Methods, apparatus, electronic devices and storage media for detecting defects in photomasks

Abstract

This invention discloses a method, apparatus, electronic device, and storage medium for detecting defects in a photomask. The method includes: determining an initial inspection image of the photomask to be tested and initial defects in the initial inspection image; determining a re-inspection image of the photomask to be tested; wherein the initial inspection image and the re-inspection image are obtained by capturing images under different lighting conditions and lenses, and the magnification of the initial inspection image is less than that of the re-inspection image; and classifying and screening defects in the photomask to be tested based on the initial inspection image, the re-inspection image, and the initial defects. This technical solution, by combining defect information obtained from re-inspection and initial inspection under different lighting conditions and lenses, reduces the probability of embossed patterns being identified as defects, effectively improving defect detection performance and efficiency, while increasing the amount of information for defect classification and screening, thus improving the accuracy of defect classification and screening.

Description

Technical Field

[0001] This invention relates to the field of photomask technology, and in particular to a method, apparatus, electronic device, and storage medium for detecting defects in photomasks. Background Technology

[0002] In the field of display panel technology, a photomask is a structure located on a substrate material for selective exposure.

[0003] Defects on photomasks are microparticle contamination introduced during exposure and transfer. The detection of photomask defects is usually carried out using automated optical equipment. The location of the particle contamination on the photomask is recorded and then optically re-inspected. This process is cumbersome, inefficient, and prone to introducing new contamination. There is also a risk of the photomask being misused, which is not conducive to improving production efficiency. Summary of the Invention

[0004] This invention provides a mask defect detection method, apparatus, electronic device, and storage medium, which can increase the amount of information for defect classification and screening by combining detection image information under different lighting conditions and lenses, thereby improving the accuracy of defect classification and screening.

[0005] According to one aspect of the present invention, a method for detecting defects in a mask is provided, the method comprising:

[0006] Determine the initial inspection image of the mask to be tested and the initial inspection defects detected from the initial inspection image;

[0007] Determine the re-inspection image of the mask to be tested; wherein the initial inspection image and the re-inspection image are obtained by taking images under different lighting conditions and with different lenses, and the magnification of the initial inspection image is less than that of the re-inspection image;

[0008] Based on the initial inspection image, the re-inspection image, and the initial inspection defects, the defects of the mask to be tested are classified and screened.

[0009] According to another aspect of the present invention, a mask defect detection device is provided, the device comprising:

[0010] The initial inspection determination module is used to determine the initial inspection image of the mask to be tested and the initial inspection defects of the initial inspection image;

[0011] The re-inspection determination module is used to determine the re-inspection image of the mask to be tested; wherein the initial inspection image and the re-inspection image are obtained by taking images under different lighting conditions and lenses, and the magnification of the initial inspection image is less than that of the re-inspection image.

[0012] The defect detection module is used to classify and filter defects in the mask to be tested based on the initial inspection image, the re-inspection image, and the initial inspection defects.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the mask defect detection method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the mask defect detection method according to any embodiment of the present invention.

[0018] The technical solution of this invention determines an initial inspection image of the mask under test and its initial defects, and determines a re-inspection image of the mask under test. The initial and re-inspection images are obtained by capturing images under different lighting conditions and lenses, with the magnification of the initial inspection image being lower than that of the re-inspection image. Based on the initial and re-inspection images and the initial defects, defects in the mask under test are classified and screened. This technical solution, by combining defect information obtained from the initial and re-inspections under different lighting conditions and lenses, reduces the probability of embossed patterns being identified as defects, effectively improving defect detection performance and efficiency. Simultaneously, it increases the amount of information for defect classification and screening, improving the accuracy of defect classification and screening.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a mask defect detection method provided according to an embodiment of the present invention;

[0022] Figure 2 This is a schematic diagram of a preliminary inspection device for mask defect detection applicable to embodiments of the present invention;

[0023] Figure 3 This is a schematic diagram of a re-inspection device for mask defect detection applicable to embodiments of the present invention.

[0024] Figure 4a This is a schematic diagram of the embossed pattern of the initial inspection image in mask defect detection according to an embodiment of the present invention;

[0025] Figure 4b This is a schematic diagram of the embossed pattern on the same mask under test, captured by a re-inspection device in mask defect detection according to an embodiment of the present invention.

[0026] Figure 4c This is a schematic diagram of the cross-sectional reflection of the indentation pattern in mask defect detection according to an embodiment of the present invention.

[0027] Figure 5 This is a flowchart of another mask defect detection method provided according to an embodiment of the present invention;

[0028] Figure 6 This is a schematic diagram of the structure of a mask defect detection device according to an embodiment of the present invention;

[0029] Figure 7 This is a schematic diagram of the structure of an electronic device that implements a mask defect detection method according to an embodiment of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "preliminary inspection," "re-inspection," and "to be tested," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] AOI (Automated Optical Inspection) equipment, as an optical defect detection tool, is widely used in industries such as solar cells, integrated circuits, and display panels to achieve rapid, non-destructive testing of defects in photomasks and silicon wafers. Among them, automated optical inspection devices for photomask defects, capable of real-time defect detection on large-area panel materials, are widely used by panel manufacturers both domestically and internationally.

[0033] However, due to issues with the incoming material processing, the surface of the metal material in the mask may have randomly shaped embossed patterns. These embossed patterns, depending on their depth and chamfer, exhibit bright or dark imaging characteristics under AOI inspection equipment lighting. These characteristics are similar to those of some particle and fiber defects, making them difficult to distinguish during defect detection and prone to misidentification. Therefore, reducing the probability of false defect identification and improving the detection performance and efficiency of the equipment becomes particularly important.

[0034] The mask defect detection method, apparatus, electronic device, and storage medium provided in this application are described in detail below through various embodiments and their optional solutions.

[0035] Figure 1 This invention provides a flowchart of a mask defect detection method. This embodiment is applicable to situations where non-destructive testing of masks is performed to achieve correct identification and classification of defects. The mask defect detection method can be executed by a mask defect detection device, which can be implemented in hardware and / or software and can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the mask defect detection method of this embodiment may include the following steps:

[0036] S110. Determine the initial inspection image of the mask to be tested and the initial inspection defects of the initial inspection image.

[0037] In the initial inspection stage of the mask under test, the mask under test can be illuminated using lighting methods such as bright field, dark field and backlight, and the initial inspection image of the mask under test under the first illumination condition can be obtained by taking pictures using the initial inspection equipment used for mask defect detection.

[0038] By adjusting the illumination source configuration, the defect signal of the mask under test is increased, the background signal and environmental noise in the mask sample are suppressed, and the signal-to-noise ratio of the defect signal is improved. Subsequently, the high-resolution lens and time-delay integration camera in the preliminary inspection equipment can be used to take high-speed pictures of the mask sample under test to obtain the preliminary inspection image and detect the defects of the mask sample under test as the preliminary inspection defects.

[0039] The test mask surface contains numerous random embossed patterns. These patterns are clearly visible under bright field illumination, making it impossible to detect other defects (such as particles and fibers). However, most of these embossed patterns do not form an image under dark field illumination. Furthermore, considering that the embossed patterns exhibit bright or dark imaging characteristics during detection due to differences in depth and chamfer, similar to the imaging characteristics of some particle and fiber defects, the embossed patterns may be incorrectly identified as defects. Therefore, during the initial inspection, a predominantly dark field illumination method is used to detect defects on the mask surface, in order to detect particle-like protrusions and fiber-like defects, and backlighting is used to inspect the open areas of the mask.

[0040] Optionally, see Figure 2 The initial inspection equipment used for the initial inspection of the mask under test may include: a bright field light box 21, a bright field optical fiber 22, a semi-reflective and semi-transparent beam splitter 23, a dark field ring light source 24, a backlight 25, a lens 26, and a camera sensor 27. The dark field ring light source is composed of ring-shaped distributed LED beads, or it may be composed of ring-shaped distributed optical fiber light sources; the camera sensor 27 may be a time-delay integration (TDI) camera or an area scan camera.

[0041] See Figure 2 The light beam emitted from the bright-field light box 21 is incident on the semi-reflective and semi-transparent beam splitter 23 via optical fiber 22. After one reflection, it shines vertically downwards onto the mask sample under test. Then, after reflection or diffraction, it propagates upwards, passing sequentially through the beam splitter 23 and lens group 26, and is finally received and imaged by the camera sensor 27. The light beam emitted from the backlight 25 illuminates the mask sample under test from below. After passing through the holes in the mask sample, it passes sequentially through the beam splitter 23 and lens group 26, and is finally received and imaged by the camera sensor 27. The light beam emitted from the dark-field ring light source 24 illuminates the mask sample under test at an angle. After being scattered by protrusions and defects on the mask sample, such as tiny particles, it passes sequentially through the beam splitter 23 and lens group 26, and is finally received and imaged by the camera sensor 27. Here, the image acquired using the predominantly dark-field illumination method is used as the initial inspection image.

[0042] S120. Determine the re-inspection image of the mask to be tested.

[0043] The initial inspection image and the re-inspection image were obtained by taking pictures under different lighting conditions and with different lenses, and the magnification of the initial inspection image was less than that of the re-inspection image.

[0044] The illumination conditions used in the initial inspection image are used to suppress the imaging of embossed defects in the mask under test. For example, the initial inspection image is illuminated in dark field. Under dark field illumination, the initial inspection equipment can detect granular protrusion defects and fibrous defects. The imaging characteristics of embossed patterns are similar to those of some granular and fibrous defects. During inspection, embossed patterns may also be mistakenly identified as defects and thus detected. However, granular and fibrous defects are often mixed with embossed patterns and are difficult to distinguish.

[0045] The re-inspection images used different lighting conditions and lenses than the initial inspection. The lighting conditions used in the re-inspection images were designed to suppress shadows from granular protrusions and defects in the mask under test. For example, the re-inspection images used a combination of dome lighting and bright field lighting to achieve a shadowless effect, which maximally suppresses shadows from granular protrusions and fiber defects on the mask surface. If the defect material is similar to that of the metal mask, it will hardly be imaged, while for recessed defects, such as deep embossing patterns, this lighting will produce noticeably darker defects. Therefore, during the re-inspection process, a dome lighting + bright field method was used to photograph the mask to detect defects on the mask surface, while backlighting was used to inspect the open areas of the mask.

[0046] Optionally, see Figure 3 The re-inspection equipment used for re-inspecting the mask under test may include: a focus tracking sensor / bright field illumination 31, a sensor beam splitter 32 (and... Figure 2 The system includes a beam splitter (similar to the beam splitter), a servo controller 33, a focus driver 34, a dome light 35, a backlight 36, a microscope lens 37, a tube lens 38, and an area array camera sensor 39. Among them, the focus sensor 31, the sensor beam splitter 32, the servo controller 33, and the focus driver 34 form a feedback device to realize the automatic focus tracking function for re-examination.

[0047] See Figure 3The focusing sensor 31 also functions as a bright-field illumination source. The beam of light, after passing through the beam splitter 32 and the microscope lens 37, illuminates the mask sample under test vertically downwards. It then propagates upwards through reflection or diffraction, passing sequentially through the microscope lens 37, sensor beam splitter 32, and tube lens 38, before finally being received and imaged by the area array camera sensor 39. The beam emitted by the backlight 36 travels upwards, passing through the opening area of ​​the mask sample under test, and then sequentially through the microscope lens 37, sensor beam splitter 32, and tube lens 38, before finally being received and imaged by the area array camera sensor 39. The beam of light from the dome lamp 35, after illuminating the mask sample under test, passes sequentially through the microscope lens 37, sensor beam splitter 32, and tube lens 38, before finally being received and imaged by the area array camera sensor 39. Here, the image acquired during the initial inspection of the same mask sample using a combination of dome lamp and bright-field illumination will be used as the re-inspection image.

[0048] In one optional embodiment, determining the re-inspection image of the mask to be tested may include steps A1-A2:

[0049] Step A1: Determine the location of the initial inspection defect on the mask to be tested.

[0050] Step A2: Control the re-inspection equipment to take an image of the local area corresponding to the initial inspection defect on the mask to be tested, and obtain a re-inspection image including the initial inspection defect.

[0051] The initial inspection of the mask under test reveals that not all areas have defects. Therefore, a global re-inspection of the mask is unnecessary. Instead, re-inspection images can be obtained by capturing images of specific areas of the mask based on the locations of the initial defects. For example, the re-inspection equipment can be oriented towards the area corresponding to the initial defect location on the mask, thus only requiring image capture of the defective area.

[0052] The initial inspection equipment performs a rapid scan of the entire mask to be tested, aiming to quickly detect defects to be classified or screened. The initial inspection images are processed by the inspection computer to obtain initial inspection defects and screenshots of the initial inspection defects, which are then saved in memory for later use. Subsequently, the re-inspection equipment takes re-inspection photos of the initial inspection defects detected by the initial inspection images, obtaining re-inspection images. Based on the initial inspection defects, the initial inspection images, and the re-inspection images, defects can be screened and classified.

[0053] S130. Based on the initial inspection image, the re-inspection image, and the initial inspection defects, classify and screen the defects of the mask to be tested.

[0054] For example, see embossed patterns. Figure 4a , Figure 4b and Figure 4cThe images shown are the initial inspection image of the mask under test, the image of the embossed pattern defect taken during the re-inspection, and a schematic diagram of the embossed pattern scattering. Figure 4a The embossed pattern captured by the initial inspection equipment, from Figure 4a As can be seen, under the dark lighting of the initial inspection equipment, the embossed pattern appears as a bright, small-particle dark defect, similar to the appearance of particle protrusions and fiber defects.

[0055] Figure 4b Images of the embossed patterns on the same test mask captured by the re-inspection equipment, from Figure 4b As can be seen, under the dome light + bright field illumination of the re-inspection equipment, the shadows of granular protrusion defects in the mask under test are suppressed to the greatest extent possible. Only the embossing defects appear as dark defects. Moreover, the area of ​​the initial embossing defect is located at the edge of the re-inspection embossing dark defect, and the edge shape is similar to the shape and direction of the re-inspection dark defect.

[0056] The reason for the above situation is that the bright defect image of the embossed pattern in the dark field comes from the reflection of the embossed pattern's cross-section, such as... Figure 4c As shown, by utilizing the aforementioned properties, the differences between the initial inspection image and the re-inspection image of the same test mask can be compared to classify and screen embossing defects. Similarly, for other defects, the performance of defect classification and screening can be improved by combining the characteristics of the initial inspection image and the re-inspection image. For example, particle defects detected by the initial inspection equipment can be further classified by combining the grayscale information of the defect area in the re-inspection image to obtain the reflectivity information of the particles.

[0057] According to the technical solution of the present invention, by combining the defect information obtained from the re-inspection and initial inspection under different lighting conditions and lenses, the probability of embossed patterns being identified as defects is reduced, effectively improving defect detection performance and efficiency. At the same time, the amount of information for defect classification and screening is increased, thereby improving the accuracy of defect classification and screening.

[0058] Figure 5 This invention provides a flowchart of another mask defect detection method. Based on the above embodiments, this embodiment further optimizes the process of classifying and screening defects in the mask under test according to the initial inspection image, the re-inspection image, and the initial inspection defect area. This embodiment can be combined with various optional solutions in one or more of the above embodiments. Figure 5 As shown, the mask defect detection method of this embodiment may include the following steps:

[0059] S510. Determine the initial inspection image of the mask to be tested and the initial inspection defects of the initial inspection image.

[0060] S520. Determine the re-inspection image of the mask to be tested; wherein the initial inspection image and the re-inspection image are obtained by taking images under different lighting conditions and with different lenses, and the magnification of the initial inspection image is less than that of the re-inspection image.

[0061] Optionally, the lighting conditions used in the initial inspection image are used to suppress the imaging of embossed defects in the mask under test, and the lighting conditions used in the re-inspection image are used to suppress the shadows of granular protrusion defects in the mask under test.

[0062] S530. When transforming from the initial inspection image to the re-inspection image, determine the re-inspection defect that matches the initial inspection defect in the re-inspection image.

[0063] The initial inspection image and the re-inspection image are taken from the same mask under different lighting conditions and lenses. Initial inspection can detect initial defects. When the initial inspection image is converted to the re-inspection image to reflect the initial defects, the re-inspection image will contain re-inspection defects that match the initial defects.

[0064] In one optional embodiment, determining the re-inspection defect that matches the initial inspection defect in the re-inspection image when transforming from the initial inspection image to the re-inspection image may include steps B1-B2:

[0065] Step B1: Perform image registration between the initial inspection image and the re-inspection image to obtain the image transformation matrix used to transform the initial inspection image into the re-inspection image.

[0066] Step B2: Based on the image transformation matrix, match the initial inspection defects in the initial inspection image to the re-inspection image to obtain the re-inspection defects that match the initial inspection defects in the re-inspection image.

[0067] The initial inspection image, initial defect inspection image, and re-inspection image are read from memory. By registering the initial inspection image and the re-inspection image, the image transformation matrix used to transform the initial inspection image into the re-inspection image can be obtained. The image transformation matrix can include, but is not limited to, the following: translation matrix, scaling matrix, rotation matrix, and affine matrix. Optionally, using the initial inspection image as the reference image, the initial inspection image is matched with the re-inspection image based on its size, angle, and other morphological information, and the coordinates of the optimal matching points are extracted to generate the image transformation matrix.

[0068] Since the initial defect is part of the initial inspection image, there will be a defect in the re-inspection image that matches the initial defect. Therefore, according to the image transformation matrix used to transform from the initial inspection image to the re-inspection image, the initial defect can be transformed to match the initial defect in the initial inspection image to the re-inspection image, thus finding the re-inspection defect that matches the initial defect in the re-inspection image.

[0069] Using the above method, the defects detected in the initial inspection can be aligned and matched onto the re-inspection image using the initial inspection image and the re-inspection image. This makes it easier to use the re-inspection defects in the matched re-inspection image to assist in the location, detection and classification of defects in the re-inspection image, thereby reducing the computational load and processing difficulty of defect classification in the re-inspection image.

[0070] S540. Based on the re-inspection image features corresponding to the re-inspection defects, classify and screen the defects of the mask to be tested.

[0071] In one optional embodiment, classifying and screening defects in the mask to be tested based on the re-inspection image features corresponding to the re-inspection defects may include steps C1-C2:

[0072] Step C1: Dilate the re-inspection defects in the re-inspection image and analyze the re-inspection image features corresponding to the dilated re-inspection defects.

[0073] Step C2: Based on the re-inspection image features corresponding to the re-inspection defects, classify and screen the defects of the mask to be tested.

[0074] The transformed defect region is expanded, and defect detection is performed on the re-inspection image within the expanded region. The defect features detected in the re-inspection image corresponding to the defect are statistically analyzed and used as the re-inspection image features. If the re-inspection image features meet the feature conditions of the embossing pattern criterion, the re-inspection defect is considered to be caused by an embossing pattern, and the corresponding initial inspection defect is also considered to be caused by an embossing pattern. If the re-inspection image features do not meet the feature conditions of the embossing pattern criterion, the re-inspection defect is considered not to be caused by an embossing pattern, and the corresponding initial inspection defect is also considered not to be caused by an embossing pattern, but may be a particle protrusion defect and / or a fiber defect.

[0075] In another optional embodiment, based on the re-inspection image features corresponding to the re-inspection defects, the defects of the mask to be tested are classified and screened, which may include steps D1-D3:

[0076] Step D1: Determine the area of ​​the initial inspection defect region and the area of ​​the reference defect region; the reference defect region includes defects that belong to the initial inspection defect but not to the re-inspection defect.

[0077] Step D2: Based on the area of ​​the initial defect area and the area of ​​the reference defect area, determine the degree of matching between the initial defect area and the re-inspection defect area.

[0078] Step D3: Based on the inter-regional matching degree and the re-inspection image features corresponding to the re-inspection defects, determine whether the initial inspection defects on the mask to be tested are embossing defects.

[0079] Based on the aligned initial and re-inspection images, local defects that belong to the initial inspection but not the re-inspection can be identified as reference defects. Then, based on the areas of the initial and reference defect regions, the matching degree P = Anot / Aall is analyzed, where Anot represents the area of ​​the region in the initial inspection that is not a re-inspection defect, and Aall is the total area of ​​the initial inspection defect region.

[0080] Optionally, the features of the re-inspected image may include image grayscale features and density features. Based on whether the region matching degree P between the initial defect area and the re-inspected defect area, and whether the re-inspected image features (including but not limited to defect grayscale G) corresponding to the re-inspected defect satisfy the imprinting criterion, it is determined whether the current initial defect is an imprint. If the re-inspected defect is determined to be an imprint, and the corresponding initial defect is a defect caused by an imprint, then the initial defect is filtered out. If the re-inspected defect on the test mask is determined not to be an imprint, and the corresponding initial defect is not a defect caused by an imprint, possibly a particle protrusion defect and / or fiber defect, then the initial defect is saved and output. This process is repeated until all initial defects are classified and filtered.

[0081] Based on the above embodiments, optionally, the embossing criterion can be that the compactness of the defect is greater than the embossing threshold, a typical example being Compact > 4. The compactness feature is a feature of the defect area, Compact = L^2 / (4*F*pi), where L is the perimeter of the defect area, F is the area of ​​the defect area, and pi is pi.

[0082] Based on the above embodiments, optionally, the embossing criterion can also be a feature classification hyperplane composed of other defect features. Other defect features include the density of the defect region, average gray level, gray level fluctuation 3sigma value, reference gray level, reference gray level fluctuation 3sigma value, geometric moments, gray-level co-occurrence matrix, etc. The feature classification hyperplane is generated using the SVM (Support Vector Machine) algorithm. The input feature set of the SVM algorithm is the aforementioned features. The input data of the SVM algorithm includes manually labeled re-inspection defect image type (whether it is an embossing pattern), the re-inspection defect image, the re-inspection defect region, etc.

[0083] Based on the above embodiments, optionally, the embossing criterion can also be a classification neural network black box. The defect feature set and input data of the classification neural network are the same as those described for SVM. Classification neural network models include convolutional neural networks, recurrent neural networks, deep neural networks, etc.

[0084] According to the technical solution of the present invention, by combining the defect information obtained from the re-inspection and the initial inspection under different lighting conditions, the amount of information for defect classification and screening is increased, which effectively improves the accuracy of defect classification and screening, reduces the probability of embossed patterns being identified as defects, and effectively improves defect detection performance and efficiency. At the same time, the initial inspection defects are aligned and matched onto the re-inspection image using the initial inspection image and the re-inspection image. The matched defects are used to assist in the defect location, detection and classification of the re-inspection image, which reduces the computational load and processing difficulty of defect detection and classification of the re-inspection image.

[0085] Figure 6 This invention provides a structural block diagram of a mask defect detection device. This embodiment is applicable to situations where non-destructive testing of masks is performed to achieve correct identification and classification of defects. The mask defect detection device can be implemented in hardware and / or software and can be configured in an electronic device with data processing capabilities. Figure 6 As shown, the mask defect detection device of this embodiment may include: a preliminary inspection determination module 610, a re-inspection determination module 620, and a defect detection module 630. Wherein:

[0086] The initial inspection determination module 610 is used to determine the initial inspection defects of the initial inspection image of the mask to be tested and the initial inspection image.

[0087] The re-inspection determination module 620 is used to determine the re-inspection image of the mask to be tested; wherein the initial inspection image and the re-inspection image are obtained by taking images under different lighting conditions and lenses, and the magnification of the initial inspection image is less than that of the re-inspection image.

[0088] The defect detection module 630 is used to classify and screen defects of the mask to be tested based on the initial inspection image, the re-inspection image, and the initial inspection defects.

[0089] Based on the above embodiments, optionally, the lighting conditions used in the initial inspection image are used to suppress the imaging of embossed defects in the mask under test, and the lighting conditions used in the re-inspection image are used to suppress the shadows of granular protrusion defects in the mask under test.

[0090] Based on the above embodiments, optionally, the re-inspection determination module 620 includes:

[0091] Determine the location of the initial inspection defect on the mask to be tested;

[0092] The re-inspection equipment is controlled to capture an image of the local area corresponding to the initial defect on the mask to be tested, thereby obtaining a re-inspection image including the initial defect.

[0093] Based on the above embodiments, optionally, the defect detection module 630 includes:

[0094] When transforming from the initial inspection image to the re-inspection image, identify the re-inspection defect that matches the initial inspection defect in the re-inspection image;

[0095] Based on the re-inspection image features corresponding to the re-inspection defects, the defects of the mask to be tested are classified and screened.

[0096] Based on the above embodiments, optionally, when transforming from the initial inspection image to the re-inspection image, the re-inspection defect that matches the initial inspection defect in the re-inspection image includes:

[0097] The initial detection image and the re-detection image are image registered to obtain the image transformation matrix used to transform the initial detection image into the re-detection image.

[0098] Based on the image transformation matrix, the initial defects of the initial inspection image are matched onto the re-inspection image to obtain the re-inspection defects that match the initial defects in the re-inspection image.

[0099] Based on the above embodiments, optionally, the defects of the mask to be tested are classified and screened according to the re-inspection image features corresponding to the re-inspection defects, including:

[0100] The re-inspection defects in the re-inspection image are dilated, and the re-inspection image features corresponding to the dilated re-inspection defects are analyzed.

[0101] Based on the re-inspection image features corresponding to the re-inspection defects, the defects of the mask to be tested are classified and screened.

[0102] Based on the above embodiments, optionally, the defects of the mask to be tested are classified and screened according to the re-inspection image features corresponding to the re-inspection defects, including:

[0103] Determine the area of ​​the initial inspection defect region and the area of ​​the reference defect region; the reference defect includes defects that belong to the initial inspection defect but not to the re-inspection defect;

[0104] Based on the area of ​​the initial defect area and the area of ​​the reference defect area, the degree of matching between the initial defect area and the re-inspection defect area is determined;

[0105] Based on the inter-regional matching degree and the re-inspection image features corresponding to the re-inspection defect, it is determined whether the initial inspection defect on the mask to be tested is an embossing defect.

[0106] Based on the above embodiments, optionally, the re-examined image features include image grayscale features and density features.

[0107] The mask defect detection device provided in the embodiments of the present invention can execute the mask defect detection method provided in any of the embodiments of the present invention, and has the corresponding functions and beneficial effects of executing the mask defect detection method. For details, please refer to the relevant operations of the mask defect detection method in the foregoing embodiments.

[0108] Figure 7 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0109] like Figure 7 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0110] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0111] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as mask defect detection methods.

[0112] In some embodiments, the mask defect detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the mask defect detection method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the mask defect detection method by any other suitable means (e.g., by means of firmware).

[0113] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0114] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0115] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0116] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0117] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0118] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0119] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0120] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting defects in a mask, characterized in that, The method includes: Determine the initial inspection image of the mask to be tested and the initial inspection defects detected from the initial inspection image; Determine the re-inspection image of the mask to be tested; wherein the initial inspection image and the re-inspection image are obtained by taking images under different lighting conditions and with different lenses, and the magnification of the initial inspection image is less than that of the re-inspection image; Based on the initial inspection image, the re-inspection image, and the initial inspection defects, the defects of the mask to be tested are classified and screened. The defects of the mask under test are classified and screened based on the initial inspection image, the re-inspection image, and the initial inspection defects, including: When transforming from the initial inspection image to the re-inspection image, identify the re-inspection defect that matches the initial inspection defect in the re-inspection image; Based on the re-inspection image features corresponding to the re-inspection defects, the defects of the mask to be tested are classified and screened. Specifically, based on the re-inspection image features corresponding to the re-inspection defects, the defects of the mask to be tested are classified and screened, including: The re-inspection defect is dilated, and the dilated image features corresponding to the re-inspection defect are obtained by parsing the dilated data. Based on the re-inspection image features corresponding to the re-inspection defects, the defects of the mask to be tested are classified and screened. or, Determine the area of ​​the initial inspection defect region and the area of ​​the reference defect region; the reference defect includes defects that belong to the initial inspection defect but not to the re-inspection defect; Based on the area of ​​the initial defect area and the area of ​​the reference defect area, the degree of matching between the initial defect area and the re-inspection defect area is determined; Based on the inter-regional matching degree and the re-inspection image features corresponding to the re-inspection defect, it is determined whether the initial inspection defect on the mask to be tested is an embossing defect.

2. The method according to claim 1, characterized in that, The lighting conditions used in the initial inspection image are used to suppress the imaging of embossed defects in the mask under test, and the lighting conditions used in the re-inspection image are used to suppress the shadows of granular protrusion defects in the mask under test.

3. The method according to claim 1, characterized in that, Determine the re-examination image of the mask to be tested, including: Determine the location of the initial inspection defect on the mask to be tested; The re-inspection equipment is controlled to take an image of the local area corresponding to the initial defect location to obtain a re-inspection image including the initial defect.

4. The method according to claim 1, characterized in that, Determining the re-inspection defect that matches the initial inspection defect in the re-inspection image when transformed from the initial inspection image to the re-inspection image includes: The initial detection image and the re-detection image are image registered to obtain the image transformation matrix used to transform the initial detection image into the re-detection image. Based on the image transformation matrix, the initial defects of the initial inspection image are matched onto the re-inspection image to obtain the re-inspection defects that match the initial defects in the re-inspection image.

5. A mask defect detection device, characterized in that, The device includes: The initial inspection determination module is used to determine the initial inspection image of the mask to be tested and the initial inspection defects of the initial inspection image; The re-inspection determination module is used to determine the re-inspection image of the mask to be tested; wherein the initial inspection image and the re-inspection image are obtained by taking images under different lighting conditions and lenses, and the magnification of the initial inspection image is less than that of the re-inspection image. The defect detection module is used to classify and filter defects in the mask to be tested based on the initial inspection image, the re-inspection image, and the initial inspection defects. Specifically, the defect detection module is used for: When transforming from the initial inspection image to the re-inspection image, identify the re-inspection defect that matches the initial inspection defect in the re-inspection image; Based on the re-inspection image features corresponding to the re-inspection defects, the defects of the mask to be tested are classified and screened. Specifically, based on the re-inspection image features corresponding to the re-inspection defects, the defects of the mask to be tested are classified and screened, including: The re-inspection defect is dilated, and the dilated image features corresponding to the re-inspection defect are obtained by parsing the dilated data. Based on the re-inspection image features corresponding to the re-inspection defects, the defects of the mask to be tested are classified and screened. or, Determine the area of ​​the initial inspection defect region and the area of ​​the reference defect region; the reference defect includes defects that belong to the initial inspection defect but not to the re-inspection defect; Based on the area of ​​the initial defect area and the area of ​​the reference defect area, the degree of matching between the initial defect area and the re-inspection defect area is determined; Based on the inter-regional matching degree and the re-inspection image features corresponding to the re-inspection defect, it is determined whether the initial inspection defect on the mask to be tested is an embossing defect.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the mask defect detection method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the mask defect detection method according to any one of claims 1-4.

Images