An industrial defect detection method and system based on artificial intelligence

Abstract

The present invention is applicable to the technical field of industrial defect detection, and provides an industrial defect detection method and system based on artificial intelligence. The present invention determines a detection stable region by obtaining historical detection data and standard product images, and intercepts a standard region image; based on artificial intelligence, performs detection adjustment to obtain a detection captured image; intercepts the corresponding region image, performs similarity comparison calculation, and determines whether there are similar detection conditions; when there are similar detection conditions, performs defect detection on the detection captured image and performs detection marking. It can determine the detection stable region, intercept the standard region image, during the product detection process, intercept the corresponding region image, perform similarity comparison calculation, and when there are similar detection conditions, perform defect detection and marking on the detection captured image, so as to realize the verification before defect detection, avoid generating false detection results, effectively improve the accuracy and reliability of industrial defect detection, and ensure the normal production of products.

Description

Technical Field

[0001] The present invention belongs to the technical field of industrial defect detection, and in particular relates to an industrial defect detection method and system based on artificial intelligence. Background Art

[0002] Industrial defect detection is to use a series of technical means to detect products comprehensively and throughout the production and manufacturing process to identify possible defects, including various forms such as cracks, scratches, stains, dimensional deviations, pores, inclusions, and circuit problems.

[0003] Image detection of industrial defects is one of the common technical means for industrial defect detection.

[0004] In the prior art, image detection of industrial defects mainly relies on direct image comparison. However, in special situations such as changes in illumination brightness, illumination occlusion, and changes in the placement position of products, it will cause the misdetection result that a product without defects is detected and identified as a defective product, resulting in the accuracy and reliability of industrial defect detection not being guaranteed, and further affecting the normal production of products. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide an industrial defect detection method and system based on artificial intelligence, aiming to solve the technical problems existing in the prior art mentioned in the background art.

[0006] The embodiments of the present invention are implemented as follows:

[0007] An industrial defect detection method based on artificial intelligence, the method specifically includes the following steps:

[0008] Obtain the historical detection data and standard product images of the target industrial product, perform detection stability analysis, determine the detection stable area from the standard product images, and intercept the standard area images;

[0009] Determine the current detected product, based on artificial intelligence, perform detection adjustment on the current detected product, and perform detection shooting to obtain the detection shooting images;

[0010] Intercept the corresponding area images of the detection stable area from the detection shooting images, perform similarity comparison calculation on the corresponding area images and the standard area images, and determine whether there are similar detection conditions;

[0011] When there are similar detection conditions, based on the standard product images, perform defect detection on the detection shooting images and perform detection marking on the current detected product.

[0012] As a further limitation of the technical solution of the embodiment of the present invention, the steps of obtaining the historical detection data and standard product image of the target industrial product, performing detection stability analysis, determining the detection stable area from the standard product image, and intercepting the standard area image specifically include the following steps:

[0013] Receive detection planning information and determine the target industrial product;

[0014] Obtain the historical detection data and standard product image of the target industrial product;

[0015] Based on the standard product image, perform detection stability analysis on the historical detection data, and determine the detection stable area from the standard product image;

[0016] In the standard product image, intercept the standard area image of the detection stable area.

[0017] As a further limitation of the technical solution of the embodiment of the present invention, the steps of determining the current detection product, performing detection adjustment on the current detection product based on artificial intelligence, and performing detection shooting to obtain a detection shooting image specifically include the following steps:

[0018] Obtain the detection adjustment parameters of the target industrial product;

[0019] Determine the current detection product in real time;

[0020] Based on artificial intelligence, perform detection adjustment on the current detection product according to the detection adjustment parameters;

[0021] Perform detection shooting to obtain a detection shooting image.

[0022] As a further limitation of the technical solution of the embodiment of the present invention, the steps of intercepting the corresponding area image of the detection stable area from the detection shooting image, performing similarity comparison calculation on the corresponding area image and the standard area image, and determining whether there are similar detection conditions specifically include the following steps:

[0023] Intercept the corresponding area image of the detection stable area from the detection shooting image;

[0024] Perform similarity comparison calculation on the corresponding area image and the standard area image to obtain a similarity comparison value;

[0025] Compare the similarity comparison value with a preset standard threshold and record the comparison result;

[0026] According to the comparison result, determine whether there are similar detection conditions.

[0027] As a further limitation of the technical solution of the embodiment of the present invention, the step of performing similarity comparison calculation on the corresponding region image and the standard region image to obtain a similarity comparison value specifically includes the following steps:

[0028] Perform grayscale processing on the corresponding region image to generate a corresponding grayscale image;

[0029] Perform grayscale processing on the standard region image to generate a standard grayscale image;

[0030] Perform similarity comparison calculation on the corresponding grayscale image and the standard grayscale image to obtain a similarity comparison value.

[0031] As a further limitation of the technical solution of the embodiment of the present invention, the calculation formula of the similarity comparison value is:

[0032]

[0033] Where N is the similarity comparison value, d represents the corresponding grayscale image, s represents the standard grayscale image, u d is the average brightness corresponding to the corresponding grayscale image, u s is the average brightness corresponding to the standard grayscale image, σ d is the standard deviation corresponding to the corresponding grayscale image, σ s is the standard deviation corresponding to the standard grayscale image, σ ds is the covariance between the corresponding grayscale image and the standard grayscale image, L is the value range of pixel values, k1 is a preset first adjustment coefficient, and k2 is a preset second adjustment coefficient.

[0034] As a further limitation of the technical solution of the embodiment of the present invention, when there are similar detection conditions, based on the standard product image, defect detection is performed on the detected and captured image, and detection marking is performed on the current detected product, which specifically includes the following steps:

[0035] When there are similar detection conditions, based on the standard product image, defect detection is performed on the detected and captured image to obtain a defect detection result;

[0036] Identify the detected and captured image to obtain the current product identity of the current detected product;

[0037] According to the current product identity and the defect detection result, detection marking is performed on the current detected product.

[0038] An industrial defect detection system based on artificial intelligence, the system includes a detection stability analysis module, a detection adjustment and shooting module, a similarity comparison and judgment module, and a defect detection and marking module, where:

[0039] The detection stability analysis module is used to obtain the historical detection data and standard product images of the target industrial product, perform detection stability analysis, determine the detection stability area from the standard product images, and intercept the standard area images;

[0040] The detection adjustment shooting module is used to determine the current product to be detected, perform detection adjustment on the current product to be detected based on artificial intelligence, and perform detection shooting to obtain detection shooting images;

[0041] The similarity comparison and judgment module is used to intercept the corresponding area images of the detection stability area from the detection shooting images, perform similarity comparison calculations on the corresponding area images and the standard area images, and judge whether there are similar detection conditions;

[0042] The defect detection and marking module is used to perform defect detection on the detection shooting images based on the standard product images and perform detection marking on the current product to be detected when there are similar detection conditions.

[0043] As a further limitation of the technical solution of the embodiment of the present invention, the detection stability analysis module specifically includes:

[0044] The product determination unit is used to receive detection planning information and determine the target industrial product;

[0045] The data acquisition unit is used to obtain the historical detection data and standard product images of the target industrial product;

[0046] The stability analysis unit is used to perform detection stability analysis on the historical detection data based on the standard product images and determine the detection stability area from the standard product images;

[0047] The standard interception unit is used to intercept the standard area images of the detection stability area in the standard product images.

[0048] As a further limitation of the technical solution of the embodiment of the present invention, the similarity comparison and judgment module specifically includes:

[0049] The corresponding interception unit is used to intercept the corresponding area images of the detection stability area from the detection shooting images;

[0050] The similarity comparison calculation unit is used to perform similarity comparison calculations on the corresponding area images and the standard area images to obtain similarity comparison values;

[0051] The comparison recording unit is used to compare the similarity comparison values with a preset standard threshold and record the comparison results;

[0052] The condition judgment unit is used to judge whether there are similar detection conditions according to the comparison results.

[0053] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0054] In the embodiment of the present invention, by obtaining historical detection data and standard product images, a detection stable region is determined, and the standard region image is intercepted; based on artificial intelligence, detection adjustment is performed to obtain a detection shooting image; the corresponding region image is intercepted, similarity comparison calculation is performed, and it is judged whether there are similar detection conditions; when there are similar detection conditions, defect detection is performed on the detection shooting image, and detection marking is performed. It is possible to determine the detection stable region, intercept the standard region image, during the product detection process, intercept the corresponding region image, perform similarity comparison calculation, and when there are similar detection conditions, perform defect detection and marking on the detection shooting image, so as to realize the verification before defect detection, avoid generating false detection results, effectively improve the accuracy and reliability of industrial defect detection, and ensure the normal production of products. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 Shows a flowchart of an industrial defect detection method based on artificial intelligence provided by an embodiment of the present invention;

[0056] Figure 2 Shows a flowchart of performing detection stability analysis in the method provided by an embodiment of the present invention;

[0057] Figure 3 Shows a flowchart of performing detection adjustment and shooting in the method provided by an embodiment of the present invention;

[0058] Figure 4 Shows a flowchart of judging whether there are similar detection conditions in the method provided by an embodiment of the present invention;

[0059] Figure 5 Shows a flowchart of performing similarity comparison calculation in the method provided by an embodiment of the present invention;

[0060] Figure 6 Shows a flowchart of performing defect detection and marking in the method provided by an embodiment of the present invention;

[0061] Figure 7 Shows an application architecture diagram of an industrial defect detection system based on artificial intelligence provided by an embodiment of the present invention;

[0062] Figure 8 Shows a structural block diagram of a detection stability analysis module in the system provided by an embodiment of the present invention;

[0063] Figure 9 Shows a structural block diagram of a similarity comparison judgment module in the system provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and 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.

[0065] It can be understood that in the prior art, the image detection of industrial defects mainly relies on direct image comparison. However, in special cases such as changes in illumination brightness, illumination occlusion, and changes in the placement position of products, it will cause the misdetection result that a product without defects is detected and recognized as a defective product, resulting in the accuracy and reliability of industrial defect detection not being guaranteed, and thus affecting the normal production of products.

[0066] To solve the above problems, an industrial defect detection method and system based on artificial intelligence disclosed in an embodiment of the present invention, by obtaining the historical detection data and standard product images of the target industrial product, performing detection stability analysis, determining the detection stable area from the standard product images, and intercepting the standard area images; determining the currently detected product, based on artificial intelligence, performing detection adjustment on the currently detected product, and performing detection shooting to obtain the detection shooting images; intercepting the corresponding area images of the detection stable area from the detection shooting images, performing similarity comparison calculation on the corresponding area images and the standard area images to determine whether there are similar detection conditions; when there are similar detection conditions, performing defect detection on the detection shooting images based on the standard product images, and performing detection marking on the currently detected product. It can determine the detection stable area, intercept the standard area images, intercept the corresponding area images during the product detection process, perform similarity comparison calculation, and perform defect detection and marking on the detection shooting images when there are similar detection conditions, so as to realize the verification before defect detection, avoid generating misdetection results, effectively improve the accuracy and reliability of industrial defect detection, and ensure the normal production of products.

[0067] Specifically, Figure 1 The flowchart of the industrial defect detection method based on artificial intelligence provided by an embodiment of the present invention is shown.

[0068] In a preferred embodiment provided by the present invention, an industrial defect detection method based on artificial intelligence, the method specifically includes the following steps:

[0069] Step S101, obtain the historical detection data and standard product images of the target industrial product, perform detection stability analysis, determine the detection stable area from the standard product images, and intercept the standard area images.

[0070] In an embodiment of the present invention, detection planning information is received, and a target industrial product to be subjected to industrial defect detection is determined. By obtaining the internal category code of the target industrial product, data matching is performed in a preset internal database according to the internal category code, and the historical detection data and standard product image of the target industrial product are obtained. Based on the standard product image, the historical detection data is analyzed, and the areas with historical detection anomalies are marked and counted on the standard product image. From the standard product image, an area that has never had a historical detection anomaly or the number of historical detection anomalies is less than a preset anomaly threshold is selected and marked as a detection stable area. Then, in the standard product image, the standard area image of the detection stable area is intercepted.

[0071] It can be understood that the target industrial product is a product category.

[0072] Furthermore, Figure 2 The flowchart of performing detection stability analysis in the method provided by the embodiment of the present invention is shown.

[0073] Specifically, in another preferred embodiment provided by the present invention, the steps of obtaining the historical detection data and standard product image of the target industrial product, performing detection stability analysis, determining the detection stable area from the standard product image, and intercepting the standard area image specifically include the following steps:

[0074] Step S1011: Receive detection planning information and determine the target industrial product.

[0075] Step S1012: Obtain the historical detection data and standard product image of the target industrial product.

[0076] Step S1013: Based on the standard product image, perform detection stability analysis on the historical detection data, and determine the detection stable area from the standard product image.

[0077] Step S1014: In the standard product image, intercept the standard area image of the detection stable area.

[0078] Furthermore, the industrial defect detection method based on artificial intelligence further includes the following steps:

[0079] Step S102: Determine the current detection product, perform detection adjustment on the current detection product based on artificial intelligence, and perform detection shooting to obtain a detection shooting image.

[0080] In an embodiment of the present invention, detection adjustment parameters of a target industrial product are obtained. During the process of industrial defect detection of the target industrial product, the current detected product is determined in real time. Based on artificial intelligence, according to the detection adjustment parameters, the current detected product is clamped, spatially positioned, and / or rotationally oriented, and the current detected product is placed in a preset detection seat, and then the current detected product is detected and photographed to obtain a detection photographing image.

[0081] It can be understood that the current detected product is a specific product entity for industrial defect detection within the product category of the target industrial product.

[0082] Furthermore, Figure 3 The flowchart of detection adjustment and photographing in the method provided by the embodiment of the present invention is shown.

[0083] Specifically, in another preferred embodiment provided by the present invention, the determination of the current detected product, based on artificial intelligence, the detection adjustment of the current detected product, and the detection photographing to obtain a detection photographing image specifically include the following steps:

[0084] Step S1021: Obtain the detection adjustment parameters of the target industrial product.

[0085] Step S1022: Determine the current detected product in real time.

[0086] Step S1023: Based on artificial intelligence, according to the detection adjustment parameters, perform detection adjustment on the current detected product.

[0087] Step S1024: Perform detection photographing to obtain a detection photographing image.

[0088] Furthermore, the industrial defect detection method based on artificial intelligence further includes the following steps:

[0089] Step S103: Intercept the corresponding region image of the detection stable region from the detection photographing image, perform a similarity comparison calculation between the corresponding region image and the standard region image, and determine whether there are similar detection conditions.

[0090] In an embodiment of the present invention, in the detected captured image, the corresponding region image of the detected stable region is intercepted, and both the corresponding region image and the standard region image are grayscaled to generate a corresponding grayscale image and a standard grayscale image. By analyzing the pixel values of the corresponding grayscale image and the standard grayscale image, similarity comparison calculation is performed to obtain a similarity comparison value. Then, the similarity comparison value is compared with a preset standard threshold, and the comparison result is recorded. Furthermore, according to the comparison result, when the similarity comparison value is greater than the standard threshold, it is determined that there are similar detection conditions; while when the similarity comparison value is not greater than the standard threshold, it is determined that there are no similar detection conditions. Specifically, the calculation formula for the similarity comparison value is as follows:

[0091]

[0092] Wherein, N is the similarity comparison value, d represents the corresponding grayscale image, s represents the standard grayscale image, u d is the average brightness corresponding to the corresponding grayscale image, u s is the average brightness corresponding to the standard grayscale image, σ d is the standard deviation corresponding to the corresponding grayscale image, σ s is the standard deviation corresponding to the standard grayscale image, σ ds is the covariance between the corresponding grayscale image and the standard grayscale image, L is the value range of pixel values, k1 is a preset first adjustment coefficient, and k2 is a preset second adjustment coefficient.

[0093] Furthermore, Figure 4 shows a flowchart for determining whether there are similar detection conditions in the method provided by the embodiment of the present invention.

[0094] Specifically, in another preferred embodiment provided by the present invention, the step of intercepting the corresponding region image of the detected stable region from the detected captured image, performing similarity comparison calculation on the corresponding region image and the standard region image, and determining whether there are similar detection conditions specifically includes the following steps:

[0095] Step S1031: Intercept the corresponding region image of the detected stable region from the detected captured image.

[0096] Step S1032: Perform similarity comparison calculation on the corresponding region image and the standard region image to obtain a similarity comparison value.

[0097] Furthermore, Figure 5 shows a flowchart for performing similarity comparison calculation in the method provided by the embodiment of the present invention.

[0098] Specifically, in another preferred embodiment provided by the present invention, the step of performing similarity comparison calculation on the corresponding region image and the standard region image to obtain a similarity comparison value specifically includes the following steps:

[0099] Step S10321: Grayscale the corresponding region image to generate a corresponding grayscale image.

[0100] Step S10322: Grayscale the standard region image to generate a standard grayscale image.

[0101] Step S10323: Perform a similarity comparison calculation on the corresponding grayscale image and the standard grayscale image to obtain a similarity comparison value.

[0102] Furthermore, the step of intercepting the corresponding region image of the detected stable region from the detected captured image, performing a similarity comparison calculation on the corresponding region image and the standard region image, and determining whether there are similar detection conditions further includes the following steps:

[0103] Step S1033: Compare the similarity comparison value with a preset standard threshold and record the comparison result.

[0104] Step S1034: Determine whether there are similar detection conditions according to the comparison result.

[0105] Furthermore, the industrial defect detection method based on artificial intelligence further includes the following steps:

[0106] Step S104: When there are similar detection conditions, perform defect detection on the detected captured image based on the standard product image, and perform a detection mark on the currently detected product.

[0107] In the embodiment of the present invention, when there are similar detection conditions, defect detection is performed on the detected captured image based on the standard product image to obtain a defect detection result, and the detected captured image is recognized to obtain the current product identity of the currently detected product. Furthermore, according to the current product identity and the defect detection result, a detection mark is performed on the currently detected product to achieve background marking of industrial defect detection.

[0108] It can be understood that the current product identity is the internal identity code of the currently detected product.

[0109] Furthermore, Figure 6 shows a flowchart of defect detection and marking in the method provided by the embodiment of the present invention.

[0110] Specifically, in another preferred embodiment provided by the present invention, the step of performing defect detection on the detected captured image based on the standard product image and performing a detection mark on the currently detected product when there are similar detection conditions specifically includes the following steps:

[0111] Step S1041: When the detection conditions are similar, perform defect detection on the detected captured image based on the standard product image to obtain a defect detection result.

[0112] Step S1042: Identify the detected captured image to obtain the current product identity of the currently detected product.

[0113] Step S1043: Perform a detection mark on the currently detected product according to the current product identity and the defect detection result.

[0114] Furthermore, Figure 7 The application architecture diagram of the industrial defect detection system based on artificial intelligence provided by the embodiment of the present invention is shown.

[0115] Specifically, in another preferred embodiment provided by the present invention, an industrial defect detection system based on artificial intelligence includes:

[0116] A detection stability analysis module 101, configured to obtain historical detection data and a standard product image of a target industrial product, perform detection stability analysis, determine a detection stability region from the standard product image, and intercept a standard region image.

[0117] In the embodiment of the present invention, the detection stability analysis module 101 receives detection planning information, determines a target industrial product that needs to perform industrial defect detection, obtains the internal category code of the target industrial product, performs data matching in a preset internal database according to the internal category code, obtains the historical detection data and the standard product image of the target industrial product, analyzes the historical detection data based on the standard product image, marks and counts the regions with historical detection anomalies on the standard product image, selects a region that has never had a historical detection anomaly or the number of historical detection anomalies is less than a preset anomaly threshold from the standard product image, and marks it as a detection stability region, and then intercepts the standard region image of the detection stability region in the standard product image.

[0118] Furthermore, Figure 8 The structural block diagram of the detection stability analysis module 101 in the system provided by the embodiment of the present invention is shown.

[0119] Specifically, in another preferred embodiment provided by the present invention, the detection stability analysis module 101 specifically includes:

[0120] A product determination unit 1011, configured to receive detection planning information and determine a target industrial product.

[0121] A data acquisition unit 1012, configured to obtain the historical detection data and the standard product image of the target industrial product.

[0122] A stability analysis unit 1013, configured to perform a detection stability analysis on the historical detection data based on the standard product image, and determine a detection stable region from the standard product image.

[0123] A standard cropping unit 1014, configured to crop a standard region image of the detection stable region in the standard product image.

[0124] Furthermore, the artificial intelligence-based industrial defect detection system further includes:

[0125] A detection adjustment shooting module 102, configured to determine a currently detected product, perform detection adjustment on the currently detected product based on artificial intelligence, and perform detection shooting to obtain a detection shooting image.

[0126] In an embodiment of the present invention, the detection adjustment shooting module 102 obtains detection adjustment parameters of a target industrial product. During the process of performing industrial defect detection on the target industrial product, the currently detected product is determined in real time. Based on artificial intelligence, the currently detected product is clamped, spatially positioned, and / or rotationally adjusted in orientation according to the detection adjustment parameters, and the currently detected product is placed in a preset detection seat, and then detection shooting is performed on the currently detected product to obtain a detection shooting image.

[0127] A similarity comparison and judgment module 103, configured to crop a corresponding region image of the detection stable region from the detection shooting image, perform a similarity comparison calculation on the corresponding region image and the standard region image, and judge whether there are similar detection conditions.

[0128] In an embodiment of the present invention, the similarity comparison and judgment module 103 crops a corresponding region image of the detection stable region in the detection shooting image, and performs grayscale processing on both the corresponding region image and the standard region image to generate a corresponding grayscale image and a standard grayscale image. Through pixel value analysis of the corresponding grayscale image and the standard grayscale image, a similarity comparison calculation is performed to obtain a similarity comparison value, and then the similarity comparison value is compared with a preset standard threshold, and the comparison result is recorded. Furthermore, according to the comparison result, when the similarity comparison value is greater than the standard threshold, it is determined that there are similar detection conditions; when the similarity comparison value is not greater than the standard threshold, it is determined that there are no similar detection conditions. Specifically, the calculation formula of the similarity comparison value is:

[0129]

[0130] where N is the similarity comparison value, d represents the corresponding grayscale image, s represents the standard grayscale image, u d is the average brightness corresponding to the corresponding grayscale image, u s is the average brightness corresponding to the standard grayscale image, and σ dis the standard deviation corresponding to the grayscale image, σ s is the standard deviation corresponding to the standard grayscale image, σ ds is the covariance between the corresponding grayscale image and the standard grayscale image, L is the value range of pixel values, k1 is a preset first adjustment coefficient, and k2 is a preset second adjustment coefficient.

[0131] Further, Figure 9 shows a structural block diagram of the similarity comparison and judgment module 103 in the system provided by the embodiment of the present invention.

[0132] Specifically, in another preferred embodiment provided by the present invention, the similarity comparison and judgment module 103 specifically includes:

[0133] The corresponding intercepting unit 1031 is used to intercept the corresponding region image of the detected stable region from the detected and captured image.

[0134] The similarity comparison calculation unit 1032 is used to perform similarity comparison calculation on the corresponding region image and the standard region image to obtain a similarity comparison value.

[0135] The comparison recording unit 1033 is used to compare the similarity comparison value with a preset standard threshold and record the comparison result.

[0136] The condition judgment unit 1034 is used to judge whether there are similar detection conditions according to the comparison result.

[0137] Further, the industrial defect detection system based on artificial intelligence further includes:

[0138] The defect detection and marking module 104 is used to perform defect detection on the detected and captured image based on the standard product image and perform detection marking on the current detected product when there are similar detection conditions.

[0139] In the embodiment of the present invention, when there are similar detection conditions, the defect detection and marking module 104 performs defect detection on the detected and captured image based on the standard product image to obtain a defect detection result, and identifies the detected and captured image to obtain the current product identity of the current detected product. Furthermore, according to the current product identity and the defect detection result, the current detected product is detected and marked to realize the background marking of industrial defect detection.

[0140] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order limit for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0141] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0142] The above embodiments only represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

Claims

1. An industrial defect detection method based on artificial intelligence, characterized in that, The method specifically includes the following steps: Obtain the historical detection data and standard product image of the target industrial product, conduct detection stability analysis, determine the detection stable area from the standard product image, and intercept the standard area image, including: receiving detection planning information, determining the target industrial product for which industrial defect detection needs to be performed, obtaining the historical detection data and standard product image of the target industrial product, analyzing the historical detection data based on the standard product image, marking and counting the areas with historical detection anomalies on the standard product image, selecting an area on the standard product image that has never had a historical detection anomaly or the number of historical detection anomalies is less than the preset anomaly threshold, and marking it as the detection stable area, and then intercepting the standard area image of the detection stable area in the standard product image; Determine the current detection product, based on artificial intelligence, perform detection adjustment on the current detection product, and conduct detection shooting to obtain a detection shooting image; Intercept the corresponding area image of the detection stable area from the detection shooting image, perform a similarity comparison calculation on the corresponding area image and the standard area image, and determine whether there are similar detection conditions; When there are similar detection conditions, based on the standard product image, perform defect detection on the detection shooting image and perform detection marking on the current detection product.

2. The industrial defect detection method based on artificial intelligence according to claim 1, wherein, The step of determining the current detection product, based on artificial intelligence, performing detection adjustment on the current detection product, and conducting detection shooting to obtain a detection shooting image specifically includes the following steps: Obtain the detection adjustment parameters of the target industrial product; Determine the current detection product in real time; Based on artificial intelligence, according to the detection adjustment parameters, perform detection adjustment on the current detection product; Conduct detection shooting to obtain a detection shooting image.

3. The industrial defect detection method based on artificial intelligence according to claim 1, wherein The step of intercepting the corresponding area image of the detection stable area from the detection shooting image, performing a similarity comparison calculation on the corresponding area image and the standard area image, and determining whether there are similar detection conditions specifically includes the following steps: Intercept the corresponding area image of the detection stable area from the detection shooting image; Perform a similarity comparison calculation on the corresponding area image and the standard area image to obtain a similarity comparison value; Compare the similarity comparison value with the preset standard threshold and record the comparison result; According to the comparison result, determine whether there are similar detection conditions.

4. The industrial defect detection method based on artificial intelligence according to claim 3, characterized in that, The step of performing a similarity comparison calculation on the corresponding area image and the standard area image to obtain a similarity comparison value specifically includes the following steps: Perform grayscale processing on the corresponding area image to generate a corresponding grayscale image; Perform grayscale processing on the standard area image to generate a standard grayscale image; Perform a similarity comparison calculation on the corresponding grayscale image and the standard grayscale image to obtain a similarity comparison value.

5. The industrial defect detection method based on artificial intelligence according to claim 1, wherein The step of, when there are similar detection conditions, based on the standard product image, performing defect detection on the detection shooting image and performing detection marking on the current detection product specifically includes the following steps: When there are similar detection conditions, based on the standard product image, perform defect detection on the detection shooting image to obtain a defect detection result; Identify the detected captured image to obtain the current product identity of the currently detected product; Based on the current product identity and the defect detection result, perform a detection mark on the currently detected product.

6. An industrial defect detection system based on artificial intelligence, characterized in that, The system includes a detection stability analysis module, a detection adjustment shooting module, a similarity comparison and judgment module, and a defect detection and marking module, where: The detection stability analysis module is used to obtain the historical detection data and standard product image of the target industrial product, perform detection stability analysis, determine the detection stability area from the standard product image, and intercept the standard area image, including: receiving detection planning information, determining the target industrial product that needs to be subjected to industrial defect detection, obtaining the historical detection data and standard product image of the target industrial product, analyzing the historical detection data based on the standard product image, performing area marking and statistics of historical detection anomalies on the standard product image, selecting an area on the standard product image that has never had historical detection anomalies or the number of historical detection anomalies is less than the preset anomaly threshold, and marking it as the detection stability area, and then intercepting the standard area image of the detection stability area in the standard product image; The detection adjustment shooting module is used to determine the currently detected product, perform detection adjustment on the currently detected product based on artificial intelligence, and perform detection shooting to obtain a detected captured image; The similarity comparison and judgment module is used to intercept the corresponding area image of the detection stability area from the detected captured image, perform a similarity comparison calculation on the corresponding area image and the standard area image, and judge whether there are similar detection conditions; The defect detection and marking module is used to, when there are similar detection conditions, perform defect detection on the detected captured image based on the standard product image, and perform a detection mark on the currently detected product.

7. The industrial defect detection system based on artificial intelligence according to claim 6, wherein The detection stability analysis module specifically includes: The product determination unit is used to receive detection planning information and determine the target industrial product; The data acquisition unit is used to obtain the historical detection data and standard product image of the target industrial product; The stability analysis unit is used to perform detection stability analysis on the historical detection data based on the standard product image and determine the detection stability area from the standard product image; The standard interception unit is used to intercept the standard area image of the detection stability area in the standard product image.

8. The industrial defect detection system based on artificial intelligence according to claim 6, characterized in that, The similarity comparison and judgment module specifically includes: The corresponding interception unit is used to intercept the corresponding area image of the detection stability area from the detected captured image; The similarity comparison calculation unit is used to perform a similarity comparison calculation on the corresponding area image and the standard area image to obtain a similarity comparison value; The comparison recording unit is used to compare the similarity comparison value with a preset standard threshold and record the comparison result; The condition judgment unit is used to judge whether there are similar detection conditions according to the comparison result.

Images