Method and system for controlling image brightness in crystal pulling process and crystal pulling furnace
By dividing the image brightness region and adjusting the brightness during the straight-pullization process, the target capture failure problem caused by abnormal image brightness is solved, accurate liquid level spacing measurement is achieved, and high-quality single crystal silicon growth is supported.
Patent Information
- Application Number
- CN202510804226.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-16
- Publication Date
- 2025-08-15
AI Technical Summary
During the direct-pullization process of single crystal silicon growth, abnormal image brightness leads to target capture failure, making it difficult to accurately measure the liquid level spacing, affecting the high-quality growth of single crystal silicon.
By reading the grayscale map collected by the image acquisition component, dividing it into multiple areas, and determining and adjusting areas whose brightness does not meet the requirements, ensuring that the brightness of all areas meets the requirements, using median filtering, canny edge detection and K-means algorithm to capture the target.
Targeted adjustment of local brightness is achieved, overexposed or underexposed problems are reduced, targets are accurately captured, and the accurate measurement of liquid level spacing is supported, and high-quality growth of single crystal silicon is supported.
Smart Images
Figure CN120485940A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of semiconductor technology, and in particular to a method for controlling image brightness during a crystal pulling process, a control system, and a crystal pulling furnace. Background Art
[0002] The Czochralski method (also known as the Czochralski method) is a process of growing single crystal silicon. The polysilicon material in the quartz crucible is heated to melt it into a silicon melt. A seed crystal is then immersed in the silicon melt and pulled upward to grow single crystal silicon.
[0003] During the Czochralski method of growing single crystal silicon, in order to ensure high-quality growth of single crystal silicon, it is necessary to measure the distance between the guide tube and the liquid level of the silicon melt in the quartz crucible (i.e., the liquid level distance) in real time.
[0004] In the related art, the reflection method is generally used to measure the liquid level distance. For example, a quartz positioning pin is installed on the guide tube. After using a charge coupled device (CCD) camera to obtain an image showing the quartz positioning pin and its reflection on the liquid surface of the silicon melt, the target point (the bright spot of the quartz positioning pin and its reflection bright spot) is captured on the image, and then the liquid level distance is calculated based on the position information of the target point.
[0005] However, related technologies often encounter the problem of target capture failure due to abnormal image brightness, which makes it difficult to accurately measure the liquid level distance, and is not conducive to the high-quality growth of single crystal silicon. Summary of the Invention
[0006] The Summary of the Invention introduces a series of simplified concepts that will be further described in the Detailed Description of the Invention. The Summary of the Invention of this application is not intended to limit the key features and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.
[0007] In response to the current problems, this application provides a method including:
[0008] Step S1: reading an image captured by an image acquisition element to obtain a grayscale image showing a positioning element located above the liquid surface of the silicon melt and a reflection of the positioning element on the liquid surface of the silicon melt;
[0009] Step S2: Divide the grayscale image into multiple regions;
[0010] Step S3: determining whether there is an area in the grayscale image whose brightness does not meet the requirements, and if so, adjusting the brightness of the area whose brightness does not meet the requirements so that the brightness of all the areas meets the requirements.
[0011] Exemplarily, each of the regions corresponds to a preset number of pixels;
[0012] Determining whether there is an area whose brightness does not meet the requirement includes: for each area, obtaining the number of pixels in the area whose grayscale value is greater than a preset grayscale value, recording it as a first pixel number, comparing the first pixel number of the area with the preset pixel number corresponding to the area, and when a difference between the first pixel number of the area and the preset pixel number corresponding to the area falls outside a preset difference range, determining that the brightness of the area does not meet the requirement;
[0013] Adjusting the brightness of the area whose brightness does not meet the requirement includes: for each area whose brightness does not meet the requirement, adjusting the brightness of the area by adjusting the grayscale values of pixels in the area.
[0014] Exemplarily, the brightness not meeting the requirement includes two situations: the brightness is too high and the brightness is too low. When the difference between the first number of pixels in the area and the preset number of pixels corresponding to the area is less than the minimum value of the preset difference range, it is determined that the brightness of the area is too low. When the difference between the first number of pixels in the area and the preset number of pixels corresponding to the area is greater than the maximum value of the preset difference range, it is determined that the brightness of the area is too high, wherein the minimum value of the preset difference range is less than 0 and the maximum value is greater than 0.
[0015] After executing step S2 and before executing step S3, the method further includes: determining whether the brightness of all the areas is too low or too high; if so, adjusting the exposure of the image acquisition element and returning to step S1.
[0016] Exemplarily, adjusting the exposure of the image acquisition element includes:
[0017] The adjusted exposure of the image acquisition element is obtained based on the current exposure of the image acquisition element, the first empirical coefficient, the sum of the preset numbers of pixels corresponding to all the areas, and the sum of the first numbers of pixels in all the areas.
[0018] Exemplarily, the adjusted exposure of the image acquisition element is obtained by the following formula based on the current exposure of the image acquisition element, the first empirical coefficient, the sum of the preset numbers of pixels corresponding to all the areas, and the sum of the first numbers of pixels in all the areas:
[0019] B=B0+K1*(T sum -S sum )
[0020] Wherein, B represents the exposure of the image acquisition element after adjustment, B0 represents the current exposure of the image acquisition element, K1 represents the first empirical coefficient, T sum represents the sum of the preset number of pixels corresponding to all the areas, S sum Represents the sum of the number of first pixels in all the areas.
[0021] Exemplarily, for each area whose brightness does not meet the requirement, adjusting the brightness of the area by adjusting the grayscale values of pixels in the area includes:
[0022] For each pixel in the area, the adjusted grayscale value of the pixel is obtained based on the current grayscale value of the pixel, the second empirical coefficient, the preset number of pixels corresponding to the area where the pixel is located, and the first number of pixels in the area where the pixel is located.
[0023] Exemplarily, the adjusted grayscale value of the pixel is obtained by the following formula based on the current grayscale value of the pixel, the second empirical coefficient, the preset number of pixels corresponding to the area where the pixel is located, and the first number of pixels in the area where the pixel is located:
[0024] G n =min(max(G n0 *K2*(T n -S n ), 0), 255)
[0025] Among them, G n Represents the grayscale value of the pixel after adjustment, G n0 represents the current grayscale value of the pixel, K2 represents the second empirical coefficient, T n Indicates the preset number of pixels corresponding to the area where the pixel is located, S n Indicates the number of first pixels in the area where the pixel is located.
[0026] Exemplarily, the preset difference range is [-10, 10].
[0027] Exemplarily, the positioning element is provided on the guide tube; and / or
[0028] The positioning element comprises a quartz positioning pin; and / or
[0029] The image acquisition element includes a CCD camera.
[0030] Exemplarily, after executing step S3, the method further includes:
[0031] Using a median filtering method to perform noise removal on the grayscale image;
[0032] Using the Canny edge detection algorithm to perform edge recognition on the grayscale image;
[0033] Using a mask algorithm to remove interference items in the grayscale image;
[0034] Using K-means algorithm to capture the target points in the grayscale image;
[0035] Based on the position information of the target point, the distance between the positioning element and the liquid surface of the silicon melt is obtained.
[0036] On the other hand, the present application provides a control system for image brightness during a crystal pulling process, comprising a memory and a processor, wherein the memory stores a computer program run by the processor, and when the computer program is run, the processor executes the above-mentioned method for controlling image brightness during the crystal pulling process.
[0037] In another aspect, the present application provides a crystal pulling furnace, comprising:
[0038] An image acquisition component, used for acquiring images;
[0039] A positioning element, located above the liquid surface of the silicon melt;
[0040] The image brightness control system during the above-mentioned crystal pulling process.
[0041] The method, control system and crystal pulling furnace for controlling image brightness during the crystal pulling process of the embodiments of the present application divide the grayscale image into multiple areas, and determine whether the brightness of each area meets the requirements. The brightness of the areas that do not meet the requirements is adjusted so that the brightness of all areas meets the requirements. The brightness of different areas in the grayscale image can be adjusted separately, that is, the local brightness can be adjusted in a targeted manner without affecting the brightness of other areas, thereby reducing overexposure or underexposure problems, and thus accurately capturing the target in the grayscale image. BRIEF DESCRIPTION OF THE DRAWINGS
[0042] The following drawings of the present application are used as part of the present application for understanding the present application. The drawings show embodiments of the present application and their descriptions, which are used to explain the principle of the present application.
[0043] In the attached figure:
[0044] Figure 1 A schematic diagram showing target capture failure due to abnormal image brightness in the related art is shown;
[0045] Figure 2 A schematic flow chart showing a method for controlling image brightness during a crystal pulling process according to an exemplary embodiment of the present application is shown;
[0046] Figure 3A schematic diagram showing a target capture method according to an exemplary embodiment of the present application is shown;
[0047] Figure 4 A schematic flow chart of capturing a target according to an exemplary embodiment of the present application is shown;
[0048] Figure 5 A schematic structural block diagram of a control system for image brightness during a crystal pulling process according to an exemplary embodiment of the present application is shown. DETAILED DESCRIPTION
[0049] Next, the present application will be described more fully in conjunction with the accompanying drawings, which illustrate embodiments of the present application. However, the present application can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to make the disclosure thorough and complete and to fully convey the scope of the present application to those skilled in the art. In the drawings, the sizes and relative sizes of layers and regions may be exaggerated for clarity. Like reference numerals throughout represent like elements.
[0050] It should be understood that when an element or layer is referred to as being "on," "adjacent to," "connected to," or "coupled to" another element or layer, it may be directly on, adjacent to, connected to, or coupled to the other element or layer, or there may be intervening elements or layers. Conversely, when an element is referred to as being "directly on," "directly adjacent to," "directly connected to," or "directly coupled to" another element or layer, there may be no intervening elements or layers. It should be understood that although the terms first, second, third, etc. may be used to describe various elements, components, regions, layers, and / or parts, these elements, components, regions, layers, and / or parts should not be limited by these terms. These terms are merely used to distinguish one element, component, region, layer, or part from another element, component, region, layer, or part. Therefore, without departing from the teachings of the present application, the first element, component, region, layer, or part discussed below may be represented as a second element, component, region, layer, or part.
[0051] Spatially relative terms such as "under," "beneath," "below," "under," "above," "above," etc., may be used herein for convenience of description to describe the relationship of one element or feature shown in the figures to other elements or features. It should be understood that the spatially relative terms are intended to include different orientations of the device in use and operation in addition to the orientations shown in the figures. For example, if the device in the drawings is flipped, then the elements or features described as "under" or "beneath" or "beneath" the other elements will be oriented as "over" the other elements or features. Thus, the exemplary terms "under" and "under" may include both the upper and lower orientations. The device may be oriented otherwise (rotated 90 degrees or in other orientations) and the spatial descriptors used herein are interpreted accordingly.
[0052] The purpose of the terms used herein is only to describe specific embodiments and is not intended to limit the present application. When used herein, the singular forms "a", "an", and "said / the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "comprising" and / or "including", when used in this specification, determine the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.
[0053] Embodiments of the application are described herein with reference to cross-sectional views which are schematic illustrations of ideal embodiments (and intermediate structures) of the application. As such, variations from the shapes shown due to, for example, manufacturing techniques and / or tolerances can be expected. Therefore, embodiments of the application should not be limited to the specific shapes of the regions shown herein, but rather include deviations in shapes due to, for example, manufacturing. For example, an implanted region shown as a rectangle typically has rounded or curved features and / or an implant concentration gradient at its edges, rather than a binary change from an implanted region to a non-implanted region. Similarly, a buried region formed by implantation may result in some implantation in the region between the buried region and the surface through which the implantation is performed. Therefore, the regions shown in the figures are schematic in nature, and their shapes are not intended to illustrate the actual shape of the region of the device and are not intended to limit the scope of the application.
[0054] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application relates. It will also be understood that terms such as those defined in commonly used dictionaries should be understood to have a meaning consistent with their meaning in the context of the relevant art and / or this specification, and should not be interpreted in an idealized or overly formal sense unless expressly defined as such herein.
[0055] In order to fully understand the present application, detailed steps and structures will be presented in the following description to illustrate the technical solution proposed by the present application. The preferred embodiments of the present application are described in detail below. However, in addition to these detailed descriptions, the present application may also have other implementation methods.
[0056] To ensure high-quality single-crystal silicon growth using the Czochralski method, real-time measurement of the liquid-to-liquid gap is required. This is typically done through reflection. For example, a quartz dowel pin is mounted on a guide tube. A CCD camera captures an image of the dowel pin and its reflection on the silicon melt surface. Edge recognition is then performed on this image, and a target point is captured on the image. The liquid-to-liquid gap is then calculated based on the target's position.
[0057] However, if Figure 1 As shown in Figure (a), the brightness of the image captured by the CCD camera is prone to abnormality. When the image brightness is abnormal, such as Figure 1 As shown in Figure (b), after edge recognition of the image, too many interference items will appear, which will lead to the following when capturing the target: Figure 1 As shown in Figure (c), target capture failure occurs ( Figure 1 The red dot in Figure (c) is the captured target, but the target is the wrong target), which makes it difficult to accurately measure the liquid level distance, which is not conducive to the high-quality growth of single crystal silicon.
[0058] Under related technologies, attempts to solve the problem of target capture failure are generally made by adjusting the overall brightness of the image. However, this method may not work at times and often requires further replacement of observation window glass and hardware equipment such as cameras. At the same time, adjusting the overall brightness of the image will cause the overall brightness of the image to change, and cannot solve the problem of abnormal local brightness of the image. For images with abnormal local brightness, for example, the brightness of one target point needs to be adjusted, adjusting the overall brightness will cause overexposure or underexposure in the local area, affecting the capture of other targets.
[0059] Therefore, in view of the existence of the above technical problems, this application proposes a method for controlling the image brightness during the crystal pulling process, such as Figure 2 As shown, it includes the following steps:
[0060] Step S1: reading an image captured by an image acquisition element to obtain a grayscale image showing a positioning element located above the liquid surface of the silicon melt and a reflection of the positioning element on the liquid surface of the silicon melt;
[0061] Step S2: Divide the grayscale image into multiple regions;
[0062] Step S3: Determine whether there is an area in the grayscale image whose brightness does not meet the requirements. If so, adjust the brightness of the area whose brightness does not meet the requirements so that the brightness of all areas meets the requirements.
[0063] The method for controlling image brightness during the crystal pulling process in an embodiment of the present application divides the grayscale image into multiple areas, and determines whether the brightness of each area meets the requirements. The brightness of the areas that do not meet the requirements is adjusted so that the brightness of all areas meets the requirements. The brightness of different areas in the grayscale image can be adjusted separately, that is, the local brightness can be adjusted in a targeted manner without affecting the brightness of other areas, reducing overexposure or underexposure problems, so that the target in the grayscale image can be accurately captured.
[0064] Below, reference Figures 2 to 4 The method for controlling the image brightness during the crystal pulling process of the present application is described in detail, wherein: Figure 2 A schematic flow chart showing a method for controlling image brightness during a crystal pulling process according to an exemplary embodiment of the present application is shown. Figure 3 A schematic diagram showing a target capture method according to an exemplary embodiment of the present application is shown. Figure 4 A schematic flowchart of capturing a target according to an exemplary embodiment of the present application is shown.
[0065] For example, Figure 2 As shown, the method 100 for controlling image brightness during the crystal pulling process of the present application includes the following steps:
[0066] First, step S1 is performed: an image captured by an image capturing element is read to obtain a grayscale image showing the positioning element located above the liquid surface of the silicon melt and the reflection of the positioning element on the liquid surface of the silicon melt.
[0067] In one example, an image capture element can be positioned in a suitable position to capture an image showing a positioning element located above the surface of a silicon melt and its reflection on the surface of the silicon melt during a crystal pulling process, wherein the crystal pulling process refers to the process of growing single crystal silicon using the Czochralski method in a crystal pulling furnace. The image captured by the image capture element can be a color image, which is converted to a grayscale image after reading the color image; alternatively, the image captured by the image capture element can be a grayscale image. Exemplarily, the image capture element includes a CCD camera or any other suitable element capable of capturing an image.
[0068] In one example, the positioning element is disposed on the guide tube. The specific arrangement of the positioning element on the guide tube is not limited. For example, the positioning element can be disposed at the bottom of the guide tube and extend downwardly a distance beyond the bottom. Exemplarily, the guide tube is located above the liquid surface of the silicon melt and is used to guide airflow within the crystal pulling furnace.
[0069] In one example, the positioning element includes a quartz positioning pin, or the positioning element may be any other suitable element. For example, the positioning element may be the guide tube itself.
[0070] Next, step S2 is performed: dividing the grayscale image into a plurality of regions. Specifically, the grayscale image can be reasonably divided according to the actual grayscale image to divide the grayscale image into a plurality of regions. The grayscale image can be divided manually or automatically by an algorithm.
[0071] Next, step S3 is executed to determine whether there is an area in the grayscale image whose brightness does not meet the requirements. If there is, the brightness of the area that does not meet the requirements is adjusted so that the brightness of all areas meets the requirements.
[0072] In one example, by dividing the grayscale image into multiple areas and determining whether the brightness of each area meets the requirements, the brightness of the areas that do not meet the requirements is adjusted so that the brightness of all areas meets the requirements. The brightness of different areas in the grayscale image can be adjusted separately, that is, the local brightness can be adjusted in a targeted manner without affecting the brightness of other areas, reducing overexposure or underexposure problems, and thus accurately capturing the target in the grayscale image.
[0073] In one example, in a grayscale image, each pixel has only one color channel, represented by a grayscale value. The grayscale value of a pixel ranges from [0, 255], where 0 represents black, 255 represents white, and grayscale values between 0 and 255 represent different shades of gray. In a grayscale image, the grayscale value of each pixel directly determines the brightness of the pixel; higher grayscale values indicate higher brightness.
[0074] In one example, each region in the grayscale image corresponds to a preset number of pixels, and the preset number of pixels is set separately for each region.
[0075] In one example, determining whether there is an area in which the brightness does not meet the requirements includes: for each area, obtaining the number of pixels in the area whose grayscale value is greater than a preset grayscale value, recorded as the first pixel number, comparing the first pixel number of the area with the preset pixel number corresponding to the area, and when the difference between the first pixel number of the area and the preset pixel number corresponding to the area falls outside the preset difference range, determining that the brightness of the area does not meet the requirements. Exemplarily, for each area, when the difference between the first pixel number of the area and the preset pixel number corresponding to the area falls within the preset difference range, determining that the brightness of the area meets the requirements. The difference between the first pixel number and the preset pixel number refers to the value obtained by subtracting the preset pixel number from the first pixel number. Exemplarily, the preset difference range is [-10, 10], or the preset difference range can also be any other suitable range.
[0076] In one example, adjusting the brightness of the region whose brightness does not meet the requirement includes: for each region whose brightness does not meet the requirement, adjusting the brightness of the region by adjusting the grayscale values of pixels in the region.
[0077] In one example, for each area whose brightness does not meet the requirements, the brightness of the area is adjusted by adjusting the grayscale value of the pixels in the area, including: for each pixel in the area, based on the current grayscale value of the pixel, the second empirical coefficient, the preset number of pixels corresponding to the area where the pixel is located, and the first number of pixels in the area where the pixel is located, the adjusted grayscale value of the pixel is obtained.
[0078] In one example, the adjusted grayscale value of the pixel is obtained by the following formula based on the current grayscale value of the pixel, the second empirical coefficient, the preset number of pixels corresponding to the area where the pixel is located, and the first number of pixels in the area where the pixel is located:
[0079] G n =min(max(G n0 *K2*(T n -S n ), 0), 255)
[0080] Among them, G n Represents the grayscale value of the adjusted pixel, G n0 represents the current grayscale value of the pixel, K2 represents the second empirical coefficient, T n Indicates the preset number of pixels corresponding to the area where the pixel is located, S n Indicates the first number of pixels in the area where the pixel is located. For example, the second empirical coefficient K2 can be reasonably set according to actual needs.
[0081] In one example, the brightness does not meet the requirements, including two situations: the brightness is too high and the brightness is too low. When the difference between the first number of pixels in the region and the preset number of pixels corresponding to the region is less than the minimum value of the preset difference range, the brightness of the region is determined to be too low. When the difference between the first number of pixels in the region and the preset number of pixels corresponding to the region is greater than the maximum value of the preset difference range, the brightness of the region is determined to be too high. The minimum value of the preset difference range is less than 0 and the maximum value is greater than 0. Exemplarily, the preset difference range is [-10, 10], or the preset difference range can also be any other suitable range. Taking the preset difference range of [-10, 10] as an example, when the difference between the first number of pixels in the region and the preset number of pixels corresponding to the region is less than -10, the brightness of the region is determined to be too low; when the difference between the first number of pixels in the region and the preset number of pixels corresponding to the region is greater than 10, the brightness of the region is determined to be too high.
[0082] In one example, after executing step S2 and before executing step S3, the process further includes: determining whether the brightness of all areas is too low or too high; if so, adjusting the exposure of the image acquisition element and returning to step S1.
[0083] In one example, the exposure of an image acquisition element refers to the amount of light received by the photosensitive element in the image acquisition element during the image acquisition process. The higher the exposure, the brighter the image. For example, taking the image acquisition element as a CCD camera, the exposure can be adjusted by adjusting the aperture, shutter speed, and ISO value.
[0084] In one example, when the brightness of all areas is too low or too high, adjusting the exposure of the image acquisition element can make a preliminary adjustment to the overall brightness of the image, compared to adjusting the brightness of each area individually. This is simpler, more efficient, and can save time. For example, adjusting the exposure of the image acquisition element can make the brightness of most areas meet the requirements, thereby reducing the number of areas that need to adjust the brightness individually later. It is worth noting that the accuracy of local brightness adjustment by adjusting the exposure of the image acquisition element is lower than the accuracy of local brightness adjustment by adjusting the brightness of each area individually. Adjusting the exposure of the image acquisition element may not make the brightness of all areas meet the requirements. Therefore, after adjusting the exposure of the image acquisition element, it is necessary to return to step S1 and re-execute the above steps.
[0085] In one example, adjusting the exposure of an image acquisition element includes obtaining the adjusted exposure of the image acquisition element based on the current exposure of the image acquisition element, a first empirical coefficient, the sum of the preset number of pixels corresponding to all areas, and the sum of the first number of pixels in all areas.
[0086] In one example, the adjusted exposure of the image acquisition element is obtained by the following formula based on the current exposure of the image acquisition element, the first empirical coefficient, the sum of the preset number of pixels corresponding to all areas, and the sum of the first number of pixels in all areas:
[0087] B=B0+K1*(T sum -S sum )
[0088] Wherein, B represents the exposure of the image acquisition element after adjustment, B0 represents the current exposure of the image acquisition element, K1 represents the first empirical coefficient, T sum Represents the sum of the preset number of pixels corresponding to all areas, S sum Represents the sum of the first pixel numbers of all regions. For example, the first empirical coefficient K1 can be reasonably set according to actual needs.
[0089] In one example, after executing step S3, the method further includes: using a median filter to denoise the grayscale image; using a canny edge detection algorithm to identify edges in the grayscale image; using a mask algorithm to remove interference items in the grayscale image; using a K-means algorithm to capture the target point in the grayscale image; and obtaining the distance between the positioning element and the surface of the silicon melt based on the position information of the target point. For example, using the canny edge detection algorithm can accurately monitor the edges of the target object; using the mask algorithm can achieve region extraction and shielding tasks; and using the K-means algorithm can obtain the characteristic values of the bright spot cluster and use them as targets.
[0090] In one example, the target includes a bright spot of a positioning element and its reflection on the surface of a silicon melt. The positioning element is set on a guide tube. Based on the position information of the target, the distance between the positioning element and the surface of the silicon melt is obtained, including: based on the position information of the bright spot of the positioning element and its reflection on the surface of the silicon melt in a grayscale image, obtaining the distance between the bright spot and the reflection, and then obtaining the distance between the bright spot of the positioning element and the surface of the silicon melt, and then obtaining the distance between the guide tube and the surface of the silicon melt (i.e., the liquid level distance). Exemplarily, the method of the present application can adjust the brightness of the grayscale image, and then accurately capture the target in the grayscale image, and then accurately measure the liquid level distance, which is conducive to the high-quality growth of single crystal silicon.
[0091] In one example, if Figure 3 As shown, Figure 3 Figure (a) is a grayscale image obtained by reading the image captured by the image acquisition element. The brightness adjustment method in the above embodiment (for example, by adjusting the grayscale value of the pixel and adjusting the exposure of the image acquisition element to adjust the brightness) is used to adjust the brightness of the grayscale image to obtain the following Figure 3 The image shown in Figure (b) (i.e. Figure 3 The image shown in (b) is the image obtained after executing step S3), and then denoising and edge recognition are performed to obtain the following Figure 3 The image shown in Figure (c) is then removed and the target is captured to obtain the following Figure 3 The image shown in Figure (d) shows that the red dot is the captured target.
[0092] In one example, as a combination of the above embodiments, Figure 4 As shown, the target capture process is described in detail:
[0093] First, an image captured by an image acquisition element is read to obtain a grayscale image showing a positioning element located above a liquid surface of the silicon melt and a reflection of the positioning element on the liquid surface of the silicon melt;
[0094] Next, the grayscale image is divided into multiple regions;
[0095] Next, determining whether the brightness of all areas is too low or too high; if so, adjusting the exposure of the image acquisition component and returning to the step of obtaining the grayscale image; if not, determining whether there is an area in the grayscale image whose brightness does not meet the requirements; if so, adjusting the brightness of the area that does not meet the requirements by adjusting the grayscale values of the pixels in the area that does not meet the requirements, so that the brightness of all areas meets the requirements;
[0096] When the brightness of all areas meets the requirements, the following steps are performed in sequence: the median filtering method is used to denoise the grayscale image; the canny edge detection algorithm is used to identify the edges of the grayscale image; the mask algorithm is used to remove interference items in the grayscale image; and the K-means algorithm is used to capture the target points in the grayscale image.
[0097] This completes the description of the key steps of the method for controlling image brightness during the crystal pulling process of the present application. The complete method may also include other steps, which will not be detailed here one by one. It is worth mentioning that the order of the above steps can be adjusted without conflict.
[0098] In summary, the method for controlling image brightness during the crystal pulling process of the embodiment of the present application divides the grayscale image into multiple regions, determines whether the brightness of each region meets the requirements, and adjusts the brightness of the regions that do not meet the requirements so that the brightness of all regions meets the requirements. This method can adjust the brightness of different regions in the grayscale image separately, that is, it can make targeted adjustments to the local brightness without affecting the brightness of other regions, reducing overexposure or underexposure problems, and thus accurately capturing the target in the grayscale image. For example, when it is determined that the brightness of all regions is low or high, adjusting the exposure of the image acquisition element can make a preliminary adjustment to the overall brightness of the image, which is simpler, more efficient, and can save time.
[0099] The following combination Figure 5 The image brightness control system 200 provided in accordance with another aspect of the present application is described as follows: Figure 5 As shown, the control system 200 for the image brightness during the crystal pulling process includes a memory 210 and a processor 220. The memory 210 stores a computer program run by the processor 220. When the computer program is running, the processor 220 executes the aforementioned method 100 for controlling the image brightness during the crystal pulling process according to the embodiment of the present application. Those skilled in the art can understand the structure and operation of the control system 200 for the image brightness during the crystal pulling process in combination with the foregoing description. For the sake of brevity, they will not be repeated here.
[0100] The present application also provides a crystal pulling furnace comprising an image capture element, a positioning element, and a control system for controlling image brightness during the crystal pulling process. The image capture element is configured to capture images, and the positioning element is positioned above the surface of the molten silicon liquid. For example, the image capture element is positioned so as to capture an image showing the positioning element positioned above the surface of the molten silicon liquid and its reflection on the surface of the molten silicon liquid during the crystal pulling process.
[0101] Exemplarily, the crystal pulling furnace may further include other component structures, such as a quartz crucible and a graphite crucible, etc., which will not be described in detail here.
[0102] Although a number of embodiments are described herein, it should be understood that a variety of other modifications and embodiments may be devised by those skilled in the art, all of which fall within the spirit and scope of the concepts disclosed herein. More particularly, within the scope of the present disclosure, the accompanying drawings, and the appended claims, various modifications and changes may be made to the arrangements and / or components of the subject matter in combination. In addition to modifications and changes to the components and / or arrangements, the use of alternatives will also be readily apparent to those skilled in the art.
Claims
1. A method for controlling image brightness during crystal pulling, characterized in that: include: Step S1: reading an image captured by an image acquisition element to obtain a grayscale image showing a positioning element located above the liquid surface of the silicon melt and a reflection of the positioning element on the liquid surface of the silicon melt; Step S2: Divide the grayscale image into multiple regions; Step S3: determining whether there is an area in the grayscale image whose brightness does not meet the requirements, and if so, adjusting the brightness of the area whose brightness does not meet the requirements so that the brightness of all the areas meets the requirements.
2. The method according to claim 1, characterized in that Each of the regions corresponds to a preset number of pixels; Determining whether there is an area whose brightness does not meet the requirement includes: for each area, obtaining the number of pixels in the area whose grayscale value is greater than a preset grayscale value, recording it as a first pixel number, comparing the first pixel number of the area with the preset pixel number corresponding to the area, and when a difference between the first pixel number of the area and the preset pixel number corresponding to the area falls outside a preset difference range, determining that the brightness of the area does not meet the requirement; Adjusting the brightness of the area whose brightness does not meet the requirement includes: for each area whose brightness does not meet the requirement, adjusting the brightness of the area by adjusting the grayscale values of pixels in the area.
3. The method according to claim 2, characterized in that The brightness does not meet the requirements, including two situations: the brightness is too high and the brightness is too low. When the difference between the first number of pixels in the area and the preset number of pixels corresponding to the area is less than the minimum value of the preset difference range, it is determined that the brightness of the area is too low. When the difference between the first number of pixels in the area and the preset number of pixels corresponding to the area is greater than the maximum value of the preset difference range, it is determined that the brightness of the area is too high, wherein the minimum value of the preset difference range is less than 0 and the maximum value is greater than 0. After executing step S2 and before executing step S3, the method further includes: determining whether the brightness of all the areas is too low or too high; if so, adjusting the exposure of the image acquisition element and returning to step S1.
4. The method according to claim 3, characterized in that Adjusting the exposure of the image acquisition element includes: The adjusted exposure of the image acquisition element is obtained based on the current exposure of the image acquisition element, the first empirical coefficient, the sum of the preset numbers of pixels corresponding to all the areas, and the sum of the first numbers of pixels in all the areas.
5. The method according to claim 4, characterized in that The adjusted exposure of the image acquisition element is obtained by the following formula based on the current exposure of the image acquisition element, the first empirical coefficient, the sum of the preset numbers of pixels corresponding to all the areas, and the sum of the first numbers of pixels in all the areas: B=B0+K1*(T sum -S sum ) Wherein, B represents the exposure of the image acquisition element after adjustment, B0 represents the current exposure of the image acquisition element, K1 represents the first empirical coefficient, T sum represents the sum of the preset number of pixels corresponding to all the areas, S sum Represents the sum of the number of first pixels in all the areas.
6. The method according to claim 2, characterized in that For each area whose brightness does not meet the requirement, adjusting the brightness of the area by adjusting the grayscale values of pixels in the area, including: For each pixel in the area, the adjusted grayscale value of the pixel is obtained based on the current grayscale value of the pixel, the second empirical coefficient, the preset number of pixels corresponding to the area where the pixel is located, and the first number of pixels in the area where the pixel is located.
7. The method according to claim 6, characterized in that The adjusted grayscale value of the pixel is obtained by the following formula based on the current grayscale value of the pixel, the second empirical coefficient, the preset number of pixels corresponding to the area where the pixel is located, and the first number of pixels in the area where the pixel is located: G n =min(max(G n0 *K2*(T n -S n ),0),255) Among them, G n Represents the grayscale value of the pixel after adjustment, G n0 represents the current grayscale value of the pixel, K2 represents the second empirical coefficient, T n Indicates the preset number of pixels corresponding to the area where the pixel is located, S n Indicates the number of first pixels in the area where the pixel is located.
8. The method according to claim 3, characterized in that The preset difference range is [-10, 10].
9. The method according to claim 1, characterized in that The positioning element is arranged on the guide tube; and / or The positioning element comprises a quartz positioning pin; and / or The image acquisition element includes a CCD camera.
10. The method according to any one of claims 1 to 9, characterized in that After executing step S3, the method further includes: Using a median filtering method to perform noise removal on the grayscale image; Using the Canny edge detection algorithm to perform edge recognition on the grayscale image; Using a mask algorithm to remove interference items in the grayscale image; Using K-means algorithm to capture the target points in the grayscale image; Based on the position information of the target point, the distance between the positioning element and the liquid surface of the silicon melt is obtained.
11. A control system for image brightness during crystal pulling, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program to be run by the processor, and when the computer program is run, the processor executes the method for controlling the image brightness during the crystal pulling process according to any one of claims 1 to 10.
12. A crystal pulling furnace, characterized in that: include: An image acquisition component, used for acquiring images; Positioning element, located above the liquid level of the silicon melt ； The image brightness control system during the crystal pulling process as claimed in claim 11.