Wafer image preprocessing method and device, equipment and storage medium

Abstract

The invention discloses a wafer image preprocessing method and device, equipment and a storage medium. The method comprises the following steps: acquiring an initial to-be-detected image of a to-be-detected wafer; performing noise distribution estimation on the initial to-be-detected image, and positioning a highlight defect area in the initial to-be-detected image; smoothing the highlight defect area to obtain a smooth image and a difference image between the highlight defect area and a corresponding area on the smooth image; performing frequency domain filtering operation on the smooth image to obtain a filtered image; and superposing the difference image to a corresponding area on the filtered image to obtain a final to-be-detected image. According to the method, the highlight defect area in the wafer diffraction image is positioned and separated, the frequency domain filtering operation is carried out on the rest part of the image, and finally the difference image corresponding to the highlight defect area is superposed to the filtered image, so that the image reconstruction is completed, the morphological characteristics of the highlight defect are reserved, and the accuracy of the image reconstruction is improved. And detection and classification of subsequent defects are not influenced.

Description

Technical Field

[0001] The present application relates to the field of wafer inspection technology, and in particular to a wafer image preprocessing method, device, equipment and storage medium. Background Art

[0002] When the wafer is illuminated by the laser spot, it produces reflected or scattered light. This light is collected by the imaging optical path and then irradiated onto the camera's light-sensitive light source, forming an image containing information about the wafer's background, structure, and defects. Defect detection in this image can be used to determine the wafer's yield. In addition to background, structure, and defect information, the image typically contains noise introduced by the laser, wafer processing, and the camera. This noise can interfere with defect detection. Periodic noise filtering is typically performed in the frequency domain. However, the image inversely transformed after frequency domain filtering often produces diffraction fringes in bright areas, disrupting the structural characteristics of the defect and affecting the subsequent defect classification process.

[0003] At present, for the problem of image distortion in highlight areas, the usual practice is to superimpose a Gaussian filter or other smoothing filter on the filter. This method can reduce the distortion effect of the inverse transformed image to a certain extent, but the smoothing of the filter will affect the effect of frequency domain filtering to a certain extent and is not effective in reducing the distortion of highlight defects, which still has a significant impact on the defect detection accuracy of the wafer. Summary of the Invention

[0004] In view of this, the present application provides a wafer image preprocessing method, device, equipment and storage medium to solve the problem of distortion of highlight defect images in the existing wafer inspection image preprocessing.

[0005] In order to solve the above technical problems, a technical solution adopted in this application is: to provide a wafer image preprocessing method, which includes: obtaining an initial image to be inspected of the wafer to be tested; estimating the noise distribution of the initial image to be inspected, and locating the highlighted defect area in the initial image to be inspected; smoothing the highlighted defect area to obtain a smoothed image and a difference image between the highlighted defect area and the corresponding area on the smoothed image; performing frequency domain filtering operation on the smoothed image to obtain a filtered image; superimposing the difference image on the corresponding area on the filtered image to obtain the final image to be inspected.

[0006] As a further improvement of the present application, the noise distribution of the initial image to be inspected is estimated, and the highlighted defect area in the initial image to be inspected is located, including: extracting the reference pixel values ​​of all reference pixels within a preset neighborhood range of each pixel point, and using the reference pixel values ​​to calculate the first eigenvalue and the second eigenvalue of each pixel point; calculating the pixel threshold of each pixel based on the first eigenvalue and the second eigenvalue; and taking the area composed of pixels whose pixel values ​​exceed the pixel threshold as the highlighted defect area.

[0007] As a further improvement of the present application, the first eigenvalue includes the median or mean of all reference pixel values ​​within a preset neighborhood range, and the second eigenvalue includes the first variance value of all reference pixel values ​​within the preset neighborhood range; the calculation process of the pixel threshold is expressed as:

[0008] T i =medain i +coeff1*std i ;

[0009] Among them, T i Represents the pixel threshold of the i-th pixel, medain i Indicates the median or mean corresponding to the i-th pixel, std i It represents the first variance value corresponding to the i-th pixel point, and coeff1 represents the preset noise estimation coefficient.

[0010] As a further improvement of the present application, the first eigenvalue includes the median or mean of all reference pixel values ​​within a preset neighborhood range, and the second eigenvalue includes a second variance value among all reference pixel values ​​within the preset neighborhood range. The second variance value is expressed as:

[0011] std j =coeff2*(medain j -min j );

[0012] Among them, std j Indicates the second variance value corresponding to the j-th pixel, medain j Indicates the median or mean corresponding to the j-th pixel, min j represents the minimum pixel value in the preset neighborhood corresponding to the j-th pixel point, and coeff2 represents the pre-calibrated parameter;

[0013] The calculation process of pixel threshold is expressed as:

[0014] T j =medain j +coeff1*[coeff2*(medain j -min j )];

[0015] Among them, T j represents the pixel threshold of the j-th pixel, and coeff1 represents the preset noise estimation coefficient.

[0016] As a further improvement of the present application, the preset neighborhood range is represented as all pixel points within a window of size M*N constructed with the pixel point as the center.

[0017] As a further improvement of the present application, the highlighted defect area is smoothed to obtain a smoothed image and a difference image between the highlighted defect area and the corresponding area on the smoothed image, including: obtaining the target pixel values ​​of all target pixels in the highlighted defect area; calculating the difference between the target pixel value corresponding to each target pixel and the corresponding first eigenvalue, and constructing a difference image based on the difference; replacing the pixel value of each target pixel in the highlighted defect area with the corresponding first eigenvalue to obtain a smoothed image.

[0018] To solve the above technical problems, another technical solution adopted in the present application is: to provide a wafer image preprocessing device, which includes: an acquisition module for acquiring an initial image to be inspected of the wafer to be tested; a positioning module for estimating the noise distribution of the initial image to be inspected and locating the highlighted defect area in the initial image to be inspected; a smoothing processing module for smoothing the highlighted defect area to obtain a smoothed image and a difference image between the highlighted defect area and the corresponding area on the smoothed image; a filtering module for performing frequency domain filtering operations on the smoothed image to obtain a filtered image; and a reconstruction module for superimposing the difference image on the corresponding area on the filtered image to obtain the final image to be inspected.

[0019] In order to solve the above technical problems, another technical solution adopted in this application is: to provide a computer device, which includes a processor and a memory coupled to the processor, wherein program instructions are stored in the memory, and when the program instructions are executed by the processor, the processor executes the steps of the wafer image preprocessing method as described in any one of the above items.

[0020] In order to solve the above technical problems, another technical solution adopted in the present application is: providing a storage medium storing program instructions capable of implementing any of the above wafer image preprocessing methods.

[0021] The beneficial effect of the present application is: the wafer image preprocessing method of the present application locates and separates the highlight defect area in the wafer diffraction image, then performs frequency domain filtering on the rest of the image, and finally superimposes the difference image corresponding to the highlight defect area onto the filtered image to complete image reconstruction. The reconstructed image retains the morphological characteristics of the highlight defect while filtering out the noise, will not affect the subsequent defect detection and classification, and improves the accuracy of defect detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 1 is a flow chart of a wafer image preprocessing method according to an embodiment of the present invention;

[0023] Figure 2 1 is a schematic diagram of the functional modules of a wafer image preprocessing device according to an embodiment of the present invention;

[0024] Figure 3 is a schematic structural diagram of a computer device according to an embodiment of the present invention;

[0025] Figure 4 It is a schematic structural diagram of a storage medium according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0027] The terms "first," "second," and "third" in this application are used only for descriptive purposes and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of such features. In the description of this application, "multiple" means at least two, for example, two, three, etc., unless otherwise specifically defined. All directional indications in the embodiments of this application (such as up, down, left, right, front, back...) are only used to explain the relative positional relationship, movement, etc. between the components under a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications also change accordingly. In addition, the terms "including" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products, or devices.

[0028] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0029] Figure 1 It is a flow chart of the wafer image preprocessing method according to an embodiment of the present invention. It should be noted that the method of the present invention is not limited to the method of FIG. Figure 1 The process sequence shown is limited. Figure 1 As shown, the wafer image preprocessing method includes the following steps:

[0030] Step S1: Acquire an initial inspection image of the wafer to be tested.

[0031] It's important to note that wafer inspection is crucial for ensuring product quality in semiconductor manufacturing. Wafer diffraction images provide information about the wafer's surface microstructure and defects. However, initially detected diffraction images are often affected by factors such as noise, making defect detection accuracy based directly on these initial images too low. Therefore, preprocessing of these initial images is necessary to improve the accuracy of subsequent analysis.

[0032] Specifically, in practical applications, a specific image acquisition device, such as a high-resolution microscope, is used to capture images of the wafer, thereby obtaining an initial image to be inspected. This initial image to be inspected includes, but is not limited to, information such as background structure, periodic noise (such as laser interference fringes), and highlight defects (such as micron-level scratches or particle contamination).

[0033] Step S2: Estimating the noise distribution of the initial image to be inspected, and locating the highlighted defect area in the initial image to be inspected.

[0034] Specifically, when locating the highlighted defect area, the pixel value of each pixel in the initial image to be inspected is first obtained; then the noise distribution is estimated based on the pixel value, and the noise distribution estimation can be achieved through a Gaussian noise model, a noise estimation model based on wavelet transform, etc.; then, according to the noise distribution, a suitable threshold is set, and this threshold can be determined in a variety of ways, such as based on empirical values, statistical analysis of known defect images, or using an adaptive threshold method (for example, setting an adaptive threshold based on the local mean and standard deviation, which is expressed as: T = μ + k*σ, where T represents the adaptive threshold, μ represents the local mean, σ represents the local standard deviation, and k represents the empirical coefficient); finally, the entire image is traversed based on the threshold, and pixels that exceed the threshold are marked, and all marked pixels constitute the highlighted defect area.

[0035] Furthermore, it should be understood that the present invention performs a pre-inspection on the initial image to be inspected, and its goal is to locate the highlighted defect area. Therefore, the noise estimation accuracy of the initial image to be inspected does not need to be too high, as long as the highlighted defect area can be located. Therefore, step S2 specifically includes:

[0036] 1. Extract the reference pixel values ​​of all reference pixels within a preset neighborhood of each pixel, and calculate the first eigenvalue and the second eigenvalue of each pixel using the reference pixel values.

[0037] 2. Calculate the pixel threshold of each pixel based on the first eigenvalue and the second eigenvalue.

[0038] 3. The area formed by pixels whose pixel values ​​exceed the pixel threshold is regarded as a highlight defect area.

[0039] In some embodiments, to ensure image reconstruction accuracy, the preset neighborhood range is represented by all pixels within an M*N window centered on the pixel. Therefore, it is necessary to traverse each pixel in the initial image to be inspected and obtain the reference pixel values ​​of all reference pixels within the M*N window centered on each pixel. The values ​​of M and N are both in the range [9, 121].

[0040] It should be noted that when traversing the pixel points at the edge position of the initial image to be inspected, the M*N window range exceeds the edge of the initial image to be inspected. Therefore, the pixel points in the exceeding area need to be filled. The filling method may include the following methods:

[0041] 1. Mirror Fill: First, for each pixel to be processed, the number of pixels required for padding in the horizontal and vertical directions is calculated based on the size of the M×N window. Then, starting from the edge of the image, the pixel values ​​are copied in sequence in a mirrored manner. For example, in the horizontal direction, if the current pixel is at the rightmost position, the mirrored pixel to its right is the pixel value at the symmetrical position to its left; the same applies vertically. Finally, after obtaining the mirrored pixels, they are used to fill the window area beyond the edge of the image.

[0042] 2. Constant fill: Constant fill fills the area beyond the image boundary with a fixed constant value. This constant value can be selected according to the specific application scenario, for example, the average pixel value of the image, 0, or 255 can be selected.

[0043] 3. Edge Copy Fill: Edge Copy Fill is similar to Mirror Fill. It calculates the number of pixels that need to be filled in the horizontal and vertical directions, and then copies the pixel values ​​of the image edge to the part that exceeds the boundary.

[0044] In this embodiment, all pixel points are traversed and then the highlighted defect area is located according to the traversal result. The positioning accuracy is high, but the amount of calculation is large.

[0045] Furthermore, in order to improve reconstruction efficiency, in other embodiments, when traversing pixel points in a preset neighborhood range with a window size of M*N, the two-dimensional convolution can be decomposed into two one-dimensional convolutions, that is, first traversing the pixels in the preset neighborhood range with a window size of M*1, and then traversing the pixels in the preset neighborhood range with a window size of 1*N. The computational complexity of the original M*N two-dimensional convolution is O=(M×N×H×W), which becomes O=((M+N)×H×W) after decomposition. When the preset neighborhood range is larger, the computational complexity after decomposition is significantly lower than the computational complexity before decomposition, thereby improving computational efficiency. Therefore, when the preset neighborhood range is large, it is preferred to adopt the method of decomposing the two-dimensional convolution into a one-dimensional convolution, sacrificing a small amount of accuracy in exchange for a significant improvement in computational efficiency.

[0046] It should be noted that, in this embodiment, it is also necessary to fill the excess area with pixels. For the filling method, please refer to the above embodiment and will not be described in detail here.

[0047] Further, based on the above embodiments, in some embodiments, the first eigenvalue includes the median or mean of all reference pixel values ​​within a preset neighborhood range, and the second eigenvalue includes the first variance value of all reference pixel values ​​within the preset neighborhood range.

[0048] The calculation process of pixel threshold is expressed as:

[0049] T i =medain i +coeff1*std i ;

[0050] Among them, T i Represents the pixel threshold of the i-th pixel, medain i Indicates the median or mean corresponding to the i-th pixel, std i Represents the first variance value corresponding to the i-th pixel, and coeff1 represents the pre-set noise estimation coefficient. It should be understood that this noise estimation coefficient controls the weight of the standard deviation in the threshold calculation. When coeff1 is low, it means that the standard deviation has less influence on the threshold. At this time, the threshold is more dependent on the median, and the segmentation result is more sensitive to defects. Because the smaller coeff1 makes the threshold relatively low, some small differences that may have been ignored are more easily identified as defects; but at the same time, due to the lower threshold, the possibility of misjudging noise as defects is also increased. When coeff1 is high, the role of the standard deviation in the threshold calculation increases, and the threshold will increase accordingly. The segmentation is relatively less sensitive, but it can effectively reduce the situation where noise is misjudged as defects.

[0051] Furthermore, based on the above embodiment, in some other embodiments, the first eigenvalue includes the median or mean of all reference pixel values ​​within a preset neighborhood range, and the second eigenvalue includes the second variance value of all reference pixel values ​​within the preset neighborhood range. The second variance value is expressed as:

[0052] std j =coeff2*(medain j -min j );

[0053] Among them, std j Indicates the second variance value corresponding to the j-th pixel, medain j Indicates the median or mean corresponding to the j-th pixel, min j represents the minimum pixel value in the preset neighborhood corresponding to the j-th pixel point, and coeff2 represents the pre-calibrated parameter;

[0054] The calculation process of pixel threshold is expressed as:

[0055] T j =medain j +coeff1*[coeff2*(medain j -min j )];

[0056] Among them, T j represents the pixel threshold of the j-th pixel, and coeff1 represents the preset noise estimation coefficient.

[0057] Step S3: Smoothing the highlighted defect area to obtain a smoothed image and a difference image between the highlighted defect area and the corresponding area on the smoothed image.

[0058] Specifically, in order to reduce the distortion problem of the highlighted defect area in the inspected image caused by the frequency domain filtering operation, this embodiment smoothes all the pixels in the highlighted defect area, thereby suppressing the brightness of the highlighted defect area, while retaining the pixel difference between the highlighted defect area and the smoothed image.

[0059] Furthermore, step S3 specifically includes:

[0060] 1. Obtain the target pixel values ​​of all target pixels in the highlighted defect area.

[0061] Specifically, each pixel in the highlighted defect area is traversed, and its pixel value is recorded as the target pixel value.

[0062] 2. Calculate the difference between the target pixel value corresponding to each target pixel point and the corresponding first eigenvalue, and construct a difference image based on the difference.

[0063] Specifically, for each target pixel point in the highlighted defect area, the first eigenvalue corresponding to the pixel point (such as the median or mean calculated in the above embodiment) is subtracted from its target pixel value to obtain the difference, and a difference image is constructed based on these differences. The value of each pixel point in the difference image reflects the degree of deviation of the point from the smoothing reference value.

[0064] 3. Replace the pixel value of each target pixel in the highlighted defect area with the corresponding first eigenvalue to obtain a smoothed image.

[0065] Specifically, by replacing the pixel value of each target pixel point in the highlighted defect area with the corresponding first eigenvalue, the highlighted defect area becomes smoother, thereby avoiding distortion problems in subsequent frequency domain filtering operations.

[0066] Step S4: Perform frequency domain filtering on the smoothed image to obtain a filtered image.

[0067] Specifically, frequency domain filtering is an effective image processing method that can remove noise or unwanted periodic patterns of specific frequency components in an image. The obtained smoothed image is converted to the frequency domain, for example, by discrete Fourier transform (DFT) and other methods. In the frequency domain, according to the characteristics of the noise or interference, corresponding filters are designed, such as low-pass filters (for removing high-frequency noise), high-pass filters (for enhancing high-frequency information such as edges), or band-pass filters (allowing frequency components in a specific frequency band to pass). The frequency domain image data processed by the filter is subjected to inverse Fourier transform and other operations to obtain a processed filtered image, which reduces noise and interference while retaining effective information.

[0068] Step S5: superimpose the difference image on the corresponding area of ​​the filtered image to obtain the final image to be inspected.

[0069] Specifically, based on the positional correspondence between the difference image and the highlighted defect area, the difference image is accurately superimposed on the corresponding highlighted defect area on the filtered image. This pixel-by-pixel overlay combines the advantages of smoothing and frequency-domain filtering to preserve the image's characteristic information while highlighting the defect information, ultimately resulting in the final image to be inspected. This final image can provide a more accurate data foundation for subsequent defect analysis, dimensional measurement, and other processes.

[0070] The wafer image preprocessing method of this embodiment locates and separates the highlighted defect area in the wafer diffraction image, then performs frequency domain filtering on the rest of the image, and finally superimposes the difference image corresponding to the highlighted defect area onto the filtered image to complete image reconstruction. The reconstructed image retains the morphological characteristics of the highlighted defects while filtering out noise, and will not affect the subsequent defect detection and classification, thereby improving the accuracy of defect detection.

[0071] Figure 2 FIG is a functional module diagram of a wafer image preprocessing device according to an embodiment of the present invention. Figure 2 As shown, the wafer image pre-processing device 20 includes: an acquisition module 21 , a positioning module 22 , a smoothing module 23 , a filtering module 24 and a reconstruction module 25 .

[0072] An acquisition module 21 is used to acquire an initial image of the wafer to be tested;

[0073] A positioning module 22 is used to estimate the noise distribution of the initial image to be inspected and locate the highlighted defect area in the initial image to be inspected;

[0074] A smoothing processing module 23 is used to smooth the highlighted defect area to obtain a smoothed image and a difference image between the highlighted defect area and the corresponding area on the smoothed image;

[0075] A filtering module 24 is configured to perform a frequency domain filtering operation on the smoothed image to obtain a filtered image;

[0076] The reconstruction module 25 is used to superimpose the difference image on the corresponding area of ​​the filtered image to obtain the final image to be inspected.

[0077] Optionally, the positioning module 22 performs noise distribution estimation on the initial image to be inspected and locates the highlighted defect area in the initial image to be inspected, specifically including: extracting the reference pixel values ​​of all reference pixels within a preset neighborhood range of each pixel point, and using the reference pixel values ​​to calculate the first eigenvalue and the second eigenvalue of each pixel point; calculating the pixel threshold of each pixel based on the first eigenvalue and the second eigenvalue; and taking the area composed of pixels whose pixel values ​​exceed the pixel threshold as the highlighted defect area.

[0078] Optionally, the first eigenvalue includes a median or mean of all reference pixel values ​​within a preset neighborhood, and the second eigenvalue includes a first variance value of all reference pixel values ​​within a preset neighborhood. The calculation process of the pixel threshold is expressed as follows:

[0079] T i =medain i +coeff1*std i ;

[0080] Among them, T i Represents the pixel threshold of the i-th pixel, medain i Indicates the median or mean corresponding to the i-th pixel, std i It represents the first variance value corresponding to the i-th pixel point, and coeff1 represents the preset noise estimation coefficient.

[0081] Optionally, the first eigenvalue includes a median or mean of all reference pixel values ​​within a preset neighborhood range, and the second eigenvalue includes a second variance value of all reference pixel values ​​within the preset neighborhood range. The second variance value is expressed as:

[0082] std j =coeff2*(medain j -min j );

[0083] Among them, std j Indicates the second variance value corresponding to the j-th pixel, medain j Indicates the median or mean corresponding to the j-th pixel, min j represents the minimum pixel value in the preset neighborhood corresponding to the j-th pixel point, and coeff2 represents the pre-calibrated parameter;

[0084] The calculation process of pixel threshold is expressed as:

[0085] T j =medain j +coeff1*[coeff2*(medain j -min j )];

[0086] Among them, T j represents the pixel threshold of the j-th pixel, and coeff1 represents the preset noise estimation coefficient.

[0087] Optionally, the preset neighborhood range is represented by all pixel points within a window of size M*N constructed with the pixel point as the center.

[0088] Optionally, the smoothing processing module 23 performs smoothing processing on the highlighted defect area to obtain a smoothed image and a difference image between the highlighted defect area and the corresponding area on the smoothed image, specifically including: obtaining the target pixel values ​​of all target pixel points in the highlighted defect area; calculating the difference between the target pixel value corresponding to each target pixel point and the corresponding first eigenvalue, and constructing a difference image based on the difference; replacing the pixel value of each target pixel point in the highlighted defect area with the corresponding first eigenvalue to obtain a smoothed image.

[0089] For other details about the technical solutions for implementing each module in the wafer image preprocessing device in the above embodiment, please refer to the description of the wafer image preprocessing method in the above embodiment, which will not be repeated here.

[0090] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similarities between the various embodiments can be referred to in conjunction with each other. For device embodiments, since they are generally similar to method embodiments, their description is relatively simple, and for relevant details, reference can be made to the description of the method embodiments.

[0091] See also Figure 3 , Figure 3 FIG. 1 is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. Figure 3 As shown, the computer device 30 includes a processor 31 and a memory 32 coupled to the processor 31. The memory 32 stores program instructions. When the program instructions are executed by the processor 31, the processor 31 executes the steps of the wafer image preprocessing method described in any of the above embodiments.

[0092] The processor 31 may also be referred to as a resource (Central Processing Unit). The processor 31 may be an integrated circuit chip having signal processing capabilities. The processor 31 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. The general-purpose processor may be a microprocessor or any conventional processor.

[0093] See Figure 4 , Figure 4 Schematic diagram of the structure of the storage medium of an embodiment of the present invention. The storage medium of an embodiment of the present invention stores program instructions 41 that can implement the above-mentioned wafer image preprocessing method, wherein the program instructions 41 can be stored in the above-mentioned storage medium in the form of a software product, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or a computer device such as a computer, a server, a mobile phone, or a tablet.

[0094] In the several embodiments provided in this application, it should be understood that the disclosed computer devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0095] In addition, the functional units in the various embodiments of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the description and drawings of this application, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A wafer image preprocessing method, characterized in that: It includes: Acquire an initial inspection image of the wafer to be tested; performing noise distribution estimation on the initial image to be inspected, and locating a highlighted defect area in the initial image to be inspected; Smoothing the highlighted defect area to obtain a smoothed image and a difference image between the highlighted defect area and a corresponding area on the smoothed image; Performing a frequency domain filtering operation on the smoothed image to obtain a filtered image; The difference image is superimposed on the corresponding area of ​​the filtered image to obtain a final image to be inspected.

2. The wafer image preprocessing method according to claim 1, wherein: The estimating noise distribution of the initial image to be inspected and locating the highlight defect area in the initial image to be inspected includes: Extracting reference pixel values ​​of all reference pixels within a preset neighborhood of each pixel, and calculating a first eigenvalue and a second eigenvalue of each pixel using the reference pixel values; Calculating a pixel threshold for each pixel based on the first eigenvalue and the second eigenvalue; The area formed by pixels whose pixel values ​​exceed the pixel threshold is regarded as the highlight defect area.

3. The wafer image preprocessing method according to claim 2, wherein: The first eigenvalue includes a median or mean of all reference pixel values ​​within a preset neighborhood range, and the second eigenvalue includes a first variance value of all reference pixel values ​​within a preset neighborhood range; The calculation process of the pixel threshold is expressed as: T i =medain i +coeff1*std i ; Among them, T i Represents the pixel threshold of the i-th pixel, medain i Indicates the median or mean corresponding to the i-th pixel, std i It represents the first variance value corresponding to the i-th pixel point, and coeff1 represents the preset noise estimation coefficient.

4. The wafer image preprocessing method according to claim 2, wherein: The first eigenvalue includes the median or mean of all reference pixel values ​​within a preset neighborhood range, and the second eigenvalue includes a second variance value of all reference pixel values ​​within a preset neighborhood range. The second variance value is expressed as: std j =coeff2*(medain j -min j ); Among them, std j Indicates the second variance value corresponding to the j-th pixel, medain j Indicates the median or mean corresponding to the j-th pixel, min j represents the minimum pixel value in the preset neighborhood corresponding to the j-th pixel point, and coeff2 represents the pre-calibrated parameter; The calculation process of the pixel threshold is expressed as: T j =medain j +coeff1*[coeff2*(medain j -min j )]; Among them, T j represents the pixel threshold of the j-th pixel, and coeff1 represents the preset noise estimation coefficient.

5. The wafer image preprocessing method according to any one of claims 2 to 4, characterized in that: The preset neighborhood range is represented by all pixel points within a window of size M*N constructed with the pixel point as the center.

6. The wafer image preprocessing method according to any one of claims 2 to 5, characterized in that: The step of smoothing the highlighted defect area to obtain a smoothed image and a difference image between the highlighted defect area and a corresponding area on the smoothed image includes: Obtain target pixel values ​​of all target pixels in the highlighted defect area; Calculating the difference between the target pixel value corresponding to each target pixel point and the corresponding first eigenvalue, and constructing the difference image based on the difference; The pixel value of each target pixel in the highlighted defect area is replaced with the corresponding first eigenvalue to obtain the smoothed image.

7. A wafer image preprocessing device, characterized in that: It includes: An acquisition module is used to acquire an initial image of the wafer to be tested; A positioning module, configured to estimate the noise distribution of the initial image to be inspected and locate a highlighted defect area in the initial image to be inspected; a smoothing processing module, configured to perform smoothing on the highlighted defect area to obtain a smoothed image and a difference image between the highlighted defect area and a corresponding area on the smoothed image; A filtering module, configured to perform a frequency domain filtering operation on the smoothed image to obtain a filtered image; The reconstruction module is used to superimpose the difference image on the corresponding area of ​​the filtered image to obtain a final image to be inspected.

8. A computer device, characterized in that: The computer device includes a processor and a memory coupled to the processor, wherein program instructions are stored in the memory. When the program instructions are executed by the processor, the processor performs the steps of the wafer image preprocessing method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: Program instructions capable of implementing the wafer image preprocessing method according to any one of claims 1 to 6 are stored.

Images