

[0050] S500, match the mark area in the real-time detection image, and according to the matching result, affine transform the standard mask binary image into the detection image so that the two completely overlap to obtain a comparison difference image, wherein the detection image is obtained by splicing the reticle image taken in real time during the detection process. The splicing process is similar to that of the template image and will not be described in detail here. The comparison difference image is as follows: Figure 9 As shown, Figure 9 The red outline is the standard outline and the green outline is the actual outline.

[0051] S600, perform subtraction processing on the corresponding contours in the comparison subtraction image to determine the defect type, and usually highlight the subtraction area to make defect judgment more convenient and accurate. The subtraction area effect diagram is as follows: Figure 10 shown.

[0052] The defect type can be customized according to the needs. For example, when the dot pattern is missing, the defect type can be determined as a circular defect. When the background area is abnormal, the defect type can be determined as a pitting defect. The specific full-image detection effect is as follows: Figure 11 As shown, the obvious colored part is the defect position after the difference processing. In order to further demonstrate the defect detection effect, Figure 12 shows one of the local detection effect diagrams, Figure 13 FIG. 2 is another diagram showing the effect of local detection.

[0053] In the present invention, since a standard mask binary image is generated by accessing a CAD contour image, the requirements for the template image are relatively low. When there are slight differences in the image, single-area adaptation can also be achieved, which has high flexibility. At the same time, it can adapt to the analysis and detection of complex patterns, thereby improving the versatility of detection. The defect type is determined by affine transformation processing and difference processing, resulting in better detection results.

[0054] According to a second aspect of the embodiment of the present disclosure, a photoresist plate detection system based on CAD generated mask is provided, such as Figure 14 As shown, it includes: a template splicing unit 10, which is used to splice the acquired local images into a complete picture according to a predetermined splicing rule to obtain a template image; a mapping processing unit 20, which is used to read the CAD contour image corresponding to the photoresist to be tested, and perform affine transformation on the CAD contour image according to the transformation area selected by the matching point corresponding to the template image to obtain a CAD mapping effect image; a mask generation unit 30, which is used to generate a standard mask binary image corresponding to the CAD mapping effect image according to the inclusion relationship between the contour lines in the CAD contour image; an identification creation unit 40, which is used to identify the mark area of ​​the template image to create a matching template; a matching mapping unit 50, which is used to match the mark area in the detection image acquired in real time, and perform affine transformation on the standard mask binary image into the detection image according to the matching result so that the two completely overlap to obtain a comparison difference image; and a defect judgment unit 60, which is used to perform difference processing on the corresponding contour in the comparison difference image to determine the defect type.

[0055] The third aspect of the present invention also provides a computer device. Figure 15 , Figure 15 This is a basic structural block diagram of the computer device in this embodiment.

[0056] like Figure 15As shown, a schematic diagram of the internal structure of a computer device. The computer device includes a processor, a non-volatile storage medium, a memory and a network interface connected via a system bus. The non-volatile storage medium of the computer device stores an operating system, a database and computer-readable instructions, and the database may store a control information sequence. When the computer-readable instructions are executed by the processor, the processor may implement a photoresist detection method based on CAD-generated masks. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor may execute a photoresist detection method based on CAD-generated masks. The network interface of the computer device is used to connect and communicate with a terminal. Those skilled in the art will understand that Figure 15 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0057] In this embodiment, the processor is used to execute Figure 14 The specific functions of the template splicing unit 10, mapping processing unit 20, mask generation unit 30, identification creation unit 40, matching mapping unit 50, and defect judgment unit 60 are described in detail. The memory stores the program code and various data required to execute these modules. The network interface is used to transmit data to user terminals or servers. The server can call the server's program code and data to execute the functions of all submodules.

[0058] The present invention also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the photoresist plate detection method for generating a mask based on CAD in any of the above embodiments.

[0059] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed, the program can include the processes in the above-described method embodiments. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0060] The above embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patented invention. It should be noted that those skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention. These variations and improvements are equivalent modifications and improvements to the above embodiments based on the essential technology of the present invention and fall within the scope of protection of the present invention.

Claims

1. A method for detecting a photomask based on a CAD-generated mask, characterized in that: include: According to a predetermined splicing rule, the acquired partial images are spliced ​​together to form a complete image to obtain a template image; Reading a CAD contour image corresponding to the photoresist plate to be tested, and performing an affine transformation on the CAD contour image according to the template image corresponding to the transformation area selected by the matching points to obtain a CAD mapping effect image; Generate a standard mask binary image corresponding to the CAD mapping effect image according to the inclusion relationship between the contour lines in the CAD contour image; Identifying a mark area of ​​the template image to create a matching template; Matching the mark area in the detection image acquired in real time, and affine transforming the standard mask binary image into the detection image according to the matching result so that the two completely overlap to obtain a comparison difference image; The corresponding contours in the comparison difference image are subjected to difference processing to determine the defect type.

2. The method for detecting a photoresist plate based on a CAD-generated mask according to claim 1, wherein: The step of stitching the acquired partial images together according to a predetermined stitching rule to form a complete image to obtain a template image specifically includes: Obtain all product partial images in order from top to bottom or from left to right; Identify the edge positions of the product parts in each product part image to determine the splicing parts; According to the position order of the product partial diagram, each splicing part is spliced ​​together to form a complete picture to obtain a template diagram.

3. The method for detecting a photoresist plate based on a CAD-generated mask according to claim 1 or 2, wherein: The step of performing affine transformation on the CAD contour image according to the selected transformation area corresponding to the template image according to the matching points to obtain the CAD mapping effect image specifically includes: Determining a corresponding matching point on the CAD outline drawing and the template drawing respectively; Selecting a first transformation area and a second transformation area on the CAD contour image and the template image respectively based on the matching points for mapping matching; Affine transformation processing is performed on the CAD contour image so that the first transformation area and the second transformation area are completely mapped and corresponded to obtain a CAD mapping effect image, wherein the affine transformation processing includes scaling transformation, rotation transformation and translation transformation.

4. The method for detecting a photoresist plate based on a CAD-generated mask according to claim 3, wherein: When the CAD mapping effect diagram is correspondingly generated into a standard mask binary diagram according to the inclusion relationship between the contour lines in the CAD contour diagram: The contour levels are divided according to the inclusion relationship between the contour lines in the CAD contour image to determine the background lines and foreground lines, and then the CAD contour effect image is correspondingly generated into a standard mask binary image according to the background lines and foreground lines.

5. The method for detecting a photoresist plate based on a CAD-generated mask according to claim 4, wherein: The identifying the mark area of ​​the template image to create a matching template specifically includes: The corresponding recognition pattern set on the photolithography plate is used as the mark area, the corresponding recognition pattern on the template image is recognized to determine the mark area of ​​the template image, and a matching template is created based on the template image and the mark area.

6. The method for detecting a photoresist plate based on a CAD-generated mask according to claim 1, wherein: The detection image is obtained by splicing the photoresist images taken in real time during the detection process.

7. The method for detecting a photoresist plate based on a CAD-generated mask according to claim 1, wherein: When performing subtraction processing on the corresponding contours in the comparison subtraction image to determine the defect type, the subtraction area is highlighted.

8. A photomask inspection system based on CAD-generated masks, characterized in that: include: A template stitching unit is used to stitch the acquired partial images together according to a predetermined stitching rule to form a complete image to obtain a template image; A mapping processing unit is used to read a CAD contour image corresponding to the photoresist plate to be tested, and perform an affine transformation on the CAD contour image according to the template image corresponding to the transformation area selected by the matching points to obtain a CAD mapping effect image; A mask generating unit, configured to generate a standard mask binary image corresponding to the CAD mapping effect image according to the inclusion relationship between the contour lines in the CAD contour image; an identification and creation unit, configured to identify a mark area of ​​the template image to create a matching template; A matching mapping unit is used to match the mark area in the detection image obtained in real time, and according to the matching result, affine transform the standard mask binary image into the detection image so that the two completely overlap to obtain a comparison difference image; The defect judgment unit is used to perform difference processing on the corresponding contours in the comparison difference image to judge the defect type.

9. A computer device comprising a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor performs the steps of the photomask detection method based on CAD-generated masks as described in any one of claims 1 to 7.

10. A storage medium storing computer-readable instructions, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors are caused to perform the steps of the photomask inspection method based on CAD-generated masks according to any one of claims 1 to 7.

Images