A material counting device based on machine vision

Abstract

The present invention relates to the technical field of material counting, and in particular to a material counting device based on machine vision, comprising: an image acquisition module, a quality detection module, a detection and analysis module, a counting and determination module, and a material counting module; the image acquisition module acquires a surface image and an internal structure image of a material, the detection and analysis module processes the image, extracts the surface features of the material, and calculates a characterization parameter of a tendency of morphological abnormality, and the counting and determination module selects a counting and analysis method of a corresponding material according to the characterization parameter to determine how to adaptively count the material; the material counting device of the present invention can automatically identify the surface features and internal structure of a material by integrating machine vision technology, and counts and classifies the material according to preset standards, thereby effectively avoiding the processing of unqualified materials and reducing material waste.

Description

Technical Field

[0001] The present invention relates to the technical field of material counting, and in particular to a material counting device based on machine vision. Background Art

[0002] Material counting usually relies on manual visual inspection or simple automated mechanical counters, which are inefficient, error-prone, and costly. Manual counting is easily affected by subjective judgment and accuracy is difficult to guarantee; while mechanical counters may not be able to accurately identify the complex shapes and sizes of materials, resulting in inaccurate counting. In addition, these methods often fail to provide an in-depth assessment of material quality and fail to screen out unqualified materials that may affect the quality of subsequent processing, thereby increasing uncertainty and waste in production.

[0003] Chinese Patent Publication No.: CN109949362B discloses a material visual inspection method, comprising the following steps: a camera component acquires a target image below a suction device, and calculates and determines whether the material reaches a target area below the suction device; calculates and obtains coordinate information of a rubber pad within an effective area; calculates and obtains a position correction distance of the suction device based on the coordinate information of the rubber pad within the target area and the coordinate information of the suction device; and the suction device is adjusted to be directly above the rubber pad based on the position correction distance.

[0004] However, the prior art still has the following problems: in actual situations, materials may have multiple parameters that do not conform to processing. If they are counted uniformly, the quality of the parts processed subsequently may be unqualified. Summary of the invention

[0005] To this end, the present invention provides a material counting device based on machine vision to overcome the problem in the prior art that in actual situations, materials may have multiple parameters that do not conform to processing. If they are counted uniformly, the quality of subsequently processed parts may be unqualified.

[0006] To achieve the above object, the present invention provides a material counting device based on machine vision, comprising:

[0007] An image acquisition module, which is a camera unit for acquiring a surface detection image group of each processed material, and a projection unit for acquiring a radiographic image of the processed material;

[0008] A quality detection module, connected to the image acquisition module, for acquiring quality information of each of the processed materials;

[0009] A detection and analysis module, which is connected to the image acquisition module, is used to amplify the surface detection image group, extract the surface characteristics of the processed material, and determine the characteristic parameters of the morphological abnormality tendency of the processed material to determine the effective counting type of the processed material;

[0010] The counting determination module, which is respectively connected with the quality detection module and the detection and analysis module, is used to determine whether to count each processing material according to the counting effective type of the processing material, including:

[0011] Obtaining the quality information of the processed material, and combining it with the preset material quality conditions to determine whether to directly count the current processed material;

[0012] Or, acquiring the radiographic image, processing the radiographic image to obtain a uniform analysis image, and determining a uniform distribution characterization parameter of the processed material according to the uniform analysis image to determine whether to process and count the current processed material;

[0013] The material counting module is connected to the counting determination module and is used to determine whether to count the processed materials accordingly according to the determination result of whether to count the processed materials.

[0014] Furthermore, the camera unit acquires the surface detection image groups of each of the processed materials one by one;

[0015] The surface detection image group includes a head shape image, a tail shape image and a surface flatness image.

[0016] Furthermore, the detection and analysis module determines the morphological abnormality tendency characterization parameter of the processed material according to the surface features of the amplified surface detection image group, and the morphological abnormality tendency characterization parameter is determined according to formula (1),

[0017]

[0018] In formula (1), C is a parameter characterizing the tendency of morphological abnormality, c0 is the circumference of the head of the processed material, c1 is the circumference of the tail of the processed material, n is the total number of divided areas in the enlarged surface flat image, si is the grayscale average value of the i-th characteristic area, s0 is the overall grayscale average value of the enlarged surface flat image, and i is an integer greater than 0.

[0019] Furthermore, the detection and analysis module determines the effective counting type of the processed material according to the characteristic parameter of the morphological abnormality tendency, including:

[0020] If the morphological abnormality tendency characterization parameter is less than or equal to the standard morphological abnormality tendency characterization parameter, the counting effective type of the processed material is the counting direct effective type;

[0021] If the morphological abnormality tendency characterization parameter is greater than the standard morphological abnormality tendency characterization parameter, the counting effective type of the processed material is the counting indirect effective type.

[0022] Furthermore, the counting determination module determines the judgment method of whether to count each processing material according to the counting effective type of the processing material, including:

[0023] If the counting effective type of the processing material is the counting direct effective type, the judgment method is to obtain the quality information of the processing material and combine it with the preset material quality conditions to determine whether to directly count the current processing material;

[0024] If the counting effective type of the processing material is the counting indirect effective type, the judgment method is to obtain the X-ray image, process the X-ray image to obtain a uniform analysis image, and determine the uniform distribution characterization parameters of the processing material according to the uniform analysis image to determine whether to process and count the current processing material.

[0025] Furthermore, the counting determination module determines whether the quality information of the processed material meets the preset material quality conditions, and determines whether to directly count the current processed material according to the determination result;

[0026] If the quality information of the processed material meets the preset material quality conditions, the current processed material is directly counted;

[0027] If the quality information of the processed material does not meet the preset material quality conditions, the current processed material will not be directly counted.

[0028] Furthermore, the counting determination module determines the uniform distribution characterization parameter of the processed material according to the uniform analysis image, and the uniform distribution characterization parameter is determined according to formula (2):

[0029]

[0030] In formula (2), K is the uniform distribution characterization parameter, m is the total number of analysis areas in the uniform analysis image, Sj is the grayscale average of the jth analysis area, S0 is the overall grayscale average of the uniform analysis image, and i is an integer greater than 0.

[0031] Furthermore, the counting determines whether to perform processing counting on the current processing material according to the uniform distribution characterization parameter of the processing material, including:

[0032] If the uniform distribution characterization parameter is less than or equal to the standard uniform distribution characterization parameter, the processing count is performed on the current processing material;

[0033] If the uniform distribution characterization parameter is greater than the standard uniform distribution characterization parameter, the processing count is not performed on the current processing material.

[0034] Furthermore, the counting determination module obtains uniform distribution characterization parameters of the processing material that is not directly counted, and determines whether to perform processing counting on the current processing material.

[0035] Furthermore, the material counting module may count materials in the following ways: directly counting materials, processing counting materials, and invalid counting materials;

[0036] Among them, the materials for invalid counting are materials that are not directly counted and are not processed.

[0037] Compared with the prior art, the beneficial effect of the present invention lies in that the image acquisition module acquires the surface image and internal structure image of the material, and then processes the image through the detection and analysis module, extracts the surface features of the material, and calculates the characterization parameters of the morphological abnormality tendency. According to the characterization parameters, the counting and judgment module selects the counting and analysis method of the corresponding material to determine how to adaptively count the material; the material counting equipment of the present invention can automatically identify the surface features and internal structure of the material by integrating machine vision technology, and screen it according to preset quality standards, effectively avoiding the processing of unqualified materials and reducing material waste. At the same time, the automated counting and quality control process greatly reduces labor costs, speeds up production, and enhances production flexibility and adaptability.

[0038] Furthermore, the appearance of materials that do not meet production requirements will be quite different from that of materials that meet the requirements. For example, there will be different widths at the beginning and end, and there will be more depressions on the surface. Parts processed using such raw materials are prone to abnormalities, while parts processed with materials with the opposite situation will have higher quality. Therefore, the morphological abnormality tendency characterization parameter corresponding to the material is calculated to characterize the tendency of parts processed from the material to have abnormalities, thereby providing data support for whether materials with different surface types can be counted subsequently. Under the premise of ensuring the counting of materials, the materials are classified and counted, which not only ensures the accuracy of material counting, but also ensures the quality of subsequent processed parts.

[0039] Furthermore, the counting judgment module selects the counting analysis method for different types of processing materials according to the effective counting type of the processing material. In actual situations, the shape rules of materials with low morphological abnormalities represent that the processed parts meet the part standards in appearance. Therefore, the quality of the materials is further verified for the above situation to determine whether the parts obtained by processing the materials meet the standards. Then, under the premise of ensuring reliability, the materials with shapes that meet the standards are quality inspected to ensure that the materials meet the processing requirements of the expected parts.

[0040] Furthermore, the present invention performs internal uniformity detection on materials with a high tendency of morphological abnormalities. In actual situations, if the internal uniformity of the material is low, the strength of the processed parts will not meet the requirements. Therefore, the present invention performs uniformity detection on materials that require further grinding to ensure that the material can undergo subsequent processing operations and reduce material waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a structural schematic diagram of a material counting device based on machine vision according to an embodiment of the present invention;

[0042] Figure 2 A logic diagram for determining the counting effective type of the processed material according to the embodiment of the present invention;

[0043] Figure 3 A logic diagram for determining whether to directly count the currently processed material according to an embodiment of the present invention;

[0044] Figure 4 A logic diagram for determining whether to perform processing counting on the currently processed material according to an embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0046] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0047] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0048] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0049] See also Figure 1 As shown, it is a structural schematic diagram of a material counting device based on machine vision according to an embodiment of the present invention. The present invention provides a material counting device based on machine vision, including:

[0050] An image acquisition module, which is a camera unit for acquiring a surface detection image group of each processed material, and a projection unit for acquiring a radiographic image of the processed material;

[0051] A quality detection module, connected to the image acquisition module, for acquiring quality information of each of the processed materials;

[0052] A detection and analysis module, which is connected to the image acquisition module, is used to amplify the surface detection image group, extract the surface characteristics of the processed material, and determine the characteristic parameters of the morphological abnormality tendency of the processed material to determine the effective counting type of the processed material;

[0053] The counting determination module, which is respectively connected with the quality detection module and the detection and analysis module, is used to determine whether to count each processing material according to the counting effective type of the processing material, including:

[0054] Obtaining the quality information of the processed material, and combining it with the preset material quality conditions to determine whether to directly count the current processed material;

[0055] Or, acquiring the radiographic image, processing the radiographic image to obtain a uniform analysis image, and determining a uniform distribution characterization parameter of the processed material according to the uniform analysis image to determine whether to process and count the current processed material;

[0056] The material counting module is connected to the counting determination module and is used to determine whether to count the processed materials accordingly according to the determination result of whether to count the processed materials.

[0057] In implementation, the camera unit is an industrial camera with an accuracy of up to 0.01mm, and the projection unit is any kind of detection equipment that uses radiation for non-destructive detection, such as an X-ray device or a radiation detector. The X-ray device is usually composed of an X-ray tube and an X-ray detector, which can generate detailed images of the internal structure of the inspected material for evaluating defects, foreign matter, structure and density changes, etc.; the radiation detector is used to receive and convert radiation imaging passing through the inspected material, such as a flat-panel detector (for planar imaging), a linear array detector (for line scanning imaging), etc. This is a prior art and is not specifically limited.

[0058] The quality detection module can be directly read by an existing gravity sensor. The gravity sensor is any sensor that can detect the mass of an object with an accuracy of 0.01g. This is a prior art and is not specifically limited.

[0059] The present invention does not limit the specific structures of the detection and analysis module, the counting and determination module, and the material counting module, which may be composed of logic components, including a field programmable processor, a computer, and a microprocessor in the computer.

[0060] The image acquisition module in the present invention acquires the surface image and internal structure image of the material, and then processes the image through the detection and analysis module, extracts the surface features of the material, and calculates the characterization parameters of the morphological abnormality tendency. According to the characterization parameters, the counting and judgment module selects the counting and analysis method of the corresponding material to determine how to adaptively count the material; the material counting device of the present invention can automatically identify the surface features and internal structure of the material by integrating machine vision technology, and screen according to preset quality standards, effectively avoiding the processing of unqualified materials and reducing material waste. At the same time, the automated counting and quality control process greatly reduces labor costs, speeds up production, and enhances production flexibility and adaptability.

[0061] Specifically, the camera unit acquires the surface detection image groups of each of the processed materials one by one;

[0062] The surface detection image group includes a head shape image, a tail shape image and a surface flatness image.

[0063] See also Figure 2 As shown, it is a logic diagram for determining the effective counting type of the processed material according to an embodiment of the present invention. The detection and analysis module determines the morphological abnormality tendency characterization parameter of the processed material according to the surface features of the amplified surface detection image group. The morphological abnormality tendency characterization parameter is determined according to formula (1):

[0064]

[0065] In formula (1), C is a parameter characterizing the tendency of morphological abnormality, c0 is the circumference of the head of the processed material, c1 is the circumference of the tail of the processed material, n is the total number of divided areas in the enlarged surface flat image, si is the grayscale average value of the i-th characteristic area, s0 is the overall grayscale average value of the enlarged surface flat image, and i is an integer greater than 0.

[0066] In the implementation, the detection and analysis image magnifies the surface detection image several times to make the surface features more obvious, preferably 20 times, and uses algorithms such as Canny edge detection to extract the edge of the material, and obtain the perimeter of the head and the perimeter of the tail of the processed material;

[0067] The surface flattening image is an image of the side surface of the processed material. The detection and analysis module divides the surface detection image into several regions with the same characteristics, and obtains the grayscale average value of each characteristic region and the overall grayscale average value of the surface flattening image.

[0068] It can be understood that after the material surface image is gray-processed, the resulting image can indicate whether there are bumps on the side of the material. The gray-scale value of the depression or protrusion will be different from the gray-scale value of the surrounding flat area. The uneven material may also cause uneven threads of the bolts after being processed into parts, thus affecting product quality.

[0069] Specifically, the detection and analysis module determines the effective counting type of the processed material according to the characteristic parameter of the abnormal morphology tendency, including:

[0070] If the morphological abnormality tendency characterization parameter is less than or equal to the standard morphological abnormality tendency characterization parameter, the counting effective type of the processed material is the counting direct effective type;

[0071] If the morphological abnormality tendency characterization parameter is greater than the standard morphological abnormality tendency characterization parameter, the counting effective type of the processed material is the counting indirect effective type.

[0072] The standard morphological abnormal tendency characterization parameter is selected within the interval [0.02, 0.15]. Generally, the larger the volume of the processed material, the larger the standard morphological abnormal tendency characterization parameter.

[0073] In practice, the appearance of materials that do not meet production requirements will be quite different from that of materials that meet the requirements. For example, there will be different widths at the beginning and end, and there will be more depressions on the surface. Parts processed using such raw materials are prone to abnormalities, while parts processed with materials with the opposite situation will have higher quality. Therefore, the morphological abnormality tendency characterization parameter corresponding to the material is calculated to characterize the tendency of parts processed from the material to have abnormalities, thereby providing data support for whether materials with different surface types can be counted subsequently. Under the premise of ensuring the counting of materials, the materials are classified and counted, which not only ensures the accuracy of material counting, but also ensures the quality of subsequent processed parts.

[0074] Specifically, the counting determination module determines the judgment method of whether to count each processing material according to the counting effective type of the processing material, including:

[0075] If the counting effective type of the processing material is the counting direct effective type, the judgment method is to obtain the quality information of the processing material and combine it with the preset material quality conditions to determine whether to directly count the current processing material;

[0076] If the counting effective type of the processing material is the counting indirect effective type, the judgment method is to obtain the X-ray image, process the X-ray image to obtain a uniform analysis image, and determine the uniform distribution characterization parameters of the processing material according to the uniform analysis image to determine whether to process and count the current processing material.

[0077] See also Figure 3 As shown, it is a logic diagram of determining whether to directly count the current processing material in an embodiment of the present invention, the counting determination module determines whether the quality information of the processing material meets the preset material quality conditions, and determines whether to directly count the current processing material according to the determination result;

[0078] If the quality information of the processed material meets the preset material quality conditions, the current processed material is directly counted;

[0079] If the quality information of the processed material does not meet the preset material quality conditions, the current processed material will not be directly counted.

[0080] In implementation, the preset quality condition is that the quality information of the processed material is within the preset material quality range. The method for determining the preset material range includes obtaining the average quality m0 of the processed materials directly counted in the same type of processed materials in the historical records. The preset material quality range is [0.98m0,1.02m0].

[0081] In the present invention, the counting judgment module selects the counting analysis method for different types of processing materials according to the effective counting type of the processing material. In actual situations, the shape of the material with low morphological abnormality characterization parameters is regular, and the processed parts meet the part standards in appearance. Therefore, the quality of the material is further verified for the above situation to determine whether the parts obtained by processing the material meet the standards. Then, under the premise of ensuring reliability, the quality of the material that meets the standard shape is tested to ensure that the material meets the processing requirements of the expected parts.

[0082] See also Figure 4 As shown, it is a logic diagram for determining whether to process and count the current processing material. The counting determination module determines the uniform distribution characterization parameter of the processing material according to the uniform analysis image. The uniform distribution characterization parameter is determined according to formula (2).

[0083]

[0084] In formula (2), K is the uniform distribution characterization parameter, m is the total number of analysis areas in the uniform analysis image, Sj is the grayscale average of the jth analysis area, S0 is the overall grayscale average of the uniform analysis image, and i is an integer greater than 0.

[0085] In implementation, by adjusting the strong contrast and brightness of the X-ray image, or using filters and enhancement algorithms to amplify the grayscale characterization effect in the X-ray image, it can be understood that by adjusting the contrast and brightness of the image, the grayscale difference between different density areas can be made more obvious, which can be achieved by directly adjusting the brightness and contrast parameters of the image, or applying histogram equalization to optimize the grayscale distribution of the entire image, or using various filters and enhancement algorithms to improve the quality and details of the image, especially for the noise and blurred parts that may exist in the X-ray image. Commonly used filters include median filtering, Gaussian filtering, etc., which can help remove noise and improve the clarity of the image. The specific adjustment process is not specifically limited. The uniform analysis image obtained after adjustment can see the degree of density unevenness in the metal rod;

[0086] The counting and judging module divides the uniform analysis image to obtain a number of identical analysis areas, and obtains the grayscale average value of each analysis area and the overall grayscale average value of the uniform analysis image. This is a prior art and will not be described in detail.

[0087] Specifically, the counting determines whether to process the current processing material based on the uniform distribution characteristic parameter of the processing material, including:

[0088] If the uniform distribution characterization parameter is less than or equal to the standard uniform distribution characterization parameter, the processing count is performed on the current processing material;

[0089] If the uniform distribution characterization parameter is greater than the standard uniform distribution characterization parameter, the processing count is not performed on the current processing material.

[0090] In implementation, the standard uniform distribution characterization parameters are selected within the interval [1.04, 1.07].

[0091] In this embodiment, the material to be processed and counted refers to the part product obtained by further grinding and other measures on the material, which can be a qualified product, that is, after further grinding the uneven outer part, the internal density of the part is uniform and can meet the production requirements.

[0092] In the present invention, the present invention performs internal uniformity detection on materials with a high tendency of morphological abnormalities. In actual situations, if the internal uniformity of the material is low, the strength of the processed parts will not meet the requirements. Therefore, the present invention performs uniformity detection on materials that require further grinding to ensure that the material can undergo subsequent processing operations and reduce material waste.

[0093] Specifically, the counting determination module obtains uniform distribution characterization parameters of the processing material that is not directly counted, and determines whether to perform processing counting on the current processing material.

[0094] In implementation, if the uniform distribution characterization parameter of the processing material that is not currently directly counted is less than or equal to the standard uniform distribution characterization parameter, the processing counting is performed on the processing material that is not currently directly counted, otherwise the processing counting is not performed.

[0095] It is understandable that the processed materials that are not directly counted may have internal unevenness. After further testing, if the processed materials can be ground so that the processed parts meet the requirements, the materials can be processed and counted, further reducing material waste and ensuring accurate counting of various materials.

[0096] Specifically, the material counting module includes directly counting the material, processing counting the material, and invalid counting the material;

[0097] Among them, the material for invalid counting is the material that is not directly counted and not processed. So far, the technical scheme of the present invention has been described in conjunction with the preferred embodiments shown in the drawings, but it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical schemes after these changes or substitutions will fall within the protection scope of the present invention.

[0098] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A material counting device based on machine vision, characterized in that: include: An image acquisition module, which is a camera unit for acquiring a surface detection image group of each processed material, and a projection unit for acquiring a radiographic image of the processed material; A quality detection module, connected to the image acquisition module, for acquiring quality information of each of the processed materials; A detection and analysis module, which is connected to the image acquisition module, is used to amplify the surface detection image group, extract the surface characteristics of the processed material, and determine the characteristic parameters of the morphological abnormality tendency of the processed material to determine the effective counting type of the processed material; A counting determination module, which is connected to the quality detection module and the detection and analysis module, is used to determine whether to count each processing material according to the counting effective type of the processing material, including: Obtaining the quality information of the processed material, and combining it with the preset material quality conditions to determine whether to directly count the current processed material; Or, acquiring the radiographic image, processing the radiographic image to obtain a uniform analysis image, and determining a uniform distribution characterization parameter of the processed material according to the uniform analysis image to determine whether to process and count the current processed material; A material counting module, which is connected to the counting determination module, and is used to determine whether to count the processed materials according to the result of the determination of whether to count the processed materials; The camera unit acquires surface detection image groups of each of the processed materials one by one; Wherein, the surface detection image group includes a head shape image, a tail shape image and a surface flatness image; The detection and analysis module determines the morphological abnormality tendency characterization parameter of the processed material according to the surface features of the amplified surface detection image group. The morphological abnormality tendency characterization parameter is determined according to formula (1): （1） In formula (1), C is the parameter characterizing the tendency of morphological abnormality, c0 is the circumference of the head of the processed material, c1 is the circumference of the tail of the processed material, n is the total number of divided regions in the enlarged surface flat image, si is the grayscale average value of the i-th feature region, s0 is the overall grayscale average value of the enlarged surface flat image, and i is an integer greater than 0.

2. The material counting device based on machine vision according to claim 1, characterized in that: The detection and analysis module determines the effective counting type of the processed material according to the characteristic parameter of the abnormal morphology tendency, including: If the morphological abnormality tendency characterization parameter is less than or equal to the standard morphological abnormality tendency characterization parameter, the counting effective type of the processed material is the counting direct effective type; If the morphological abnormality tendency characterization parameter is greater than the standard morphological abnormality tendency characterization parameter, the counting effective type of the processed material is the counting indirect effective type.

3. The material counting device based on machine vision according to claim 2 is characterized in that: The counting determination module determines the judgment method of whether to count each processing material according to the counting effective type of the processing material, including: If the counting effective type of the processing material is the counting direct effective type, the judgment method is to obtain the quality information of the processing material and combine it with the preset material quality conditions to determine whether to directly count the current processing material; If the counting effective type of the processing material is the counting indirect effective type, the judgment method is to obtain the X-ray image, process the X-ray image to obtain a uniform analysis image, and determine the uniform distribution characterization parameters of the processing material according to the uniform analysis image to determine whether to process and count the current processing material.

4. The material counting device based on machine vision according to claim 3 is characterized in that: The counting determination module determines whether the quality information of the processed material meets the preset material quality conditions, and determines whether to directly count the current processed material according to the determination result; If the quality information of the processed material meets the preset material quality conditions, the current processed material is directly counted; If the quality information of the processed material does not meet the preset material quality conditions, the current processed material will not be directly counted.

5. The material counting device based on machine vision according to claim 4, characterized in that: The counting determination module determines the uniform distribution characterization parameter of the processed material according to the uniform analysis image. The uniform distribution characterization parameter is determined according to formula (2): （2） In formula (2), K is the uniform distribution characterization parameter, m is the total number of analysis areas in the uniform analysis image, Sj is the grayscale average of the jth analysis area, S0 is the overall grayscale average of the uniform analysis image, and i is an integer greater than 0.

6. The material counting device based on machine vision according to claim 5, characterized in that: The counting determines whether to process and count the current processing material according to the uniform distribution characteristic parameter of the processing material. include, If the uniform distribution characterization parameter is less than or equal to the standard uniform distribution characterization parameter, the processing count is performed on the current processing material; If the uniform distribution characterization parameter is greater than the standard uniform distribution characterization parameter, the processing count is not performed on the current processing material.

7. The material counting device based on machine vision according to claim 6, characterized in that: The counting determination module obtains uniform distribution characterization parameters of the processing materials that are not directly counted, and determines whether to process and count the current processing materials.

8. The material counting device based on machine vision according to claim 7, characterized in that: The material counting module includes directly counting the material, processing counting the material, and invalid counting the material. Among them, the materials for invalid counting are materials that are not directly counted and are not processed.

Images