Cooling bed crystallizer surface state evaluation method and system

Abstract

The invention belongs to the technical field of image processing, and particularly relates to a cooling bed crystallizer surface state evaluation method and system, and the method comprises the steps: collecting an original image of the inner surface of a crystallizer; calculating a background estimation value of the target pixel point; subtracting the background estimation value from the gray value of each pixel point to obtain a detail image; for each pixel point in the detail image, determining the information entropy of the pixel point, clustering all the information entropies, and taking the maximum information entropy in a cluster of the most pixel points as a reference entropy; determining a dynamic regularization parameter of the pixel point according to the difference between the information entropy of the pixel point and the reference entropy; and carrying out filtering and threshold segmentation on the detail image by using the dynamic regularization parameter, counting the percentage of defect pixel points in the segmented image, and judging whether the surface state of the crystallizer is qualified or not. According to the method, the self-adaptive adjustment of the regularization parameters is realized, and the evaluation accuracy of the inner surface state of the crystallizer is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing. More particularly, the present application relates to a cold bed crystallizer surface state evaluation method and system. BACKGROUND

[0002] In the smelting process of metal materials, the cold bed crystallizer is the core mold component that determines the quality of the ingot. The inner cavity surface of the cold bed crystallizer directly contacts the high-temperature molten metal during the smelting process and causes it to solidify and form. The smoothness of the inner surface of the crystallizer has a decisive influence on the surface quality of the ingot. If there are scratches, pits, cracks or attachments left by previous smelting tasks on the surface of the crystallizer, these defects are extremely easy to reproduce when the ingot solidifies, resulting in surface defects of the ingot, which seriously affects the product performance and yield.

[0003] At present, the automatic detection method for the surface state of the crystallizer, such as the guided filter (Guided Filter) algorithm, uses a guide image to calculate the filter weight, which can smooth the image while maintaining the strong edges in the guide image, thereby distinguishing the surface texture and defects.

[0004] However, the guided filter algorithm relies on the gray scale information in its neighborhood range and a fixed regularization parameter when calculating the output value of each pixel point. The regularization parameter controls the sensitivity of the filter to the edge and is used to determine the retention and smoothing of the edge. Considering that there are regular machining textures on the inner surface of the crystallizer, if the regularization parameter value is set too small, the filter will be too sensitive and will retain all the machining textures as edges while retaining the defects, resulting in false positives. If the regularization parameter value is set too large, the filter will successfully smooth out the textures, but it will also smooth out the weak real defects at the same time, resulting in false negatives, which will affect the product quality. SUMMARY

[0005] To solve the technical problems of false positives and false negatives caused by the inability of the regularization parameter in the traditional guided filter to adapt, the present application provides solutions in the following aspects.

[0006] In a first aspect, the present application provides a cold bed crystallizer surface state evaluation method, comprising: collecting a crystallizer inner surface original image; taking any pixel point in the original image as a target pixel point, extracting the median of the gray values of all neighborhood pixel points in the neighborhood window of the target pixel point; determining a weight value according to the deviation of the gray value of each neighborhood pixel point from the median; obtaining a background estimation value of the target pixel point by weighted average of the gray values of all neighborhood pixel points according to the weight value; subtracting the gray value of each pixel point in the original image from the background estimation value to obtain the gray value of each pixel point in the detail image; for each pixel point in the detail image: statistics the probability of each gray level in the neighborhood window of the pixel point; determining the information entropy according to the probability of each gray level; clustering all information entropies, and taking the cluster containing the most pixel points as a texture cluster; taking the maximum value of the information entropy in the texture cluster as a reference entropy; determining the dynamic regularization parameter of the pixel point according to the difference between the information entropy of the pixel point and the reference entropy; filtering the detail image by using the dynamic regularization parameter of each pixel point, thresholding the filtered image, and statistics the percentage of defect pixel points in the thresholded binary image, and determining that the state is unqualified in response to the percentage being greater than a set threshold.

[0007] The present application first obtains a detail image by background estimation, calculates the information entropy of each pixel point in the detail image, automatically identifies the texture cluster containing the most pixel points by clustering all information entropies, and defines the maximum information entropy in the texture cluster as a reference entropy; generates a dynamic regularization parameter for each pixel point according to the difference between the information entropy of each pixel point and the reference entropy, ensures that the texture region obtains a larger parameter and the defect region obtains a smaller parameter, and this method effectively smooths the texture region while retaining defect details, thereby improving the accuracy of the evaluation of the inner surface state of the crystallizer.

[0008] Preferably, the weight value is equal to the reciprocal of the absolute difference between the gray value of each neighborhood pixel point and the median; and when the absolute difference is 0, the weight value is 1.

[0009] The present application uses the reciprocal of the absolute difference between the gray value of each pixel point and the normal gray level of its neighborhood as the weight, so that the pixel points with larger deviation from the normal gray level obtain lower weight, and the pixel points close to the normal gray level obtain higher weight, which can effectively reduce the interference of defect and other abnormal pixel points on the background estimation, make the background extraction purer, and ensure that the subsequent detail image only contains high-frequency textures and defects.

[0010] Preferably, the background estimation value of the target pixel point satisfies the expression: ; in the expression, is the background estimation value of the target pixel point; is the gray value of the i-th neighborhood pixel point in the neighborhood window of the target pixel point; and is the number of neighborhood pixel points in the neighborhood window of the target pixel point. Within the neighborhood window of the target pixel, the first The weight values ​​of each neighboring pixel; This refers to the index value and number of pixels within the neighborhood window of the target pixel.

[0011] This invention achieves a weighted average of neighboring pixels by acquiring weight values, ensuring that the background estimate can accurately reflect low-frequency illumination changes, while effectively eliminating interference from defective areas with high grayscale differences.

[0012] Preferably, the probability of each gray level within the neighborhood window of a pixel includes: counting the number of pixels at each gray level based on the gray values ​​of all pixels within the neighborhood window of each pixel, and calculating the probability of each gray level, wherein the probability is equal to the ratio of the number of pixels at each gray level to the number of all pixels within the neighborhood window.

[0013] Preferably, the information entropy satisfies the expression: In the formula, For the first Information entropy of each pixel; For the first Within the neighborhood window of the nth pixel The probability of each gray level; This refers to the index value and total number of gray levels; This is a logarithmic function.

[0014] This invention, by calculating information entropy, can assess the complexity of grayscale value distribution within the neighborhood of a pixel in a detailed image. The grayscale distribution in regular texture areas is relatively simple, with a lower entropy value; while the irregularity of defective areas makes the grayscale distribution more chaotic, with a higher entropy value. This indicator provides a reliable data basis for distinguishing between texture and defects.

[0015] Preferably, the algorithm for clustering all information entropy is the DBSCAN clustering algorithm.

[0016] Preferably, the dynamic regularization parameters of the pixel satisfy the expression: In the formula, For the first Dynamic regularization parameters for each pixel; As the baseline entropy; For the first Information entropy of each pixel; It is the hyperbolic tangent function.

[0017] This invention utilizes the hyperbolic tangent function to map the difference between the information entropy of a pixel and the baseline entropy to the range of 0-1 to obtain dynamic regularization parameters. This ensures that defective regions receive smaller parameters to preserve edge details, while textured regions receive larger parameters to achieve smoothing, providing accurate control signals for subsequent adaptive filtering.

[0018] Preferably, the threshold segmentation algorithm is the Otsu method, and the white pixels in the segmented binary image are defective pixels.

[0019] Preferably, the percentage of defective pixels is equal to the percentage of white pixels in the segmented binary image out of all pixels.

[0020] Secondly, the present invention provides a surface condition assessment system for a cold bed crystallizer, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned surface condition assessment method for a cold bed crystallizer is implemented.

[0021] By adopting the above technical solution, a computer program for evaluating the surface condition of a cold bed crystallizer is generated and stored in a memory for loading and execution by a processor. This allows for the creation of a terminal device based on the memory and processor, facilitating its use.

[0022] The beneficial effects of this invention are as follows: (1) By subtracting the gray value of each pixel in the original image from the background estimate, the present invention can extract more accurately detailed images containing only high-frequency textures and defects; (2) This invention clusters the information entropy of all pixels in the detail image. Based on the prior feature that the normal texture pixels account for the largest proportion, it automatically marks the maximum entropy value in the largest cluster as the benchmark entropy. There is no need to manually set the threshold, which provides an adaptive texture complexity evaluation benchmark for subsequent parameter calculation. (3) The present invention guides the subsequent filtering process based on the dynamic regularization parameters of each pixel, so that the filtering behavior can dynamically adjust the intensity of edge smoothing, improve the accuracy of crystallizer inner surface defect detection, and overcome the limitations of traditional fixed parameter guided filtering. Attached Figure Description

[0023] Figure 1 This is a flowchart illustrating a method for evaluating the surface condition of a cold bed crystallizer according to the present invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0026] This invention discloses a method for evaluating the surface condition of a cold bed crystallizer, referring to... Figure 1 This includes steps S1-S5: S1. Acquire the original image of the inner surface of the crystallizer.

[0027] It should be noted that the surface finish of the inner surface of the cooling bed crystallizer has a significant impact on the surface quality of the ingot. If there are defects on the inner surface, it will affect the molding quality. Therefore, it is necessary to take images of the inner surface of the crystallizer before the process operation to assess whether its surface condition meets the standards, thereby reducing the defect rate.

[0028] Specifically, a rotation-lifting mechanism is installed in the area where the crystallizer is placed on the cooling bed. An area array camera and a coaxial ring light source are deployed above the mechanism. Before the process operation, the mechanism is adjusted to a position parallel to the center plane of the crystallizer to acquire images of the inner surface of the crystallizer. The acquired images are then processed into grayscale to obtain the grayscale value of each pixel.

[0029] At this point, the original image of the inner surface of the crystallizer and the grayscale value of each pixel have been obtained.

[0030] S2. Take any pixel in the original image as the target pixel and calculate the background estimate of the target pixel; subtract the background estimate from the gray value of each pixel to get the gray value of each pixel in the detail image.

[0031] It should be noted that crystallizers are usually made of curved surfaces processed from metals such as copper or aluminum. Both metals and curved surfaces have high reflectivity under light sources, resulting in bright areas in the acquired images. In fact, these bright areas are manifestations of low-frequency uneven illumination, that is, slow and large-scale changes in illumination, which can mask the true details and affect the subsequent filtering effect. Therefore, it is necessary to extract the low-frequency components of the image, that is, the background illumination, in order to recover an enhanced image that contains only high-frequency details.

[0032] Specifically, the preset neighborhood window size is ,in, The local analysis range for each pixel is defined to capture grayscale changes within that local area. The value cannot be too small to avoid failing to capture grayscale changes. Furthermore, the analysis process involves acquiring other pixels within a neighborhood window centered on each pixel. The value is singular; this invention will The value is set to 13, and implementers can adjust it as needed. It should be added that for pixels in the edge area where a complete neighborhood window cannot be obtained, the pixel's own grayscale value is used for completion processing.

[0033] Considering that the texture of the normal inner wall of the crystallizer is composed of dense grooves, which is represented by rapid alternation of gray values ​​in a local range in the image, averaging the gray values ​​in this rapid change of gray values ​​in the local range will smooth out all high-frequency texture details; however, if there are defective areas, their gray values ​​may also be low-frequency signals. To avoid this part of the signal contaminating the low-frequency illumination extraction, a weighted averaging method based on neighborhood statistical characteristics is introduced, which can smooth high-frequency textures and eliminate defect interference, ensuring accurate extraction of a clean background.

[0034] Take any pixel in the original image as the target pixel, and extract the median of the gray values ​​of all neighboring pixels in the neighborhood window of the target pixel; calculate the weight value of each neighboring pixel, where the weight value is equal to the reciprocal of the absolute difference between the gray value of each neighboring pixel and the median; it should be noted that if the absolute difference is 0, it indicates that the pixel is a normal pixel in the neighborhood, and the weight value of the pixel is set to 1.

[0035] The background estimate of the target pixel is obtained by weighting the gray values ​​of all neighboring pixels according to the weight values; the background estimate satisfies the expression:

[0036] In the formula, The background estimate for the target pixel; Within the neighborhood window of the target pixel, the first The grayscale value of each neighboring pixel; Within the neighborhood window of the target pixel, the first The weight values ​​of each neighboring pixel; This refers to the index value and number of pixels within the neighborhood window of the target pixel.

[0037] in, Reflects the neighborhood window of the target pixel, the first The weight value of the nth neighboring pixel is inversely proportional to the weight value of the nth neighboring pixel. The absolute difference between the grayscale value and the median of the nth neighboring pixels; the smaller the weight value, the better. The more the grayscale value of a neighboring pixel deviates from the normal level of the neighborhood, the more it means that the grayscale value of the i-th neighboring pixel is... The higher the probability that the nth neighboring pixel is a defect, the more likely it is to be determined by assigning the nth... Smaller weights are assigned to neighboring pixels to reduce the contribution of defects to the background estimation calculation; conversely, larger weights are assigned to neighboring pixels that are close to the median to dominate the background estimation calculation.

[0038] At this point, the background estimates for all pixels in the original image have been obtained; The grayscale value of each pixel in the original image is subtracted from the estimated background value to obtain the grayscale value of each pixel in the detail image, thus obtaining the detail image.

[0039] S3. For each pixel in the detailed image: Calculate the probability of each gray level within the neighborhood window of the pixel; determine the information entropy based on the probability of each gray level.

[0040] It should be noted that the acquired high-frequency detail images contain both normal textures and abnormal defects. The actual processing texture distribution on the inner surface of the crystallizer is relatively regular, meaning that the grayscale changes are relatively stable within a local range. Abnormal defects, on the other hand, disrupt the stability of grayscale values ​​within the original region. Therefore, by analyzing the distribution changes of grayscale values ​​within the neighborhood window of each pixel in the detail image, the information entropy is evaluated. The local information entropy of normal texture regions will be stable at a low level, while the local information entropy of defect regions will be higher, thus providing data for subsequent filtering.

[0041] Specifically, for each pixel in the detail image: based on the gray values ​​of all pixels in the neighborhood window of each pixel, count the number of pixels at each gray level, and calculate the probability of each gray level. The probability is equal to the ratio of the number of pixels at each gray level to the number of pixels in the neighborhood window.

[0042] The information entropy of each pixel is determined based on the probability of each gray level within its neighborhood window; the information entropy satisfies the expression:

[0043] In the formula, For the first Information entropy of each pixel; For the first Within the neighborhood window of the nth pixel The probability of each gray level; This refers to the index value and total number of gray levels; This is a logarithmic function.

[0044] in, The first image reflects details The complexity of grayscale value changes within the neighborhood window of a pixel. The larger the value, the more chaotic the grayscale distribution within the neighborhood window of that pixel, and the higher the probability of it being a defect; conversely, the more consistent the grayscale distribution within the neighborhood window of that pixel, and the higher the probability of it being a regular texture area.

[0045] At this point, the information entropy of each pixel in the detailed image has been obtained.

[0046] S4. Cluster all information entropy and select the cluster containing the most pixels as the texture cluster; use the maximum information entropy in the texture cluster as the baseline entropy; determine the dynamic regularization parameter of the pixel based on the difference between the information entropy of the pixel and the baseline entropy.

[0047] It should be noted that, considering that defects on the inner surface of the actual crystallizer are caused by wear, scratches, or deposits, the proportion of defective pixels is usually very small, and the vast majority of the inner wall area is normal texture. Therefore, clustering algorithms can be used to cluster the information entropy of each pixel in the acquired detail image. The cluster containing the most pixels has a higher probability of being a texture cluster. The regularization parameter of the guided filter is used to control the sensitivity of the filter to edges. Too large or too small a parameter value will affect the filtering effect. If it is set too small, too much texture will be retained; if it is set too large, real defects will be smoothed out, leading to inaccurate subsequent state evaluation. Therefore, the regularization parameter needs to be adaptively adjusted.

[0048] Specifically, the information entropy of all pixels is used as clustering samples, and DBSCAN clustering is performed to obtain the clustering results. It should be noted that the DBSCAN clustering algorithm is a well-known technology and will not be described in detail here. The cluster with the most pixels in the cluster is taken as the texture cluster. The maximum value of the information entropy of the pixels in the texture cluster is extracted as the baseline entropy.

[0049] The dynamic regularization parameter is determined based on the difference between the information entropy of each pixel and the baseline entropy; the dynamic regularization parameter satisfies the expression:

[0050] In the formula, For the first Dynamic regularization parameters for each pixel; As the baseline entropy; For the first Information entropy of each pixel; It is the hyperbolic tangent function.

[0051] in, Reflecting the The deviation of the information entropy of the nth pixel from the baseline entropy; if this value is less than 0 and the smaller the value, the more likely the nth pixel is to be deviating from the baseline entropy. The complexity of grayscale changes in the region containing the nth pixel far exceeds the complexity of the largest grayscale change in a normal texture region, meaning that the nth pixel... The higher the probability that a pixel belongs to an abnormal defect region, the smaller the regularization parameter is needed to ensure that its edge information is preserved in subsequent processing; conversely, the lower the probability, the more likely the pixel is to belong to an abnormal defect region. Pixels belonging to normal texture regions or smooth regions require larger regularization parameters to allow for stronger smoothing in subsequent processing; among them, The function is for making The mapping is in the range of 0-1.

[0052] At this point, the dynamic regularization parameters for each pixel in the detailed image have been obtained.

[0053] S5. Filter the detail image using the dynamic regularization parameters of each pixel, perform threshold segmentation on the filtered image, and count the percentage of defective pixels in the segmented binary image. If the percentage is greater than the set threshold, the state is determined to be unqualified.

[0054] It should be noted that the guided filter can smooth the image while maintaining strong edges in the guided image, thus distinguishing between texture and defects. To ensure the filter processing effect, it is combined with adaptively adjusted regularization parameters to ensure that the filtering can smooth textures while preserving defects. The filtered effect has significantly enhanced the defect area and effectively smoothed the normal texture. The grayscale contrast has been significantly improved. By performing threshold segmentation on the filtered image, the surface defect area can be segmented, thereby significantly improving the accuracy of surface condition assessment.

[0055] Specifically, the dynamic regularization parameters of each pixel are replaced with the regularization parameters in the traditional guided filtering algorithm to filter the detail image and obtain a filtered image. The filtered image is then subjected to Otsu's threshold segmentation to obtain a segmented binary image, where the defective region is the area where white pixels are located and the normal region is the area where black pixels are located. Therefore, white pixels are recorded as defective pixels. The number of white pixels is counted, and the percentage of white pixels to the total number of pixels is calculated. If the percentage is greater than a preset threshold, the inner surface of the crystallizer is determined to be unqualified, and an alarm is issued; otherwise, the inner surface of the crystallizer is determined to be qualified, and subsequent process operations can proceed.

[0056] Among them, the guided filtering algorithm and Otsu's method are well-known technologies and will not be described in detail here; the specific value of the preset threshold can be set according to the actual application scenario and needs, and the range of the preset threshold is [1%, 10%]. This range is set to take into account that the actual surface is allowed to have minor flaws, but not to have significant damage; the present invention sets the preset threshold to 5%.

[0057] This invention also discloses a surface condition assessment system for a cold bed crystallizer, including a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement a surface condition assessment method for a cold bed crystallizer according to the present invention.

[0058] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.

Claims

1. A method for evaluating the surface condition of a cold bed crystallizer, characterized in that, include: Acquire the original image of the inner surface of the crystallizer; take any pixel in the original image as the target pixel, and extract the median gray value of all neighboring pixels in the neighborhood window of the target pixel; The weight value is determined based on the deviation of the gray value of each neighboring pixel from the median; the gray values ​​of all neighboring pixels are then weighted and averaged according to the weight value to obtain the background estimate of the target pixel. Subtract the estimated background value from the gray value of each pixel in the original image to obtain the gray value of each pixel in the detail image; For each pixel in the detailed image: Calculate the probability of each gray level within the neighborhood window of the pixel; determine the information entropy based on the probability of each gray level; cluster all information entropies and take the cluster containing the most pixels as the texture cluster; take the maximum information entropy in the texture cluster as the baseline entropy; determine the dynamic regularization parameter of the pixel based on the difference between the information entropy of the pixel and the baseline entropy. The detailed image is filtered using the dynamic regularization parameters of each pixel. The filtered image is then segmented by thresholding, and the percentage of defective pixels in the segmented binary image is counted. If the percentage is greater than a set threshold, the image is determined to be unqualified.

2. The method for evaluating the surface condition of a cold bed crystallizer according to claim 1, characterized in that, The weight value is equal to the reciprocal of the absolute difference between the gray value and the median of each neighboring pixel; and when the absolute difference is 0, the weight value is set to 1.

3. The method for evaluating the surface condition of a cold bed crystallizer according to claim 1, characterized in that, The estimated background value of the target pixel satisfies the expression: ； In the formula, The background estimate for the target pixel; Within the neighborhood window of the target pixel, the first The grayscale value of each neighboring pixel; Within the neighborhood window of the target pixel, the first The weight values ​​of each neighboring pixel; This refers to the index value and number of pixels within the neighborhood window of the target pixel.

4. The method for evaluating the surface condition of a cold bed crystallizer according to claim 1, characterized in that, The probability of each gray level within the neighborhood window of the statistical pixel includes: Based on the gray values ​​of all pixels within the neighborhood window of each pixel, the number of pixels at each gray level is counted, and the probability of each gray level is calculated. The probability is equal to the ratio of the number of pixels at each gray level to the number of pixels in the neighborhood window.

5. The method for evaluating the surface condition of a cold bed crystallizer according to claim 1, characterized in that, The information entropy satisfies the expression: ； In the formula, For the first Information entropy of each pixel; For the first Within the neighborhood window of the nth pixel The probability of each gray level; This refers to the index value and total number of gray levels; This is a logarithmic function.

6. The method for evaluating the surface condition of a cold bed crystallizer according to claim 1, characterized in that, The algorithm used to cluster all information entropy is the DBSCAN clustering algorithm.

7. The method for evaluating the surface condition of a cold bed crystallizer according to claim 1, characterized in that, The dynamic regularization parameters of the pixel satisfy the expression: ； In the formula, For the first Dynamic regularization parameters for each pixel; As the baseline entropy; For the first Information entropy of each pixel; It is the hyperbolic tangent function.

8. The method for evaluating the surface condition of a cold bed crystallizer according to claim 1, characterized in that, The threshold segmentation algorithm is the Otsu method, and the white pixels in the segmented binary image are defective pixels.

9. The method for evaluating the surface condition of a cold bed crystallizer according to claim 1, characterized in that, The percentage of defective pixels is equal to the percentage of white pixels in the segmented binary image out of all pixels.

10. A surface condition assessment system for a cold bed crystallizer, characterized in that, include: A processor and a memory, the memory storing computer program instructions that, when executed by the processor, implement a method for evaluating the surface condition of a cold bed crystallizer according to any one of claims 1-9.

Images