Goat milk filtering efficiency detection method and system based on machine vision

Abstract

The invention relates to the field of image processing, in particular to a goat milk filtering efficiency detection method and system based on machine vision, and the method comprises the steps: obtaining a gray-scale image of the work of a filter screen, carrying out the image enhancement of the gray-scale image, and obtaining a preprocessed filtering image; calculating the blocking degree of the filtered image; and when the blocking degree is larger than or equal to a preset threshold value, the filter screen is cleaned. By combining the stability and smoothness of a flowing path and the change of gray values at different moments, when the blockage degree reaches or exceeds a preset threshold value, the system can automatically trigger the cleaning process, so that the continuous smoothness of the filter screen and the filtering efficiency of goat milk are ensured.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and more specifically, to a method and system for detecting goat milk filtration efficiency based on machine vision. Background Art

[0002] Goat milk is a nutritious dairy product that comes from goats or sheep. The processing of fresh goat milk is particularly important and is the key to ensuring the purity and freshness of the raw milk. In the production process of goat milk powder, heating and filtering of goat milk are two core links.

[0003] Prior art, such as the patent application document with publication number CN118743417A, discloses a preparation process of a dairy product, which includes preparing a milk source and inspecting the milk source; weighing the milk source and heating it; placing the milk source in a filter and filtering it, and then placing it in a separator and separating it for a period of time to remove fine solid impurities in the milk source; taking out the separated milk source and introducing it into a sterilization device, increasing the sterilization temperature, and sterilizing it for a period of time; taking out the sterilized milk source and introducing it into a milk supply pump, and then introducing it into a milk storage box; regularly stirring the milk in the milk storage box, each stirring lasting for a period of time; regularly sampling the milk for inspection, and the storage time of the milk does not exceed a certain limit; preparing a number of milk cartons, filling the milk cartons with a certain amount of dairy products; and storing the dairy products in a suitable storage environment.

[0004] During the heating process mentioned in the patent application, the fat particles in the goat milk undergo physical changes, resulting in the formation of larger fat clumps. These larger fat clumps may clog the filtration equipment in the subsequent filtration step. Due to the location and structural limitations of the filter, the staff cannot directly observe whether the filter is clogged, resulting in reduced filtration efficiency. Summary of the invention

[0005] In order to solve the technical problem of reduced filtration efficiency, the present invention provides solutions in the following aspects.

[0006] In a first aspect, a method for detecting goat milk filtration efficiency based on machine vision comprises: Acquire a grayscale image of the filter screen in operation, perform image enhancement on the grayscale image, and obtain a preprocessed filtered image; Calculate the clogging degree of the filtered image; When the blockage degree is greater than or equal to a preset threshold, cleaning the filter screen; Wherein, the blockage degree is: ; In the formula, For the The total blockage degree of the image at the moment, For the The first degree of congestion at the moment, For the The second congestion level at the moment, for The weight of for The weight of , satisfy The first blockage degree is used to characterize the stability of the goat milk flow path in the holes in the filtered image, and the second blockage degree is used to characterize the difference in the grayscale values ​​of the pixels at the same position in the filtered image at different times.

[0007] The present invention acquires a filtered image of the filter and analyzes the filtered image. By monitoring the first blockage degree, the filtering effect of the filter can be evaluated. If the first blockage degree is low, it means that the holes of the filter are unobstructed, the goat milk flows smoothly, and the filtering effect is good. Otherwise, it means that the filter has a blockage problem. By monitoring the second blockage degree, if the second blockage degree is high, it means that at different times, the grayscale values ​​of pixels at the same position in the filtered image are quite different, which means that the blockage situation of the filter at that position is constantly changing, or there is some dynamic blockage process. Otherwise, it shows that the blockage situation at the same position of the filter is relatively stable without significant changes. Then, the blockage degree of the filtered image is calculated in combination with the first blockage degree and the second blockage degree to more comprehensively reflect the actual blockage situation of the filter, thereby avoiding excessive blockage of the filter and affecting the filtering effect and operating efficiency.

[0008] Preferably, the process of obtaining the first blockage degree includes: For each row in the filtered image, calculate the The consistency of the aperture flow rate and flow direction of each hole in the row at all times; Normalizing the accumulated value of the product of all the aperture flow rates and flow direction consistency of the corresponding row as the hole blockage degree of the corresponding row; The average value of the sum of the hole blockage degrees corresponding to all rows in the filtered image is taken as the first blockage degree.

[0009] By calculating the aperture flow and flow consistency, the system can more accurately evaluate the blockage of each hole on the filter. The aperture flow reflects the actual flow capacity of the hole, while the flow consistency reveals the coordination of fluid flow between holes. The product of these two parameters can comprehensively reflect the impact of hole blockage on fluid flow.

[0010] Preferably, the process of obtaining the aperture flow rate of the hole includes: Construct the hole analysis area, select the pixel with the largest gray value in the analysis area as the seed point, use the growing region algorithm to obtain the flow path of goat milk, and extract its boundary pixel points; For The filtered image at the moment, two boundary pixel points with the same ordinate among the boundary pixel points corresponding to each hole are divided into a group, the distance between two boundary pixel points in each group is calculated using the Euclidean distance, all the distances in the row are summed and averaged to obtain the width of the flow path of the hole; the average of the widths of the flow paths of all holes in the corresponding row is taken as the normal path width of the hole; The ratio of the width of the flow path of the hole to the normal path width is normalized to obtain the aperture flow rate of the hole.

[0011] Through the growth area algorithm, the system can accurately identify the flow path of goat milk on the filter. The process of obtaining the aperture flow takes into account the change in the width of the hole flow path. When the hole is blocked by impurities, the width of its flow path will decrease, resulting in a decrease in the aperture flow. By monitoring the changes in the aperture flow, the system can promptly detect and solve the blockage problem.

[0012] Preferably, the process of acquiring the flow direction consistency includes: For the flow path corresponding to the hole, the gradient direction of the edge pixel points of the flow path is calculated using the Sobel operator to determine the gradient direction range of the edge pixel points of each hole; For each hole, calculate the variance of the gradient direction range of all edge pixels; The variance is normalized to obtain the flow direction consistency of the corresponding hole.

[0013] Flow consistency reflects the stability of the hole flow path. When the gradient direction of the edge pixel points of the flow path is relatively consistent, it means that the flow of the fluid in the hole is relatively stable; when the gradient direction is dispersed, it may mean that there are unstable factors in the flow path, such as impurity blockage or hole deformation. By calculating the flow consistency, the system can quantitatively evaluate the stability of the flow path.

[0014] Preferably, the second blockage degree satisfies the relationship: ; In the formula, is the second blocking degree, For the Pixel point The gray value at the moment, For the Pixel point The gray value at the moment, is the total number of pixels in the filtered image, is the initial observation period of the hole, For the The difference weight of the moment, Indicates normalization processing.

[0015] The second clogging degree combines the time factor and the change of the pixel gray value to more accurately evaluate the clogging of the filter. In particular, when the filter is slowly clogged or partially clogged, this indicator can provide more sensitive detection capabilities.

[0016] Preferably, the process of obtaining the first blockage degree includes:

[0017] In the formula, is the first blocking degree, To filter the total number of rows in the image, For the corresponding row The weight factor of the hole, For the Moment The aperture flow rate of the hole, For the Moment The consistency of the flow direction of the holes, It is an exponential function with the natural constant e as its base.

[0018] Preferably, it also includes: The grayscale image is binarized to separate the hole area from the background area, a morphological operation is performed on the binarized image, and each independent hole area is marked using a marking algorithm.

[0019] In a second aspect of the present invention, a goat milk filtration efficiency detection system based on machine vision is provided, 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 goat milk filtration efficiency detection method based on machine vision according to the first aspect of the present invention is implemented.

[0020] The present invention has the following effects: The comprehensive calculated blockage degree can more comprehensively evaluate the blockage condition of the filter, taking into account both the stability and smoothness of the flow path (the first blockage degree) and the changes in grayscale values ​​at different times (the second blockage degree). When the blockage degree reaches or exceeds the preset threshold, the system will automatically trigger the cleaning process to ensure the continued smooth flow of the filter and the filtration efficiency of goat milk. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 It is a method flow chart of steps S1 to S3 in the method for detecting goat milk filtration efficiency based on machine vision in an embodiment of the present invention.

[0022] Figure 2 It is a schematic diagram of a template image in a method for detecting goat milk filtration efficiency based on machine vision according to an embodiment of the present invention.

[0023] Figure 3 It is a schematic diagram of the analysis area of ​​the filter image in the goat milk filtration efficiency detection method based on machine vision in an embodiment of the present invention.

[0024] Figure 4 It is a structural block diagram of a goat milk filtration efficiency detection system based on machine vision according to an embodiment of the present invention. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0026] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0027] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0028] Reference Figure 1 The method for detecting goat milk filtration efficiency based on machine vision includes steps S1 to S3, which are as follows: S1: Obtain a grayscale image of the filter mesh at work, and perform image enhancement on the grayscale image to obtain a preprocessed filtered image.

[0029] Firstly, an image of goat milk filtered by a filter is obtained and converted into a grayscale image. Since goat milk needs to be continuously heated and filtered during the processing, the long-term operation of the camera used to collect images will produce noise and motion blur, resulting in blurred edges of the flow path of goat milk in each hole in the collected image. The grayscale image is enhanced by using adaptive filtering and Canny edge detection algorithm to obtain the enhanced filtered image of the filter.

[0030] S2: Calculate the clogging degree of the filtered image.

[0031] First, the flow path area of ​​goat milk was determined for quick analysis, as follows: Set filter surface to have OK A row of holes with the same size evenly distributed; Binarize the grayscale image of the filter to separate the hole area from the background area, perform morphological operations on the binarized image, use a marking algorithm to mark each independent hole area, and then divide the holes with the same vertical coordinate of the center into a row and use it as a template image; Divide the template image to obtain the analysis area corresponding to each hole, and each analysis area corresponds to one hole; Since goat milk is milky white, the grayscale value of the pixel corresponding to goat milk is larger than that of the metal filter. Therefore, the pixel with the largest grayscale value is selected as the seed point in the analysis area, and the region growing algorithm is used to obtain the flow path area of ​​the goat milk in the analysis area.

[0032] In this embodiment, there may be blockage when the amount of goat milk flowing out of the filter gradually decreases, but it is not ruled out that it may be caused by the end of goat milk filtration. Therefore, by analyzing the flow path of the goat milk, when the holes are not blocked, the flow path width of the goat milk flowing out is a normal width and the degree of consistency of the path edge direction is the highest; if the holes are blocked, the flow path width of the goat milk flowing out is a smaller width and the degree of consistency of the path edge direction is medium; if the holes are severely blocked, the flow path width of the goat milk flowing out is the minimum width and the degree of consistency of the path edge direction is the lowest.

[0033] Therefore, the degree of blockage of the holes can be obtained from two aspects: the pore flow rate and the consistency of flow direction, so as to evaluate the filtration of goat milk.

[0034] Specifically, based on the filtered image at the first moment, two boundary pixel points with the same vertical coordinate in the boundary pixel points of the flow path area corresponding to each hole in each row are divided into a group, and the distance between each group of two boundary pixel points in each hole is calculated using Euclidean distance. The Euclidean distances of each group of two boundary pixel points are summed and averaged to obtain the flow path width of the goat milk corresponding to each hole in each row at the first moment; the average value of the width of the flow path of all holes in the corresponding row is taken as the normal path width of the hole.

[0035] It should be noted that when filtering goat milk at the first moment, goat milk flows out normally from each hole, but the goat milk flowing out of the first row will affect the path of the goat milk flowing out of the second row, and thus the normal flow path of the goat milk flowing out of each row is different, so it is necessary to calculate the normal flow path width of the goat milk in each row of holes.

[0036] Similarly, based on the filtered image at the current moment, the flow path width corresponding to each hole in each row at the current moment is obtained respectively.

[0037] The ratio of the width of the flow path corresponding to the hole to the normal path width is normalized to obtain the aperture flow rate of the hole.

[0038] The aperture flow rate of the hole satisfies the relationship:

[0039]

[0040]

[0041]

[0042] in, , , …, Respectively represent the 1st, 2nd, ..., The corresponding hole number in the row, , , …, In the At this moment, the first row The aperture flow rate of the hole, the second row The aperture flow rate of the hole, ..., No. The aperture flow rate of the hole, , , …, are respectively the normal flow path width of the first row of holes at the first moment, the normal flow path width of the second row of holes, ..., the normal flow path width of the first row of holes at the first moment. Normal flow path width of row holes, , , …, In the At this moment, the first row The flow path width of the hole, the The flow path width of the hole, ..., No. The flow path width of the hole.

[0043] The larger the flow path width of each row of holes, the larger the aperture flow rate of the holes; otherwise, it is smaller.

[0044] Get each boundary pixel point of the flow path area corresponding to each hole, use the Sobel operator to calculate the gradient direction of each edge pixel point, quantify the gradient direction and divide it into several discrete direction ranges. For each edge pixel point, take the direction range to which the gradient direction of each edge pixel point belongs as the direction range of each edge pixel point, calculate the variance of the direction range of all edge pixels, and thus measure the consistency of the flow direction of the hole.

[0045] The calculation formula for the consistency of the flow direction of the above holes is:

[0046]

[0047]

[0048]

[0049] in, , , …, In the At this moment, the first row The consistency of the flow direction of the holes, the The consistency of the flow direction of the holes, ..., No. The consistency of the flow direction of the holes, Indicates the first row The variance of the direction range of all edge pixels of the hole, Indicates the second row The variance of the direction range of all edge pixels of the hole, ..., Indicates No. The variance of the direction range of all edge pixels of the hole, represents a normalization process, and the direction range represents the direction range to which the gradient direction of each edge pixel belongs.

[0050] The first blockage degree is calculated based on the above aperture flow rate and flow direction consistency. The specific calculation formula is as follows:

[0051]

[0052]

[0053]

[0054]

[0055] In the formula, , , …, Respectively represent the 1st, 2nd, ..., The number of holes in the row, is an exponential function with the natural constant e as the base, which represents , , …, Perform normalization processing, , , …, Respectively represent the 1st, 2nd, ..., Line The moment , , …, The degree of blockage of the holes, Indicates the first degree of blockage.

[0056] For ease of understanding, in this embodiment, Figure 2 As shown, it is assumed that a filter surface has 3 rows and 3 columns, with 9 holes of the same size evenly distributed, and the filtered image at the first moment is used as the template image, where the holes in each row are numbered 1, 2, and 3, respectively. In other embodiments, 1-9 can also be set as the hole numbers arranged from left to right and from top to bottom on the template image.

[0057] like Figure 3 As shown in the figure, take the analysis area of ​​the first hole as an example: take 1 / 2 of the distance between the center of the first hole and the center of the second hole as the right boundary of the analysis area, and symmetrically take the left boundary of the analysis area; take the straight line where the vertex of the first hole is located as the upper boundary of the analysis area, and the straight line where the vertex of the fourth hole is located as the lower boundary of the analysis area of ​​the first hole. The closed area surrounded by the left and right boundaries and the upper and lower boundaries is the analysis area of ​​the first hole. By analogy, the analysis area corresponding to each hole in the template image is determined.

[0058] It should be noted that, since the goat milk is excluded from flowing above the hole when the goat milk flows out in the first row, only the hole and the area below the hole are analyzed.

[0059] For example, in the calculation formula for the aperture flow rate and flow direction consistency, , You can choose 1, 2, or 3. You can choose 1, 2, or 3. You can choose 1, 2, 3, and the overall hole blockage degree calculation formula: , , In other embodiments, in the above formula for calculating the thickness of the goat milk flow path and the formula for calculating the consistency of the edge direction of the goat milk flow path, , You can choose 1, 2, or 3. The options are 4, 5, 6, 7, 8, 9 can be taken, as well as the calculation formula for the overall blockage degree of the holes. , , Take 3, 6, and 9 respectively. 1. 4. 7 is preferred.

[0060] It should be noted that, in the present invention, considering that If the time is close to the first time, the goat milk may not have flowed out yet. If the time difference is too large, the possibility of blockage is greater. Therefore, an exemplary time is selected: = 10. Then the period between 1 and 10 is the initial observation period of the hole.

[0061] In another embodiment, the process of obtaining the first blockage degree includes:

[0062] In the formula, is the first blocking degree, To filter the total number of rows in the image, For the corresponding row The weight factor of the hole (which can be adjusted by the implementer based on historical test data), For the Moment The aperture flow rate of the hole, For the Moment The consistency of the flow direction of the holes, is an exponential function with the natural constant e as base, is the corresponding row number.

[0063] As time goes by, the pores become more and more clogged during the filtration process. The filtered image at the time of the filtering may be significantly different from the image at the beginning of the filtering due to blockage and other reasons, that is, the grayscale values ​​of the pixels at the same position in the images at different times may be different. The greater the difference between the grayscale values ​​of all pixels in the image at the moment and the grayscale values ​​of all pixels in the image at the beginning of filtering, the The more you filter the image, the greater the possibility that there will be holes that are blocked.

[0064] In the embodiment of the present invention, it is set that the total number of filtered images is pixels, the first pixel in the filter image Pixel point The gray value at the moment is recorded as , the first Pixel point The gray value at the moment is recorded as When judging the overall blockage degree, filter the image Pixel point Gray value at the moment With the filtered image Pixel point Gray value at the moment The difference in the impact of each moment is different, so it is necessary to and The difference of is given the corresponding weight. Pixel point There is always a possibility of hole clogging And sum them up to get the second blocking degree , the second blocking degree The expression is as follows:

[0065] In the formula, is the second blocking degree, For the Pixel point The gray value at the moment, For the Pixel point The gray value at the moment, is the total number of pixels in the filtered image, is the initial observation period of the hole, For the The difference weight of the moment, represents the normalization process, Indicates the filtering image and The weight given to the difference .

[0066] It is necessary to add that =10.

[0067] First degree of blockage Can be reflected in The degree of blockage of each hole at the moment, and the second blockage degree Can be reflected in The overall blockage degree of the filtered image at the time, so the first blockage degree With the second degree of blockage Together they provide a more accurate picture of the overall blockage level in the image, making it easier to subsequently clean the filter.

[0068] Specifically, the calculation formula for the overall blockage degree of the image is as follows:

[0069] For the The total blockage degree of the image at the moment, For the The first degree of congestion at the moment, For the The second congestion level at the moment, for The weight of for The weight of , satisfy ; For example, is 0.6, is 0.4.

[0070] when and When the corresponding values ​​are large, the overall blockage degree of the image The value of is also large, and vice versa.

[0071] S3: When the blockage degree is greater than or equal to a preset threshold, the filter screen is cleaned.

[0072] For example, when Time congestion level If it is greater than or equal to 0.5, it is considered that the clogging of the filter image at this moment is serious and the filter needs to be cleaned.

[0073] The present invention also provides a goat milk filtration efficiency detection system based on machine vision. Figure 4 As shown, the system includes a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the method for detecting goat milk filtration efficiency based on machine vision according to the first aspect of the present invention is implemented.

[0074] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0075] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0076] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0077] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A method for detecting goat milk filtration efficiency based on machine vision, characterized in that: include: Acquire a grayscale image of the filter screen in operation, perform image enhancement on the grayscale image, and obtain a preprocessed filtered image; Calculate the clogging degree of the filtered image; When the blockage degree is greater than or equal to a preset threshold, cleaning the filter screen; Wherein, the blockage degree is: ; In the formula, For the The total blockage degree of the image at the moment, For the The first degree of congestion at the moment, For the The second congestion level at the moment, for The weight of for The weight of , satisfy The first blockage degree is used to characterize the stability of the goat milk flow path in the holes in the filtered image, and the second blockage degree is used to characterize the difference in the grayscale values ​​of the pixels at the same position in the filtered image at different times.

2. The method for detecting goat milk filtration efficiency based on machine vision according to claim 1, characterized in that: The process of obtaining the first blockage degree includes: For each row in the filtered image, calculate the The consistency of the aperture flow rate and flow direction of each hole in the row at all times; Normalizing the accumulated value of the product of all the aperture flow rates and flow direction consistency of the corresponding row as the hole blockage degree of the corresponding row; The average value of the sum of the hole blockage degrees corresponding to all rows in the filtered image is taken as the first blockage degree.

3. The method for detecting goat milk filtration efficiency based on machine vision according to claim 2, characterized in that: The process of obtaining the aperture flow rate of the hole includes: Construct the hole analysis area, select the pixel with the largest gray value in the analysis area as the seed point, use the growing region algorithm to obtain the flow path of goat milk, and extract its boundary pixel points; For The filtered image at the moment, two boundary pixel points with the same ordinate among the boundary pixel points corresponding to each hole are divided into a group, the distance between two boundary pixel points in each group is calculated using the Euclidean distance, all the distances in the row are summed and averaged to obtain the width of the flow path of the hole; the average of the widths of the flow paths of all holes in the corresponding row is taken as the normal path width of the hole; The ratio of the width of the flow path of the hole to the normal path width is normalized to obtain the aperture flow rate of the hole.

4. The method for detecting goat milk filtration efficiency based on machine vision according to claim 3, characterized in that: The process of obtaining the flow consistency includes: For the flow path corresponding to the hole, the gradient direction of the edge pixel points of the flow path is calculated using the Sobel operator to determine the gradient direction range of the edge pixel points of each hole; For each hole, calculate the variance of the gradient direction range of all edge pixels; The variance is normalized to obtain the flow direction consistency of the corresponding hole.

5. The method for detecting goat milk filtration efficiency based on machine vision according to claim 4, characterized in that: The second blocking degree satisfies the relationship: ; In the formula, For the second blocking degree, For the Pixel point The gray value at the moment, For the Pixel point The gray value at the moment, is the total number of pixels in the filtered image, is the initial observation period of the hole, For the The difference weight of the moment, Indicates normalization processing.

6. The method for detecting goat milk filtration efficiency based on machine vision according to claim 1, characterized in that: The process of obtaining the first blockage degree includes: ; In the formula, is the first blocking degree, To filter the total number of rows in the image, For the corresponding row The weight factor of the hole, For the Moment The aperture flow rate of the hole, For the Moment The consistency of the flow direction of the holes, It is an exponential function with the natural constant e as its base.

7. The method for detecting goat milk filtration efficiency based on machine vision according to claim 1, characterized in that: Also includes: The grayscale image is binarized to separate the hole area from the background area, a morphological operation is performed on the binarized image, and each independent hole area is marked using a marking algorithm.

8. The goat milk filtration efficiency detection system based on machine vision is characterized by: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the method for detecting goat milk filtration efficiency based on machine vision according to any one of claims 1 to 7 is implemented.

Images