A capacitor appearance detection control method and device

Abstract

The present invention discloses a capacitor appearance detection control method and device, the method comprising: obtaining capacitor image information to be processed; the capacitor image information to be processed includes a plurality of capacitor images to be processed; according to the capacitor image information to be processed and a preset artificial intelligence model, determining a set of appearance detection types; the appearance detection type set includes at least one appearance detection type corresponding to the capacitor image to be processed; according to the appearance detection type set, determining a target type corresponding to a target capacitor. It can be seen that the present invention can obtain a set of appearance detection types by obtaining capacitor image information to be processed and a preset artificial intelligence model, and thereby determine a target type corresponding to a target capacitor, which is conducive to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the detection efficiency of capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a capacitive appearance detection control method and device. Background Art

[0002] Capacitor manufacturers currently usually use manual inspection of the appearance, which cannot conduct a comprehensive inspection of the capacitor appearance, is prone to missed inspections, and has low inspection efficiency. Therefore, it is particularly important to provide a capacitor appearance inspection control method to solve the problem of incomplete inspection of the capacitor appearance during the capacitor appearance inspection process and improve the inspection efficiency of the capacitor appearance, thereby improving the reliability of capacitor appearance inspection and the effectiveness of capacitor product quality inspection. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a capacitor appearance detection control method and device, which can provide a capacitor appearance detection control method to solve the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improve the detection efficiency of capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0004] In order to solve the above technical problems, a first aspect of an embodiment of the present invention discloses a capacitive appearance detection control method, the method comprising:

[0005] Acquire capacitive image information to be processed; the capacitive image information to be processed includes a plurality of capacitive images to be processed;

[0006] Determine an appearance detection type set according to the capacitive image information to be processed and a preset artificial intelligence model; the appearance detection type set includes at least one appearance detection type corresponding to the capacitive image to be processed;

[0007] According to the appearance detection type set, a target type corresponding to the target capacitance is determined.

[0008] As an optional implementation manner, in the first aspect of the embodiment of the present invention, determining the appearance detection type set according to the capacitive image information to be processed and a preset artificial intelligence model includes:

[0009] For any of the capacitive images to be processed in the capacitive image information to be processed, determining a floating-point array corresponding to the capacitive image to be processed according to the capacitive image to be processed and a preset artificial intelligence model;

[0010] According to the floating-point array and a preset threshold classification rule, the appearance detection type corresponding to the capacitive image to be processed is determined.

[0011] As an optional implementation manner, in the first aspect of the embodiment of the present invention, determining the target type corresponding to the target capacitance according to the appearance detection type set includes:

[0012] According to the appearance detection type set and a preset type discrimination rule, a target type corresponding to the target capacitance is determined; the type discrimination rule is related to the number of appearance detection types corresponding to the target type.

[0013] As an optional implementation manner, in the first aspect of the embodiment of the present invention, determining the target type corresponding to the target capacitance according to the appearance detection type set and a preset type discrimination rule includes:

[0014] Performing quantitative statistical processing on the appearance detection types corresponding to all the to-be-processed capacitive images in the appearance detection type set to obtain quantity information of the appearance detection types;

[0015] The target type corresponding to the target capacitance is determined according to the appearance detection type quantity information and a preset type discrimination rule.

[0016] As an optional implementation manner, in the first aspect of the embodiment of the present invention, before obtaining the capacitive image information to be processed, the method further includes:

[0017] Acquire original capacitive image information; the original capacitive image information includes a plurality of original capacitive images;

[0018] The original capacitive image information is processed to obtain selected capacitive image information; the selected capacitive image information includes a plurality of selected capacitive images.

[0019] As an optional implementation manner, in the first aspect of the embodiment of the present invention, after the original capacitive image information is processed to obtain the selected capacitive image information, the method further includes:

[0020] The capacitive image information to be processed is determined according to the capacitive image information to be selected and a preset screening model.

[0021] As an optional implementation manner, in the first aspect of the embodiment of the present invention, determining the capacitive image information to be processed according to the capacitive image information to be selected and a preset screening model includes:

[0022] For any of the to-be-selected capacitive images in the to-be-selected capacitive image information, determine a to-be-selected type corresponding to the to-be-selected capacitive image by using a preset screening model;

[0023] Determine whether the candidate type corresponding to the candidate capacitive image satisfies a rejection condition, and obtain a first determination result;

[0024] When the first judgment result indicates that the to-be-selected type corresponding to the to-be-selected capacitive image does not satisfy the elimination condition, the to-be-selected capacitive image is determined as the to-be-processed capacitive image.

[0025] As an optional implementation manner, in the first aspect of the embodiment of the present invention, determining the capacitive image information to be processed according to the capacitive image information to be selected and a preset screening model includes:

[0026] For any of the to-be-selected capacitive images in the to-be-selected capacitive image information, background removal is performed on the to-be-selected capacitive image using a preset screening model, and contour features are extracted to obtain the to-be-processed capacitive image.

[0027] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the method further includes:

[0028] Obtaining parameter information corresponding to the target capacitance;

[0029] And, determining a set of appearance detection types according to the capacitive image information to be processed and a preset artificial intelligence model includes:

[0030] A set of appearance detection types is determined according to the capacitive image information to be processed, the parameter information and a preset artificial intelligence model.

[0031] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the processing of the original capacitive image information to obtain the selected capacitive image information includes:

[0032] For any original capacitive image in the original capacitive image information, perform median filtering on the original capacitive image to extract image features corresponding to the original capacitive image;

[0033] Performing region division processing on the image features corresponding to the original capacitive image to obtain a first target region corresponding to the original capacitive image;

[0034] The contour of the first target area corresponding to the original capacitive image is extracted to determine a selected capacitive image corresponding to the original capacitive image.

[0035] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the processing of the original capacitive image information to obtain the selected capacitive image information includes:

[0036] For any original capacitive image in the original capacitive image information, processing the image color of the original capacitive image to obtain a capacitive image to be optimized corresponding to the original capacitive image;

[0037] Optimizing the capacitance image to be optimized corresponding to the original capacitance image to obtain a second target area corresponding to the original capacitance image;

[0038] The contour of the second target area corresponding to the original capacitive image is extracted to determine a selected capacitive image corresponding to the original capacitive image.

[0039] A second aspect of an embodiment of the present invention discloses a capacitive appearance detection control device, the device comprising:

[0040] An acquisition module, used for acquiring capacitive image information to be processed; the capacitive image information to be processed includes a plurality of capacitive images to be processed;

[0041] A first determination module is used to determine an appearance detection type set according to the capacitive image information to be processed and a preset artificial intelligence model; the appearance detection type set includes at least one appearance detection type corresponding to the capacitive image to be processed;

[0042] The second determination module is used to determine the target type corresponding to the target capacitance according to the appearance detection type set.

[0043] As an optional implementation, in the second aspect of the embodiment of the present invention, the first determining module includes a first determining submodule and a second determining submodule, wherein

[0044] The first determination submodule is used to determine, for any of the capacitive images to be processed in the capacitive image information to be processed, a floating-point array corresponding to the capacitive image to be processed according to the capacitive image to be processed and a preset artificial intelligence model;

[0045] The second determination submodule is used to determine the appearance detection type corresponding to the capacitive image to be processed according to the floating-point array and a preset threshold classification rule.

[0046] As an optional implementation manner, in the second aspect of the embodiment of the present invention, the second determination module determines the target type corresponding to the target capacitance according to the appearance detection type set in a specific manner as follows:

[0047] According to the appearance detection type set and a preset type discrimination rule, a target type corresponding to the target capacitance is determined; the type discrimination rule is related to the number of appearance detection types corresponding to the target type.

[0048] As an optional implementation, in the second aspect of the embodiment of the present invention, the second determination module determines the target type corresponding to the target capacitance according to the appearance detection type set and the preset type discrimination rule in a specific manner as follows:

[0049] Performing quantitative statistical processing on the appearance detection types corresponding to all the to-be-processed capacitive images in the appearance detection type set to obtain quantity information of the appearance detection types;

[0050] The target type corresponding to the target capacitance is determined according to the appearance detection type quantity information and a preset type discrimination rule.

[0051] As an optional implementation, in the second aspect of the embodiment of the present invention, the acquisition module is further used to acquire original capacitive image information before acquiring the capacitive image information to be processed; the original capacitive image information includes a plurality of original capacitive images;

[0052] The device also includes:

[0053] The processing module is used to process the original capacitive image information to obtain the capacitive image information to be selected; the capacitive image information to be selected includes a plurality of capacitive images to be selected.

[0054] As an optional implementation manner, in the second aspect of the embodiment of the present invention, the device further includes:

[0055] The third determination module is used to determine the capacitive image information to be processed according to the capacitive image information to be selected and a preset screening model after the processing module processes the original capacitive image information to obtain the capacitive image information to be selected.

[0056] As an optional implementation, in the second aspect of the embodiment of the present invention, the third determination module determines the specific manner of the capacitive image information to be processed according to the capacitive image information to be selected and the preset screening model as follows:

[0057] For any of the to-be-selected capacitive images in the to-be-selected capacitive image information, determine a to-be-selected type corresponding to the to-be-selected capacitive image by using a preset screening model;

[0058] Determine whether the candidate type corresponding to the candidate capacitive image satisfies a rejection condition, and obtain a first determination result;

[0059] When the first judgment result indicates that the to-be-selected type corresponding to the to-be-selected capacitive image does not satisfy the elimination condition, the to-be-selected capacitive image is determined as the to-be-processed capacitive image.

[0060] As an optional implementation, in the second aspect of the embodiment of the present invention, the third determination module determines the specific manner of the capacitive image information to be processed according to the capacitive image information to be selected and the preset screening model as follows:

[0061] For any of the to-be-selected capacitive images in the to-be-selected capacitive image information, background removal is performed on the to-be-selected capacitive image using a preset screening model, and contour features are extracted to obtain the to-be-processed capacitive image.

[0062] As an optional implementation manner, in the second aspect of the embodiment of the present invention, the acquisition module is further used to acquire parameter information corresponding to the target capacitance;

[0063] The specific manner in which the first determination module determines the appearance detection type set according to the capacitive image information to be processed and the preset artificial intelligence model is:

[0064] A set of appearance detection types is determined according to the capacitive image information to be processed, the parameter information and a preset artificial intelligence model.

[0065] As an optional implementation manner, in the second aspect of the embodiment of the present invention, the specific manner in which the processing module processes the original capacitive image information to obtain the selected capacitive image information is:

[0066] For any original capacitive image in the original capacitive image information, perform median filtering on the original capacitive image to extract image features corresponding to the original capacitive image;

[0067] Performing region division processing on the image features corresponding to the original capacitive image to obtain a first target region corresponding to the original capacitive image;

[0068] The contour of the first target area corresponding to the original capacitive image is extracted to determine a selected capacitive image corresponding to the original capacitive image.

[0069] As an optional implementation manner, in the second aspect of the embodiment of the present invention, the specific manner in which the processing module processes the original capacitive image information to obtain the selected capacitive image information is:

[0070] For any original capacitive image in the original capacitive image information, processing the image color of the original capacitive image to obtain a capacitive image to be optimized corresponding to the original capacitive image;

[0071] Optimizing the capacitance image to be optimized corresponding to the original capacitance image to obtain a second target area corresponding to the original capacitance image;

[0072] The contour of the second target area corresponding to the original capacitive image is extracted to determine a selected capacitive image corresponding to the original capacitive image.

[0073] The third aspect of the present invention discloses another capacitive appearance detection control device, the device comprising:

[0074] A memory storing executable program code;

[0075] a processor coupled to the memory;

[0076] The processor calls the executable program code stored in the memory to execute part or all of the steps in the capacitive appearance detection control method disclosed in the first aspect of the embodiment of the present invention.

[0077] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the capacitive appearance detection control method disclosed in the first aspect of the embodiment of the present invention.

[0078] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0079] In an embodiment of the present invention, the capacitor image information to be processed is obtained; the capacitor image information to be processed includes a plurality of capacitor images to be processed; a set of appearance detection types is determined based on the capacitor image information to be processed and a preset artificial intelligence model; the set of appearance detection types includes at least one appearance detection type corresponding to the capacitor image to be processed; and a target type corresponding to the target capacitor is determined based on the set of appearance detection types. It can be seen that the present invention can obtain the set of appearance detection types by obtaining the capacitor image information to be processed and the preset artificial intelligence model, and thereby determine the target type corresponding to the target capacitor, which is conducive to solving the problem of incomplete detection of the capacitor appearance during the capacitor appearance detection process and improving the detection efficiency of the capacitor appearance, thereby improving the reliability of the capacitor appearance detection and the effectiveness of the capacitor product quality inspection. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0081] Figure 1 It is a flow chart of a capacitive appearance detection control method disclosed in an embodiment of the present invention;

[0082] Figure 2 It is a flow chart of another capacitive appearance detection control method disclosed in an embodiment of the present invention;

[0083] Figure 3 It is a structural schematic diagram of a capacitive appearance detection control device disclosed in an embodiment of the present invention;

[0084] Figure 4 It is a structural schematic diagram of another capacitive appearance detection control device disclosed in an embodiment of the present invention;

[0085] Figure 5 A schematic structural diagram of another capacitive appearance detection control device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0086] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0087] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.

[0088] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0089] The present invention discloses a capacitor appearance detection control method and device, which can obtain a set of appearance detection types by acquiring capacitor image information to be processed and a preset artificial intelligence model, and thereby determine the target type corresponding to the target capacitor, which is conducive to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the detection efficiency of capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection. The following are detailed descriptions.

[0090] Embodiment 1

[0091] See also Figure 1 , Figure 1 1 is a flow chart of a capacitive appearance detection control method disclosed in an embodiment of the present invention. Figure 1The described capacitor appearance detection control method is applied to a capacitor appearance detection system, such as a local server or cloud server for aluminum electrolytic capacitor appearance detection, and the embodiments of the present invention are not limited thereto. Figure 1 As shown, the capacitive appearance detection control method may include the following operations:

[0092] 101. Obtain capacitive image information to be processed.

[0093] In the embodiment of the present invention, the capacitive image information to be processed includes a plurality of capacitive images to be processed.

[0094] 102. Determine a set of appearance detection types based on the capacitive image information to be processed and a preset artificial intelligence model.

[0095] In the embodiment of the present invention, the appearance detection type set includes at least one appearance detection type corresponding to the capacitive image to be processed.

[0096] 103. Determine a target type corresponding to the target capacitance according to the appearance detection type set.

[0097] In an embodiment of the present invention, the target type corresponding to the target capacitor is used to screen the target capacitor. For example, when the target type corresponding to the target capacitor does not meet the screening requirements, the target capacitor is eliminated; when the target type corresponding to the target capacitor meets the screening requirements, the target capacitor is confirmed to be a usable product.

[0098] In the embodiment of the present invention, the capacitor image to be processed includes one or more of a lead pin image, a top surface image, a circumferential surface image, and a bottom surface image of the target capacitor.

[0099] Optionally, the circumferential surface images include multiple circumferential surface images taken from different angles. Specifically, the multiple circumferential surface images taken from different angles are 8 images taken by 8 camera devices distributed at 45° intervals.

[0100] Optionally, the bottom surface image includes a plurality of bottom surface images obtained by taking pictures from different angles. Specifically, the plurality of bottom surface images obtained by taking pictures from different angles include a bottom surface center image and two images taken at 180° opposite angles.

[0101] Optionally, the artificial intelligence model may be a neural network model, or a deep learning network model, or other artificial intelligence algorithm models, which is not limited in the embodiment of the present invention. Preferably, the artificial intelligence model is a LeViT model. Furthermore, the size of the input image of the LeViT model is 3*224*224.

[0102] It can be seen that the capacitor appearance detection control method described in the embodiment of the present invention can obtain the capacitor image information to be processed and the preset artificial intelligence model to obtain a set of appearance detection types, and thereby determine the target type corresponding to the target capacitor, which is beneficial to solving the problem of incomplete detection of the capacitor appearance during the capacitor appearance detection process and improving the detection efficiency of the capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0103] In an optional embodiment, in the above step 102, according to the capacitive image information to be processed and the preset artificial intelligence model, a set of appearance detection types is determined, including:

[0104] For any capacitive image to be processed in the capacitive image information to be processed, determining a floating-point array corresponding to the capacitive image to be processed according to the capacitive image to be processed and a preset artificial intelligence model;

[0105] According to the floating-point array and the preset threshold classification rule, the appearance detection type corresponding to the capacitive image to be processed is determined.

[0106] In an embodiment of the present invention, for any capacitive image to be processed, the capacitive image to be processed is input into an artificial intelligence model, and a floating-point array corresponding to the capacitive image to be processed is obtained after processing, and then the maximum value subscript is obtained through numerical processing. Furthermore, the appearance detection type corresponding to the capacitive image to be processed is determined according to the maximum value subscript and the preset threshold classification rule. For example, the max function is used to process the floating-point array to obtain the maximum value in the floating-point array, and then the position information of the maximum value in the floating-point array is matched to obtain the maximum value subscript. For example, when the floating-point array is [0.5, 0.3, 0.2], the floating-point array is processed by the max function to obtain a maximum value of 0.5, and its corresponding subscript is 1, then the maximum value subscript corresponding to the floating-point array is 1.

[0107] Optionally, the appearance detection type includes genuine products, and / or suboptimal products, and / or defective products, which is not limited in the embodiment of the present invention. Further, the number of appearance detection types matches the number of elements in the floating-point array. For example, when the appearance detection type includes genuine products and suboptimal products, the number of elements in the floating-point array is 2.

[0108] Optionally, the threshold classification rule is to determine the appearance detection type based on the type threshold range. Specifically, the type threshold range corresponding to the appearance detection type where the largest value subscript is located is matched to obtain the target type threshold range, and then the appearance detection type corresponding to the largest value subscript is determined based on the target type threshold range. For example, when the appearance detection types include genuine, substandard and defective products, and the type threshold ranges corresponding to the three appearance detection types are [a1,b1), [c1,d1) and [e1,f1] respectively, the largest value subscript corresponding to the capacitive image to be processed is g1, and g1 is within the range of [c1,d1), then the appearance detection type corresponding to the capacitive image to be processed is determined to be a substandard product.

[0109] It can be seen that the capacitor appearance detection control method described in the embodiment of the present invention can determine the floating-point array of the capacitor image to be processed through the artificial intelligence model, and then determine the appearance detection type corresponding to the capacitor image to be processed in combination with the threshold classification rule, so as to achieve the determination of the target type corresponding to the target capacitor, which is conducive to solving the problem of incomplete detection of the capacitor appearance during the capacitor appearance detection process and improving the detection efficiency of the capacitor appearance, thereby improving the reliability of the capacitor appearance detection and the effectiveness of the capacitor product quality inspection.

[0110] In another optional embodiment, in the above step 103, determining the target type corresponding to the target capacitance according to the appearance detection type set includes:

[0111] According to the appearance detection type set and the preset type discrimination rule, the target type corresponding to the target capacitance is determined; the type discrimination rule is related to the number of appearance detection types corresponding to the target type.

[0112] In the embodiment of the present invention, after the appearance detection types of all the images to be processed are determined, the target type of the target capacitance is determined by using a type discrimination rule.

[0113] Optionally, the type discrimination rule is to determine the target type according to a first quantity threshold range. Specifically, the quantity threshold range of the candidate target type where the quantity of the appearance detection type is matched is obtained to obtain the target quantity threshold range, and the candidate target type corresponding to the target capacitor is determined according to the target quantity threshold range, and then the target type corresponding to the target capacitor is determined.

[0114] Optionally, the target type to be selected corresponds to all appearance detection types in the threshold classification rule. Further, each target type to be selected corresponds to a target type. For example, when the appearance detection types include genuine products, suboptimal products and defective products, and the type threshold ranges corresponding to the three target types to be selected (genuine products to be selected, suboptimal products to be selected and defective products to be selected) are [a2, b2), [c2, d2) and [e2, f2] respectively, and the quantities corresponding to the three appearance detection types (genuine products, suboptimal products and defective products) are h1, h2 and h3 respectively, it is determined whether h1 is in the range of [a2, b2). If so, the target type to be selected corresponding to the target capacitor is determined to be a genuine product to be selected, and then the target type is determined to be a genuine product; if not, it is determined whether h2 is in the range of [c2, d2). If so, the target type to be selected corresponding to the target capacitor is determined to be a suboptimal product to be selected, and then the target type is determined to be a suboptimal product; if not, it is determined that the target type to be selected corresponding to the target capacitor is a defective product to be selected, and then the target type is determined to be a defective product.

[0115] It can be seen that the capacitor appearance detection control method described in the embodiment of the present invention can use the type discrimination rule to discriminate the number of all appearance detection types to determine the target type corresponding to the target capacitor, which provides a feasible path for determining the target type corresponding to the target capacitor, and is beneficial to solving the problem of incomplete detection of the capacitor appearance during the capacitor appearance detection process and improving the detection efficiency of the capacitor appearance, thereby improving the reliability of the capacitor appearance detection and the effectiveness of the capacitor product quality inspection.

[0116] In yet another optional embodiment, the above-mentioned determining the target type corresponding to the target capacitance according to the appearance detection type set and the preset type discrimination rule includes:

[0117] Performing quantitative statistical processing on the appearance detection types corresponding to all the to-be-processed capacitive images in the appearance detection type set to obtain the quantity information of the appearance detection types;

[0118] According to the appearance detection type quantity information and preset type discrimination rules, the target type corresponding to the target capacitor is determined.

[0119] In an embodiment of the present invention, the appearance detection types in the appearance detection type set are divided into type categories, and then the number of appearance detection types in each category is counted to obtain the number of elements corresponding to each category. Further, the number of elements corresponding to any category is determined as the number of appearance detection types corresponding to the category. Optionally, the above-mentioned type categories correspond to the appearance detection types in the type discrimination rules. For example, when the target types to be selected in the type discrimination rules include genuine products to be selected, suboptimal products to be selected, and defective products to be selected, the corresponding type categories include genuine product categories, suboptimal product categories, and defective product categories, and the appearance detection types corresponding to the to-be-processed capacitor images in the appearance detection type set include the appearance detection type corresponding to the stitch image as genuine, the appearance detection type corresponding to the top surface image as genuine, the appearance detection type of the first circular surface image as genuine, the appearance detection type of the second circular surface image as genuine, and the appearance detection type of the third circular surface image as suboptimal. The stitch image, top surface image, first circumferential surface image, and second circumferential surface image are classified into the genuine product category, and the third circumferential surface image is classified into the suboptimal product category. There is no element in the defective product category. The number of elements in the genuine product category is counted as 4, the number of elements in the suboptimal product category is 1, and the number of elements in the defective product category is 0. Further, it is determined that the number of appearance inspection types (genuine products) corresponding to the genuine product category is 4, the number of appearance inspection types (suboptimal products) corresponding to the suboptimal product category is 1, and the number of appearance inspection types (defective products) corresponding to the defective product category is 0.

[0120] It can be seen that the implementation of the capacitor appearance detection control method described in the embodiment of the present invention can separately count the number of appearance detection types so as to determine the target type corresponding to the target capacitor, which is more conducive to solving the problem of incomplete detection of the capacitor appearance during the capacitor appearance detection process and improving the detection efficiency of the capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0121] In yet another optional embodiment, the capacitive appearance detection control method further includes:

[0122] Obtain parameter information corresponding to the target capacitance;

[0123] And, according to the capacitive image information to be processed and the preset artificial intelligence model, a set of appearance detection types is determined, including:

[0124] A set of appearance detection types is determined based on the capacitive image information to be processed, parameter information and a preset artificial intelligence model.

[0125] In an embodiment of the present invention, before processing the image to be processed, parameter information corresponding to the target capacitance is first obtained, and then processed by the above-mentioned artificial intelligence model to obtain standard reference information for processing the corresponding image to be processed, so that the artificial intelligence model can predict the image to be processed and obtain a floating-point array of the image to be processed.

[0126] Optionally, the parameter information corresponding to the target capacitor includes size information of the target capacitor, and / or specification information of the target capacitor, and / or temperature information of the target capacitor, and / or color information of the target capacitor, which is not limited in the implementation of the present invention.

[0127] It can be seen that the implementation of the capacitor appearance detection control method described in the embodiment of the present invention can determine the appearance detection type corresponding to the image to be processed in combination with the parameter information corresponding to the target capacitance, so as to achieve the determination of the target type corresponding to the target capacitance, which is more conducive to solving the problem of incomplete detection of the capacitor appearance during the capacitor appearance detection process and improving the detection efficiency of the capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0128] Embodiment 2

[0129] See also Figure 2 , Figure 2 is a flow chart of another capacitive appearance detection control method disclosed in an embodiment of the present invention. Figure 2 The described capacitor appearance detection control method can obtain the capacitor image information to be processed and the preset artificial intelligence model to obtain the appearance detection type set, and thereby determine the target type corresponding to the target capacitor, which is conducive to solving the problem of incomplete detection of the capacitor appearance during the capacitor appearance detection process and improving the detection efficiency of the capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection. Figure 2 As shown, the capacitive appearance detection control method may include the following operations:

[0130] 201. Obtain original capacitive image information.

[0131] In the embodiment of the present invention, the original capacitive image information includes a plurality of original capacitive images.

[0132] 202. Process the original capacitive image information to obtain the capacitive image information to be selected.

[0133] In the embodiment of the present invention, the to-be-selected capacitive image information includes a plurality of to-be-selected capacitive images.

[0134] 203. Obtain capacitive image information to be processed.

[0135] 204. Determine a set of appearance detection types based on the capacitive image information to be processed and a preset artificial intelligence model.

[0136] 205. Determine a target type corresponding to the target capacitance according to the appearance detection type set.

[0137] In the embodiment of the present invention, for the specific technical details and technical terminology explanations of steps 203 to 205, reference may be made to the detailed description of steps 101 to 103 in the first embodiment, and the embodiment of the present invention will not be repeated herein.

[0138] In the embodiment of the present invention, the original capacitive image may be acquired by a camera device, or may be input after being processed by a smart terminal, which is not limited in the embodiment of the present invention.

[0139] Optionally, the processing of the original capacitive image is to pre-process the acquired original capacitive image, including processing of the image orientation and image color, so that the processed image can be suitable for the artificial intelligence model.

[0140] It can be seen that the capacitor appearance detection control method described in the embodiment of the present invention can obtain a selected capacitor image by processing the original capacitor image, thereby obtaining the information of the capacitor image to be processed, and then obtaining a set of appearance detection types through a preset artificial intelligence model, and thereby determining the target type corresponding to the target capacitor, which is conducive to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the detection efficiency of capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0141] In an optional embodiment, after the original capacitive image information is processed to obtain the selected capacitive image information, the capacitive appearance detection control further includes:

[0142] The capacitive image information to be processed is determined according to the capacitive image information to be selected and a preset screening model.

[0143] In the embodiment of the present invention, after the original capacitive image is processed to obtain the capacitive image to be selected, the capacitive image to be selected is screened using a preset screening model to obtain the capacitive image to be processed.

[0144] Optionally, the screening model is an image processing model based on Opencv. For example, the image processing model based on Opencv is an image recognition model of Opencv.

[0145] It can be seen that the capacitor appearance detection control method described in the embodiment of the present invention can determine the capacitor image information to be processed through the screening model, which is more conducive to solving the problem of incomplete detection of the capacitor appearance during the capacitor appearance detection process and improving the detection efficiency of the capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0146] In another optional embodiment, the method of determining the capacitive image information to be processed according to the capacitive image information to be selected and a preset screening model includes:

[0147] For any capacitor image to be selected in the capacitor image information to be selected, a candidate type corresponding to the capacitor image to be selected is determined by using a preset screening model;

[0148] Determine whether the candidate type corresponding to the candidate capacitive image satisfies a rejection condition, and obtain a first determination result;

[0149] When the first judgment result indicates that the to-be-selected type corresponding to the to-be-selected capacitive image does not satisfy the elimination condition, the to-be-selected capacitive image is determined as the to-be-processed capacitive image.

[0150] In the implementation example of the present invention, the screening model is used to identify the capacitor image to be selected, and the type to be selected corresponding to the capacitor image to be selected is determined.

[0151] Optionally, the above screening model can determine the type of the selected capacitor image by comparing the target feature of the selected capacitor image with the standard feature of the target capacitor. Specifically, the type of the selected capacitor image is determined according to the degree of matching between the target feature of the selected capacitor image and the standard feature of the target capacitor.

[0152] Optionally, the standard features of the above-mentioned target capacitor include contour area information of the target capacitor, and / or, color gamut area information of the target capacitor, and / or, reverse projection contrast histogram information of the target capacitor, and / or, white straight line information of the capacitance cylinder of the target capacitor, and / or, size information of the target capacitor, which is not limited to the implementation examples of the present invention.

[0153] Optionally, the above-mentioned types to be selected include genuine products, and / or sub-optimal products, and / or defective products, which are not limited in this embodiment of the present invention.

[0154] Optionally, the above-mentioned elimination condition is that the capacitor type is a suboptimal product and / or a defective product, which is not limited in the embodiment of the present invention.

[0155] In this optional embodiment, as an optional implementation, when the above-mentioned rejection condition is that the capacitor type is a defective product.

[0156] Determine whether the type to be selected matches the defective product;

[0157] When the type to be selected does not match the defective product, it means that the type to be selected corresponding to the capacitor image to be selected does not meet the rejection condition;

[0158] When the candidate type matches the defective product, it means that the candidate type corresponding to the candidate capacitor image meets the rejection condition, and this process ends.

[0159] In this optional embodiment, as an optional implementation, when the above-mentioned rejection condition is that the capacitor type is a suboptimal product, or the capacitor type is a defective product.

[0160] Determine whether the candidate type matches the suboptimal product;

[0161] When the candidate type matches the suboptimal product, it means that the candidate type corresponding to the candidate capacitor image meets the rejection condition, and this process ends;

[0162] When the type to be selected does not match the suboptimal product, determine whether the type to be selected matches the defective product;

[0163] When the candidate type matches the defective product, it means that the candidate type corresponding to the candidate capacitor image meets the rejection condition, and this process ends;

[0164] When the candidate type does not match the defective product, it means that the candidate type corresponding to the candidate capacitor image does not meet the rejection condition.

[0165] It can be seen that the capacitor appearance detection control method described in the embodiment of the present invention can use the screening model to determine the candidate type of the capacitor image to be selected, and judge the candidate capacitor image to determine whether it can be determined as the capacitor image to be processed, which is more conducive to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the detection efficiency of capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0166] In yet another optional embodiment, the above-mentioned determining the capacitive image information to be processed according to the capacitive image information to be selected and the preset screening model includes:

[0167] For any capacitor image to be selected in the capacitor image information to be selected, a background removal process is performed on the capacitor image to be selected using a preset screening model, and contour features are extracted to obtain a capacitor image to be processed.

[0168] In an embodiment of the present invention, a screening model is used to separate the background and target capacitance of a capacitor image to be selected, and contour features of the target capacitance are extracted to weaken the interference of filtering out background information in a floating-point array for predicting and identifying the target capacitance using an artificial intelligence model.

[0169] It can be seen that the implementation of the capacitor appearance detection control method described in the embodiment of the present invention can perform background processing on the selected capacitor image and extract contour features to obtain the capacitor image to be processed, which is more conducive to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the detection efficiency of capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0170] In yet another optional embodiment, the original capacitive image information is processed in the above step 202 to obtain the capacitive image information to be selected, including:

[0171] For any original capacitive image in the original capacitive image information, perform median filtering on the original capacitive image to extract image features corresponding to the original capacitive image;

[0172] Performing region division processing on the image features corresponding to the original capacitive image to obtain a first target region corresponding to the original capacitive image;

[0173] The contour of the first target area corresponding to the original capacitive image is extracted to determine a selected capacitive image corresponding to the original capacitive image.

[0174] In an embodiment of the present invention, after the original capacitor image is acquired, it is necessary to preprocess the original capacitor image to eliminate some defect points in the image so as to use the artificial intelligence model to predict and identify the floating-point array of the target capacitor and reduce the probability of misjudgment.

[0175] Optionally, before the above median filtering process, the original capacitive image needs to be grayscaled to obtain a grayscale image.

[0176] Optionally, median filtering is used to eliminate noise mixed in the original capacitance image by performing a grayscale filtering on the image, and image features corresponding to the target capacitance are extracted to obtain a median filtered image.

[0177] Optionally, binarization and adaptive binarization processing are performed on the median filtered image to separate background information and target capacitance image information in the median filtered image to obtain a binarized image.

[0178] Optionally, an opening operation of first erosion and then dilation is performed on the binary image to remove noise in the binary image and obtain an operation image.

[0179] Optionally, edges of target capacitance information in the computation image are detected to extract discontinuous features corresponding to the target capacitance, so as to divide a first target area corresponding to the target capacitance;

[0180] Optionally, by searching for the regional contour features corresponding to the first target region, the first target feature region corresponding to the target capacitor is extracted to obtain a selected capacitor image corresponding to the original capacitor image. For example, the regional contour features corresponding to the target capacitor are determined by searching for the outer circle radius corresponding to the first target region, and the region corresponding to the outer circle radius is extracted as the first target feature region, and the first target feature region is determined as the selected capacitor image corresponding to the original capacitor image.

[0181] Preferably, the original capacitive image includes a top surface image.

[0182] It can be seen that the capacitor appearance detection control method described in the embodiment of the present invention can perform median filtering and area division processing on the original capacitor image to obtain a selected capacitor image, which is more conducive to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the efficiency of capacitor appearance detection, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0183] In yet another optional embodiment, the original capacitive image information is processed in the above step 202 to obtain the capacitive image information to be selected, including:

[0184] For any original capacitive image in the original capacitive image information, the image color of the original capacitive image is processed to obtain a capacitive image to be optimized corresponding to the original capacitive image;

[0185] Optimizing the capacitance image to be optimized corresponding to the original capacitance image to obtain a second target area corresponding to the original capacitance image;

[0186] The contour of the second target area corresponding to the original capacitive image is extracted to determine a selected capacitive image corresponding to the original capacitive image.

[0187] In an embodiment of the present invention, after the original capacitor image is acquired, it is necessary to preprocess the original capacitor image to eliminate some defect points in the image so as to use the artificial intelligence model to predict and identify the floating-point array of the target capacitor and reduce the probability of misjudgment.

[0188] Optionally, image color processing of the original capacitive image includes filtering colors irrelevant to the target capacitive color, and / or, smoothing the original capacitive image to eliminate noise, and / or, processing the original capacitive image from RGB to HSV, which is not limited in this embodiment of the present invention.

[0189] Optionally, the optimizing processing of the capacitive image to be optimized corresponding to the original capacitive image includes optimizing processing of the capacitive image to be optimized, and / or performing an opening operation on the capacitive image to be optimized to remove small noise points, which is not limited in the embodiment of the present invention.

[0190] Optionally, the optimization processing of the capacitive image to be optimized includes binarizing the capacitive image to be optimized according to an image threshold value, for example, setting pixels within the image threshold value to white, and setting pixels outside the image threshold value to black.

[0191] Optionally, the above-mentioned extraction of the contour of the second target area corresponding to the original capacitive image includes detecting the contour edges of each feature in the second target area to find the feature with the largest area in the second target area, and extracting the feature as a selected capacitive image corresponding to the original capacitive image.

[0192] Preferably, the original capacitive image includes one or more of a top surface image, a circumferential surface image, and a bottom surface image.

[0193] It can be seen that the implementation of the capacitor appearance detection control method described in the embodiment of the present invention can perform image color and further optimization processing on the original capacitor image to obtain a selected capacitor image, which is more conducive to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the efficiency of capacitor appearance detection, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0194] Embodiment 3

[0195] See also Figure 3 , Figure 3 : is a schematic diagram of a capacitive appearance detection control device disclosed in an embodiment of the present invention. Figure 3 The described device can obtain the capacitor image information to be processed and the preset artificial intelligence model to obtain the appearance detection type set, and thereby determine the target type corresponding to the target capacitor, which is conducive to solving the problem of incomplete detection of the capacitor appearance during the capacitor appearance detection process and improving the detection efficiency of the capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection. Figure 3 As shown, the device may include:

[0196] The acquisition module 301 is used to acquire the capacitive image information to be processed; the capacitive image information to be processed includes a plurality of capacitive images to be processed;

[0197] The first determination module 302 is used to determine an appearance detection type set according to the capacitive image information to be processed and a preset artificial intelligence model; the appearance detection type set includes at least one appearance detection type corresponding to the capacitive image to be processed;

[0198] The second determination module 303 is used to determine the target type corresponding to the target capacitance according to the appearance detection type set.

[0199] It can be seen that the implementation Figure 3The described capacitor appearance detection control device can obtain a set of appearance detection types by acquiring capacitor image information to be processed and a preset artificial intelligence model, and thereby determine the target type corresponding to the target capacitor, which is conducive to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the efficiency of capacitor appearance detection, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0200] In another optional embodiment, Figure 4 As shown, the first determination module 302 includes a first determination submodule 3021 and a second determination submodule 3022, wherein

[0201] The first determination submodule 3021 is used to determine, for any capacitive image to be processed in the capacitive image information to be processed, a floating-point array corresponding to the capacitive image to be processed according to the capacitive image to be processed and a preset artificial intelligence model;

[0202] The second determination submodule 3022 is used to determine the appearance detection type corresponding to the capacitive image to be processed according to the floating-point array and a preset threshold classification rule.

[0203] It can be seen that the implementation Figure 4 The described capacitor appearance detection control device can determine the floating-point array of the capacitor image to be processed through an artificial intelligence model, and then determine the appearance detection type corresponding to the capacitor image to be processed in combination with the threshold classification rule, so as to achieve the determination of the target type corresponding to the target capacitor, which is conducive to solving the problem of incomplete detection of the capacitor appearance during the capacitor appearance detection process and improving the detection efficiency of the capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0204] In yet another optional embodiment, Figure 4 As shown, the second determination module 303 determines the target type corresponding to the target capacitance according to the appearance detection type set in a specific manner as follows:

[0205] According to the appearance detection type set and the preset type discrimination rule, the target type corresponding to the target capacitance is determined; the type discrimination rule is related to the number of appearance detection types corresponding to the target type.

[0206] It can be seen that the implementation Figure 4 The described capacitor appearance detection control device can use type discrimination rules to discriminate the number of all appearance detection types to determine the target type corresponding to the target capacitor, providing a feasible path for determining the target type corresponding to the target capacitor, which is beneficial to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the efficiency of capacitor appearance detection, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0207] In yet another optional embodiment, Figure 4 As shown, the second determination module 303 determines the target type corresponding to the target capacitance in the following specific manner according to the appearance detection type set and the preset type discrimination rule:

[0208] Performing quantitative statistical processing on the appearance detection types corresponding to all the to-be-processed capacitive images in the appearance detection type set to obtain the quantity information of the appearance detection types;

[0209] According to the appearance detection type quantity information and preset type discrimination rules, the target type corresponding to the target capacitor is determined.

[0210] It can be seen that the implementation Figure 4 The described capacitor appearance detection control device can count the number of appearance detection types separately so as to determine the target type corresponding to the target capacitor, which is more conducive to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the efficiency of capacitor appearance detection, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0211] In yet another optional embodiment, Figure 4 As shown, the acquisition module 301 is also used to acquire original capacitive image information before acquiring the capacitive image information to be processed; the original capacitive image information includes a plurality of original capacitive images;

[0212] The device also includes:

[0213] The processing module 304 is used to process the original capacitive image information to obtain the capacitive image information to be selected; the capacitive image information to be selected includes a plurality of capacitive images to be selected.

[0214] It can be seen that the implementation Figure 4 The described capacitor appearance detection control device can obtain a selected capacitor image by processing the original capacitor image, thereby acquiring information about the capacitor image to be processed, and then obtain a set of appearance detection types through a preset artificial intelligence model, and thereby determine the target type corresponding to the target capacitor, which is conducive to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the efficiency of capacitor appearance detection, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0215] In yet another optional embodiment, Figure 4 As shown, the device also includes:

[0216] The third determination module 305 is used to determine the capacitive image information to be processed according to the capacitive image information to be selected and a preset screening model after the processing module 304 processes the original capacitive image information to obtain the capacitive image information to be selected.

[0217] It can be seen that the implementation Figure 4 The described capacitor appearance detection control device can determine the capacitor image information to be processed through a screening model, which is more conducive to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the efficiency of capacitor appearance detection, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0218] In yet another optional embodiment, Figure 4 As shown, the specific manner in which the third determination module 305 determines the capacitive image information to be processed according to the capacitive image information to be selected and the preset screening model is:

[0219] For any capacitor image to be selected in the capacitor image information to be selected, a candidate type corresponding to the capacitor image to be selected is determined by using a preset screening model;

[0220] Determine whether the candidate type corresponding to the candidate capacitive image satisfies a rejection condition, and obtain a first determination result;

[0221] When the first judgment result indicates that the to-be-selected type corresponding to the to-be-selected capacitive image does not satisfy the elimination condition, the to-be-selected capacitive image is determined as the to-be-processed capacitive image.

[0222] It can be seen that the implementation Figure 4 The described capacitor appearance detection control device can use a screening model to determine the candidate type of a candidate capacitor image, and judge the candidate capacitor image to determine whether it can be determined as a capacitor image to be processed. It is more conducive to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the efficiency of capacitor appearance detection, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0223] In yet another optional embodiment, Figure 4 As shown, the specific manner in which the third determination module 305 determines the capacitive image information to be processed according to the capacitive image information to be selected and the preset screening model is:

[0224] For any capacitor image to be selected in the capacitor image information to be selected, a background removal process is performed on the capacitor image to be selected using a preset screening model, and contour features are extracted to obtain a capacitor image to be processed.

[0225] It can be seen that the implementation Figure 4The described capacitor appearance detection control device can perform background processing on the capacitor image to be selected and extract contour features to obtain the capacitor image to be processed, which is more conducive to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the detection efficiency of capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0226] In yet another optional embodiment, Figure 4 As shown, the acquisition module 301 is also used to obtain parameter information corresponding to the target capacitance;

[0227] The first determination module 302 determines the appearance detection type set according to the capacitive image information to be processed and the preset artificial intelligence model in the following specific manner:

[0228] A set of appearance detection types is determined based on the capacitive image information to be processed, parameter information and a preset artificial intelligence model.

[0229] It can be seen that the implementation Figure 4 The described capacitor appearance detection control device can determine the appearance detection type corresponding to the image to be processed in combination with the parameter information corresponding to the target capacitor, so as to achieve the determination of the target type corresponding to the target capacitor, which is more conducive to solving the problem of incomplete detection of the capacitor appearance during the capacitor appearance detection process and improving the detection efficiency of the capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0230] In yet another optional embodiment, Figure 4 As shown, the specific manner in which the processing module 304 processes the original capacitive image information to obtain the capacitive image information to be selected is:

[0231] For any original capacitive image in the original capacitive image information, perform median filtering on the original capacitive image to extract image features corresponding to the original capacitive image;

[0232] Performing region division processing on the image features corresponding to the original capacitive image to obtain a first target region corresponding to the original capacitive image;

[0233] The contour of the first target area corresponding to the original capacitive image is extracted to determine a selected capacitive image corresponding to the original capacitive image.

[0234] It can be seen that the implementation Figure 4 The described capacitor appearance detection control device can perform median filtering and area division processing on the original capacitor image to obtain a selected capacitor image, which is more conducive to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the efficiency of capacitor appearance detection, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0235] In yet another optional embodiment, Figure 4 As shown, the specific manner in which the processing module 304 processes the original capacitive image information to obtain the capacitive image information to be selected is:

[0236] For any original capacitive image in the original capacitive image information, the image color of the original capacitive image is processed to obtain a capacitive image to be optimized corresponding to the original capacitive image;

[0237] Optimizing the capacitance image to be optimized corresponding to the original capacitance image to obtain a second target area corresponding to the original capacitance image;

[0238] The contour of the second target area corresponding to the original capacitive image is extracted to determine a selected capacitive image corresponding to the original capacitive image.

[0239] It can be seen that the implementation Figure 4 The described capacitor appearance detection control device can perform image color and further optimization processing on the original capacitor image to obtain a selected capacitor image, which is more conducive to solving the problem of incomplete detection of capacitor appearance during capacitor appearance detection and improving the efficiency of capacitor appearance detection, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection.

[0240] Embodiment 4

[0241] See also Figure 5 , Figure 5 is a schematic diagram of the structure of another capacitive appearance detection control device disclosed in an embodiment of the present invention. Figure 5 The described device can obtain the capacitor image information to be processed and the preset artificial intelligence model to obtain the appearance detection type set, and thereby determine the target type corresponding to the target capacitor, which is conducive to solving the problem of incomplete detection of the capacitor appearance during the capacitor appearance detection process and improving the detection efficiency of the capacitor appearance, thereby improving the reliability of capacitor appearance detection and the effectiveness of capacitor product quality inspection. Figure 5 As shown, the device may include:

[0242] A memory 401 storing executable program codes;

[0243] a processor 402 coupled to the memory 401;

[0244] The processor 402 calls the executable program code stored in the memory 401 to execute the steps in the capacitive appearance detection control method described in the first or second embodiment.

[0245] Embodiment 5

[0246] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the capacitive appearance detection control method described in the first or second embodiment.

[0247] Embodiment 6

[0248] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps in the capacitive appearance detection control method described in Embodiment 1 or Embodiment 2.

[0249] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0250] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or partly contributed to the prior art in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0251] Finally, it should be noted that the capacitive appearance detection control method and device disclosed in the embodiments of the present invention disclose only the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A capacitive appearance detection control method, characterized in that: The capacitor is an aluminum electrolytic capacitor, and the method comprises: Acquire capacitive image information to be processed; the capacitive image information to be processed includes a plurality of capacitive images to be processed; Determine an appearance detection type set according to the capacitive image information to be processed and a preset artificial intelligence model; the appearance detection type set includes at least one appearance detection type corresponding to the capacitive image to be processed; Determine the target type corresponding to the target capacitance according to the appearance detection type set and a preset type discrimination rule; the type discrimination rule is related to the number of appearance detection types corresponding to the target type; The method of determining a set of appearance detection types based on the capacitive image information to be processed and a preset artificial intelligence model includes: for any of the capacitive images to be processed in the capacitive image information to be processed, determining a floating-point array corresponding to the capacitive image to be processed based on the capacitive image to be processed and a preset artificial intelligence model; determining an appearance detection type corresponding to the capacitive image to be processed based on the floating-point array and a preset threshold classification rule; the number of appearance detection types matches the number of elements in the floating-point array, and the threshold classification rule is to judge the appearance detection type based on a type threshold range.

2. The capacitive appearance detection control method according to claim 1, characterized in that: The determining the target type corresponding to the target capacitance according to the appearance detection type set and a preset type discrimination rule includes: Performing quantitative statistical processing on the appearance detection types corresponding to all the to-be-processed capacitive images in the appearance detection type set to obtain quantity information of the appearance detection types; The target type corresponding to the target capacitance is determined according to the appearance detection type quantity information and a preset type discrimination rule.

3. The capacitive appearance detection control method according to claim 1, characterized in that: Before acquiring the capacitive image information to be processed, the method further includes: Acquire original capacitive image information; the original capacitive image information includes a plurality of original capacitive images; The original capacitive image information is processed to obtain selected capacitive image information; the selected capacitive image information includes a plurality of selected capacitive images.

4. The capacitive appearance detection control method according to claim 3, characterized in that: After the original capacitive image information is processed to obtain the capacitive image information to be selected, the method further includes: The capacitive image information to be processed is determined according to the capacitive image information to be selected and a preset screening model.

5. The capacitive appearance detection control method according to claim 4, characterized in that: The step of determining the capacitive image information to be processed according to the capacitive image information to be selected and a preset screening model includes: For any of the to-be-selected capacitive images in the to-be-selected capacitive image information, determine a to-be-selected type corresponding to the to-be-selected capacitive image by using a preset screening model; Determine whether the candidate type corresponding to the candidate capacitive image satisfies a rejection condition, and obtain a first determination result; When the first judgment result indicates that the to-be-selected type corresponding to the to-be-selected capacitive image does not satisfy the elimination condition, the to-be-selected capacitive image is determined as the to-be-processed capacitive image.

6. The capacitive appearance detection control method according to claim 4, characterized in that: The step of determining the capacitive image information to be processed according to the capacitive image information to be selected and a preset screening model includes: For any of the to-be-selected capacitive images in the to-be-selected capacitive image information, background removal is performed on the to-be-selected capacitive image using a preset screening model, and contour features are extracted to obtain the to-be-processed capacitive image.

7. A capacitive appearance detection control device, characterized in that: The device comprises: An acquisition module, used for acquiring capacitive image information to be processed; the capacitive image information to be processed includes a plurality of capacitive images to be processed; A first determination module is used to determine an appearance detection type set according to the capacitive image information to be processed and a preset artificial intelligence model; the appearance detection type set includes at least one appearance detection type corresponding to the capacitive image to be processed; A second determination module is used to determine the target type corresponding to the target capacitance according to the appearance detection type set and a preset type discrimination rule; the type discrimination rule is related to the number of appearance detection types corresponding to the target type; The first determination module includes a first determination submodule and a second determination submodule; wherein the first determination submodule is used to determine, for any of the capacitive images to be processed in the capacitive image information to be processed, a floating-point array corresponding to the capacitive image to be processed according to the capacitive image to be processed and a preset artificial intelligence model; the second determination submodule is used to determine the appearance detection type corresponding to the capacitive image to be processed according to the floating-point array and a preset threshold classification rule; the number of appearance detection types matches the number of elements in the floating-point array, and the threshold classification rule is to determine the appearance detection type according to the type threshold range.

8. A capacitive appearance detection control device, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the capacitive appearance detection control method according to any one of claims 1 to 6.

Images