Defect detection method, electronic device and storage device eliminating reflection interference

Abstract

The present application is about a defect detection method that eliminates reflective interference. The method includes: obtaining a surface reflective image of a surface reflective device to be tested; determining a first reflective area image based on the surface reflective image, wherein the first reflective area image includes an interfering reflective area and a target reflective area of ​​a target detection object; eliminating the interfering reflective area based on the shape characteristics and spatial characteristics of the target detection object to obtain the target object reflective area; determining whether the target detection object has defects based on the target object reflective area, and the defects include damage defects and missing defects. The solution provided by the present application can eliminate the surface reflective interference of the surface reflective device, improve the detection efficiency and detection accuracy of the surface reflective device, and improve product quality.

Description

Technical Field

[0001] The present application relates to the field of visual inspection technology, and in particular to a defect inspection method, electronic device and storage device that eliminates reflection interference. Background Art

[0002] When visually inspecting some equipment made of reflective materials such as metal, the material of the target inspection object in the equipment is often also reflective. Therefore, it is difficult to implement visual inspection in this case, and manual inspection is required, which is not only inefficient but also has low accuracy and high workload for inspectors. For example, in the inspection process of pipe bending equipment, since the pipe bending equipment and the core rod used for bending operations in the pipe bending equipment are made of metal, they are all reflective under the light source of visual inspection, making it difficult to distinguish. The core head set at one end of the core rod is prone to deformation, breakage and other damage defects after long-term use for pipe bending. Using a damaged core head will cause the bent pipe product to deform, and the core head that falls off due to breaking may fall into the bent pipe product, causing serious product quality problems. Therefore, it is necessary to frequently inspect the defects of the core head, but the lack of efficient inspection methods to replace manual inspection is the biggest difficulty.

[0003] In the prior art, in the patent (core head detection device) with publication number CN210907546U, the difference between the material of the bending tube and the material of the core head is utilized, and a suction mechanism is provided to attract the core head that falls into the bending tube, so that the core head drives the bending tube to move, so that the sensing mechanism can sense the movement of the bending tube, and then determine that the core head of the bending device has fallen.

[0004] The above prior art has the following disadvantages:

[0005] This solution requires that the material of the bending tube and the material of the core head are different in order to complete the inspection. When the material properties of the bending tube and the core head are similar, it is difficult to achieve the inspection effect, and the reflection interference cannot be eliminated. Therefore, it is necessary to develop a visual inspection method that can exclude the interfering reflection area and retain the reflection area of ​​the target inspection object to perform defect detection on the target inspection object. Summary of the invention

[0006] In order to overcome the problems existing in the related art, the present application provides a defect detection method that eliminates reflective interference. The defect detection method that eliminates reflective interference can eliminate the surface reflective interference of the surface reflective equipment, improve the detection efficiency and detection accuracy of the surface reflective equipment, and improve product quality.

[0007] The first aspect of the present application provides a defect detection method for eliminating reflection interference, comprising:

[0008] Acquire a surface reflective image of the surface reflective device to be tested;

[0009] Determine a first reflective region image according to the surface reflective image, wherein the first reflective region image includes an interfering reflective region and a target object reflective region of the target detection object;

[0010] Eliminate the interfering reflective area according to the shape characteristics and spatial characteristics of the target detection object to obtain the reflective area of ​​the target object;

[0011] Determine whether the target object has defects based on the reflective area of ​​the target object. Defects include damage defects and missing defects.

[0012] In one embodiment, the shape feature includes a roundness feature and an angle feature; the spatial feature includes a length feature and an area feature;

[0013] The interfering reflective area includes a first reflective interference area and a second reflective interference area, the first reflective interference area is an area with an irregular reflective shape, and the second reflective interference area is an area whose reflective shape matches one of the shape feature and the spatial feature compared with the target detection object;

[0014] The target detection object includes a pipe bending core head of a pipe bending device, and the pipe bending core head is connected to one end of a pipe bending core rod of the pipe bending device.

[0015] In one embodiment, the interfering reflective area is eliminated according to the shape characteristics and spatial characteristics of the target detection object to obtain the reflective area of ​​the target object, including:

[0016] Determine a first reflective interference area according to the first reflective area image;

[0017] Excluding the first reflective interference area from the first reflective area image to obtain a second reflective area image;

[0018] Determining a target search area in the second reflective area image according to a preset activity range of the target detection object;

[0019] Perform image enhancement processing on the target search area to obtain a target detection image;

[0020] The second reflection interference area is eliminated according to the target detection image, shape characteristics and spatial characteristics to obtain the target object reflection area.

[0021] In one embodiment, determining the first reflective interference area according to the first reflective area image includes:

[0022] The first reflection interference area is determined in the first reflection area image by using a particle analysis algorithm.

[0023] In one embodiment, excluding the first reflective interference area from the first reflective area image includes:

[0024] The first reflection interference area is excluded from the first reflection area image by using the area difference operation.

[0025] In one implementation, performing image enhancement processing on the target search area includes:

[0026] Perform contrast enhancement on the target search area.

[0027] In one embodiment, excluding the second reflection interference area according to the target detection image, shape characteristics and spatial characteristics includes:

[0028] The target detection image is subjected to threshold segmentation processing, and the reflective area of ​​the target object is determined according to the shape characteristics and spatial characteristics through the particle analysis algorithm, and the second reflective interference area is excluded.

[0029] In one embodiment, the reflective area of ​​the target object is determined according to shape characteristics and spatial characteristics by using a particle analysis algorithm, including:

[0030] When the target object is a curved pipe core, the shape feature is the roundness feature, and the spatial feature is the area feature;

[0031] If the area feature of the reflective area to be measured in the target detection image is greater than the area of ​​P pixels, and the roundness feature of the reflective area to be measured is greater than K and less than M, then the reflective area to be measured is determined to be the reflective area of ​​the target object; P is a positive integer, K and M are greater than zero and less than or equal to 1.

[0032] In one embodiment, determining whether the target object has defects according to the reflective area of ​​the target object includes:

[0033] When the target object is a curved tube core head, if the number of reflective areas of the target object is an odd number, it is determined that the curved tube core head has a missing defect, and a warning message is sent;

[0034] If the number of reflective areas of the target object is an even number, the edge point set of the reflective area of ​​the target object is obtained by a straight line extraction algorithm, and the eccentric distance between each point in the edge point set and the center point of the reflective area of ​​the target object is determined;

[0035] If the difference in eccentricity distances between any adjacent points in the edge point set is greater than a preset difference, it is determined that the elbow core head has a damage defect and a warning message is sent.

[0036] In one embodiment, determining the first reflective area image according to the surface reflective image includes:

[0037] The surface reflection image is subjected to threshold segmentation processing to obtain a first reflection area image.

[0038] A second aspect of the present application provides an electronic device, including:

[0039] Processor; and

[0040] The memory stores executable codes thereon, and when the executable codes are executed by the processor, the processor is caused to execute the method as described above.

[0041] A third aspect of the present application provides a non-transitory machine-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as described above.

[0042] The technical solution provided by this application may have the following beneficial effects:

[0043] By acquiring a surface reflective image of a surface reflective device to be tested, a first reflective area image is determined in the surface reflective image, wherein the first reflective area image includes an interfering reflective area and a target object reflective area of ​​the target detection object, and according to shape characteristics and spatial characteristics of the target detection object, the interfering reflective area that does not conform to the shape characteristics and the spatial characteristics is excluded, thereby obtaining the target object reflective area, and determining whether the target detection object has a damage defect or a missing defect according to the target object reflective area, thereby improving the detection efficiency and detection accuracy of the surface reflective device to be tested, avoiding missed detection or wrong detection due to fatigue of detection personnel performing manual detection for a long time, and improving production quality.

[0044] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and other objects, features and advantages of the present application will become more apparent through a more detailed description of exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0046] Figure 1 It is a flow chart of a first embodiment of a defect detection method for eliminating reflection interference shown in an embodiment of the present application;

[0047] Figure 2 It is a flow chart of a second embodiment of a defect detection method for eliminating reflection interference shown in an embodiment of the present application;

[0048] Figure 3 1 is a flow chart of a third embodiment of a defect detection method for eliminating reflection interference shown in an embodiment of the present application;

[0049] Figure 4 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION

[0050] The preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0051] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0052] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0053] Embodiment 1

[0054] When performing visual inspection on some equipment made of reflective materials such as metal, the material of the target inspection object in the equipment is often also reflective. Therefore, it is difficult to implement visual inspection in this case, and manual inspection is required, which is not only inefficient but also has low accuracy and high workload for inspectors. The existing technology requires that the material of the bending tube and the material of the core head be different in order to complete the inspection. When the material properties of the bending tube and the core head are similar, it is difficult to achieve the inspection effect, and the reflective interference cannot be eliminated. Therefore, it is necessary to develop a visual inspection method that can exclude interfering reflective areas and retain the reflective area of ​​the target inspection object to perform defect detection on the target inspection object.

[0055] In response to the above problems, an embodiment of the present application provides a defect detection method that eliminates reflective interference, which can eliminate the surface reflective interference of surface reflective equipment, improve the detection efficiency and detection accuracy of surface reflective equipment, and improve product quality.

[0056] The technical solution of the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0057] See also Figure 1 , the first embodiment of the defect detection method for eliminating reflection interference shown in the embodiment of the present application includes:

[0058] 101. Acquire a surface reflective image of a surface reflective device to be tested;

[0059] The reflective device of the surface to be measured includes but is not limited to a device made of metal or glass and a device coated or pasted with a reflective material on the surface, and the reflective material can be a reflective film or a reflective paint. It is understood that when the surface of the reflective device of the surface to be measured is irradiated by incident light, it can reflect most or even all of the incident light.

[0060] In the embodiment of the present application, an industrial camera can be used to image the preset shooting position of the surface reflective device to be tested under the illumination of a strip light source to obtain the surface reflective image. The strip light source can be mainly illuminated at the position of the target detection object. It is understandable that there are various ways to obtain the surface reflective image of the surface reflective device to be tested. In actual applications, the method for obtaining the surface reflective image needs to be determined according to the actual application situation, and it is not limited here.

[0061] 102. Determine a first reflective area image according to the surface reflective image;

[0062] In an embodiment of the present application, the first reflective area image can be extracted or segmented from the acquired surface reflective image. Under the illumination of the incident light, the non-target detection object and the target detection object will also form reflections. Therefore, the first reflective area image includes an interfering reflective area and a target object reflective area of ​​the target detection object, wherein the interfering reflective area is the area formed by the reflection of the non-target detection object, which can be understood as an invalid detection area and needs to be excluded.

[0063] 103. Eliminate interfering reflective areas based on the shape characteristics and spatial characteristics of the target detection object;

[0064] The target detection object has shape characteristics and spatial characteristics that are inconsistent with the non-target detection object. Therefore, by identifying the shape characteristics and spatial characteristics that are inconsistent between the target detection object and the non-target detection object, the interfering reflective area, that is, the reflective area generated by the non-target detection object, can be excluded, and the target object reflective area, that is, the reflective area generated by the target detection object, can be retained.

[0065] 104. Determine whether the target object has defects based on the reflective area of ​​the target object.

[0066] Based on the retained reflective area of ​​the target object, it is judged and detected whether the target object has defects. In the embodiment of the present application, the defects include but are not limited to damage defects and missing defects. Damage defects refer to damage to the target object, and missing defects refer to the missing of the target object.

[0067] From the above embodiment 1, the following beneficial effects can be seen:

[0068] By acquiring a surface reflective image of a surface reflective device to be tested, a first reflective area image is determined in the surface reflective image, wherein the first reflective area image includes an interfering reflective area and a target object reflective area of ​​the target detection object, and according to shape characteristics and spatial characteristics of the target detection object, the interfering reflective area that does not conform to the shape characteristics and the spatial characteristics is excluded, thereby obtaining the target object reflective area, and determining whether the target detection object has a damage defect or a missing defect according to the target object reflective area, thereby improving the detection efficiency and detection accuracy of the surface reflective device to be tested, avoiding missed detection or wrong detection due to fatigue of detection personnel performing manual detection for a long time, and improving production quality.

[0069] Embodiment 2

[0070] For ease of understanding, an embodiment of a defect detection method for eliminating reflective interference is provided below for illustration. In actual applications, in the step of eliminating interfering reflective areas based on the shape characteristics and spatial characteristics of the target detection object, a particle analysis algorithm and regional difference operations are used to eliminate interfering reflective areas to improve the accuracy of defect detection.

[0071] See also Figure 2 , the second embodiment of the defect detection method for eliminating reflection interference shown in the embodiment of the present application includes:

[0072] 201. Determine a first light-reflecting interference area according to a first light-reflecting area image;

[0073] In the embodiments of the present application, shape features include but are not limited to roundness features and angle features; spatial features include but are not limited to length features and area features.

[0074] The interfering reflective area includes a first reflective interference area and a second reflective interference area. The first reflective interference area is an area with an irregular reflective shape. It can be understood that the area with an irregular reflective shape is an area formed by the reflection of the device surface around the target detection object. Whether in terms of shape characteristics or spatial characteristics, there is a large gap between the shape characteristics and spatial characteristics of the target detection object. The second reflective interference area is an area whose reflective shape matches one of the shape characteristics and spatial characteristics of the target detection object. It can be understood that the second reflective interference area is a reflective area that is similar to the target detection object reflective area.

[0075] Therefore, in an embodiment of the present application, the reflective area of ​​the target object can be determined by first excluding the first reflective interference area and then excluding the second reflective interference area, so as to improve the accuracy of defect detection, while reducing computing costs and improving computing efficiency.

[0076] In the embodiment of the present application, the first reflective interference area is determined in the first reflective area image by a particle analysis algorithm, wherein the particle analysis algorithm refers to a particle swarm algorithm, the full name of which is a particle swarm optimization algorithm, which is an algorithm mainly used to solve optimization problems, and its basic principle is to generate a group of random particles and find the optimal solution through multiple iterations. The algorithm principle of the particle swarm algorithm is as follows:

[0077] Step 1: Initialize the particle swarm. There are n particles in the particle swarm. Give each particle a random initial position and velocity.

[0078] Step 2: Calculate the fitness value of each particle according to the fitness function;

[0079] Step 3: For each particle, compare the fitness value of its current position with the fitness value corresponding to its best historical position. If the fitness value of the current position is higher, use the current position to update the best historical position.

[0080] Step 4: For each particle, compare the fitness value of its current position with the fitness value corresponding to its global best position. If the fitness value of the current position is higher, use the current position to update the global best position.

[0081] Step 5: Update the speed and position of each particle according to the speed update formula and the position update formula. For example, the speed update formula can be expressed as follows:

[0082]

[0083] in, is the d-th dimension component of the velocity vector of particle i at the k-th iteration, is the d-th dimension component of the position vector of particle i in the k-1th iteration, c1 and c2 represent acceleration constants, which are used to adjust the maximum learning step size, r1 and r2 represent two random parameters, and their value range is [0,1] to increase the randomness of the search, w represents the inertia weight, and its value is a non-negative number, which is used to adjust the search range of the solution space, and pbest id refers to the d-th dimension component of the best position ever experienced by particle i, gbest d It refers to the d-th dimension component of the best position experienced by all particles;

[0084] The position update formula can be expressed as follows:

[0085]

[0086] Step six, determine whether the end condition is met. If the end condition is not met, return to step two. If the end condition is met, the algorithm ends and the global best position is the global optimal solution.

[0087] In the embodiment of the present application, the location of the first light reflection interference area is found through the particle analysis algorithm, so that the first light reflection interference area can be excluded.

[0088] 202. Exclude the first light-reflecting interference area from the first light-reflecting area image;

[0089] The first reflective interference area is excluded from the first reflective area image by using a regional difference operation to obtain a second reflective area image. In the embodiment of the present application, the regional difference operation refers to subtracting all pixel points of the first reflective area image from the pixel points in the first reflective interference area, so that the first reflective interference area can be excluded from the first reflective area image.

[0090] 203. Determine a target search area in the second reflective area image according to a preset activity range of the target detection object;

[0091] In an embodiment of the present application, an activity range of a target detection object is preset, and the preset activity range refers to the activity range of the target detection object during the operation of the reflective device on the surface to be detected. By recording a large number of activity ranges of the target detection object each time it operates, a trajectory set graph of all activity trajectories of the target detection object is obtained, and the minimum bounding rectangle of the trajectory set graph can be used as the preset activity range. Since detection is performed simultaneously during the operation process, the minimum bounding rectangle is matched with the position of the predicted activity range of the target detection object in the second reflective area image, so the minimum bounding rectangle can be established in the second reflective area image as the target search area. Determining the target search area in the second reflective area image according to the preset activity range is conducive to saving the search time of the reflective area of ​​the target object and improving the operation efficiency.

[0092] It is understandable that there are various ways to obtain the preset activity range. The above use of the minimum circumscribed rectangle of the trajectory set graphic as the preset activity range is only exemplary. In actual applications, the preset activity range needs to be determined according to the actual application situation, and is not limited here.

[0093] 204. Perform image enhancement processing on the target search area;

[0094] Image enhancement processing includes but is not limited to contrast enhancement, hue enhancement, saturation enhancement, and brightness enhancement. In an embodiment of the present application, contrast enhancement is performed on the target search area to obtain a target detection image.

[0095] 205. Eliminate the second reflection interference area according to the target detection image, shape features, and spatial features to obtain the target object reflection area.

[0096] The target detection image is subjected to threshold segmentation processing, and the pixels that do not meet the grayscale threshold after contrast enhancement are excluded, so that the target detection image has fewer impurities and the detection accuracy is improved. The particle analysis algorithm is used to determine the reflective area of ​​the target object based on the shape characteristics and spatial characteristics, thereby excluding the second reflective interference area.

[0097] From the above-mentioned embodiment 2, the following beneficial effects can be seen:

[0098] The reflective area of ​​the target object is determined by first excluding the first reflective interference area and then excluding the second reflective interference area, so as to improve the accuracy of defect detection, reduce computing costs and improve computing efficiency.

[0099] Embodiment 3

[0100] For ease of understanding, an embodiment of a defect detection method for eliminating reflection interference is provided below for illustration. In practical applications, the target detection object may be a bending core head of a bending equipment. Visual inspection of defects in the bending core head can improve detection efficiency and accuracy, and prevent defects in the bending core head from affecting the production quality of the bent pipes.

[0101] See also Figure 3 , the third embodiment of the defect detection method for eliminating reflection interference shown in the embodiment of the present application includes:

[0102] 301. Obtain a surface reflective image of the reflective device to be tested under the illumination of a strip light source by using an industrial camera;

[0103] The target detection object includes but is not limited to a pipe bending core head of a pipe bending device, and the pipe bending core head is connected to one end of a pipe bending core rod of the pipe bending device.

[0104] When the target detection object is a bending tube core head, the corresponding surface reflective device to be tested is a bending tube device. The entire body of the bending tube device is made of metal. During the production process, the bending tube core rod will penetrate the metal tube that needs to be bent, such as the copper tube in the heat exchange device of the air conditioner. The bending tube core rod extends the bending tube core head, and the metal tube is bent along the bending tube core head. Therefore, when the strip light source is irradiated, the bending tube core head, the end of one end of the bending tube core rod connected to the bending tube core head, and the surface of the bending tube device around the bending tube core head will all produce reflections. The surface of the bending tube device where the bending tube core head is located is imaged by an industrial camera to obtain the surface reflective image.

[0105] 302. Determine a first reflective area image according to the surface reflective image;

[0106] The surface reflection image is subjected to threshold segmentation processing to exclude the area without reflection, thereby obtaining a first reflection area image.

[0107] 303. Eliminate interfering reflective areas according to the shape characteristics and spatial characteristics of the elbow core head;

[0108] When the target detection object is a bending tube core head, the shape characteristics of the bending tube core head that are inconsistent with the surface of the bending tube equipment around the bending tube core head are roundness characteristics, spatial characteristics and area characteristics.

[0109] The first reflective interference area is determined according to the first reflective area image, and the first reflective interference area is excluded from the first reflective area image. According to the preset activity range of the target detection object, the target search area is determined in the second reflective area image, and the target search area is image enhanced to obtain a target detection image. If the area feature of the reflective area to be measured in the target detection image is greater than the area of ​​P pixels, and the roundness feature of the reflective area to be measured is greater than K and less than M, then the reflective area to be measured is determined to be the reflective area of ​​the target object.

[0110] In the embodiment of the present application, P is a positive integer. Preferably, the value of P can be any value between 195-205. The steps for determining the roundness feature are as follows: first, find the center of the minimum circumscribed circle of the reflective area to be measured, then find the edge point of the reflective area to be measured, calculate the distance from the edge point to the center of the circle, and divide the minimum distance obtained by the maximum distance to obtain the roundness feature. K and M are greater than zero and less than or equal to 1. Preferably, the value of K can be 0.7, and the value of M can be 1. It can be understood that the values ​​of P, K and M need to be determined according to the actual application situation, and are not limited here.

[0111] 304. Determine whether the target object has defects based on the reflective area of ​​the target object.

[0112] When the target detection object is a bent tube core head, when the bent tube core head is not damaged, the bent tube core head and the end of one end of the bent tube core rod connected to the bent tube core head have matching shape characteristics and spatial characteristics under the condition of reflection. Therefore, when the bent tube core head is not damaged, the two should appear in pairs in the reflective area of ​​the target object, that is, the reflective area of ​​the target object includes the reflective area of ​​the bent tube core head and the reflective area of ​​the end of one end of the bent tube core rod connected to the bent tube core head.

[0113] That is, if the number of reflective areas of the target object is an odd number, it can be determined that there is a missing defect in the bent tube core head, and a warning message is sent;

[0114] If the number of reflective areas of the target object is an even number, it means that the bend tube core head is still connected to the bend tube core rod and is not missing. The edge point set of the reflective area of ​​the target object is obtained through the straight line extraction algorithm, and the eccentric distance between each point in the edge point set and the center point of the reflective area of ​​the target object is determined to determine whether the bend tube core head has a damage defect.

[0115] If the difference in eccentric distances between any adjacent points in the edge point set is greater than the preset difference, it means that the edge of one of the reflective areas in the target object's reflective area is not smooth. Since the end of the bending core rod connected to the bending core head will not suffer significant wear during the production process, it is mainly the bending core head that suffers wear. In this case, it is determined that the bending core head has a damage defect and a warning message is sent.

[0116] From the above embodiment 3, the following beneficial effects can be seen:

[0117] When the target inspection object is the bending core head of the bending equipment, visual inspection of the defects of the bending core head can improve the inspection efficiency and accuracy, avoid missed inspections or wrong inspections due to fatigue of the inspectors during long-term manual inspections, and prevent the defects of the bending core head from affecting the production quality of the bent pipes.

[0118] Embodiment 4

[0119] Corresponding to the aforementioned application function implementation method embodiment, the present application also provides an electronic device and corresponding embodiments.

[0120] Figure 4 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application.

[0121] See also Figure 4 , the electronic device 1000 includes a memory 1010 and a processor 1020 .

[0122] The processor 1020 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0123] The memory 1010 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, ROM can store static data or instructions required by the processor 1020 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at run time. In addition, the memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 1010 may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (such as a DVD-ROM, a double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (such as an SD card, a mini SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. The computer-readable storage medium does not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0124] The memory 1010 stores executable codes, and when the executable codes are processed by the processor 1020 , the processor 1020 can execute part or all of the methods described above.

[0125] The scheme of the present application has been described in detail above with reference to the accompanying drawings. In the above embodiments, the description of each embodiment has its own emphasis. For the part that is not described in detail in a certain embodiment, refer to the relevant description of other embodiments. Those skilled in the art should also know that the actions and modules involved in the description are not necessarily required for the present application. In addition, it can be understood that the steps in the method of the embodiment of the present application can be adjusted in order, merged and deleted according to actual needs, and the modules in the device of the embodiment of the present application can be merged, divided and deleted according to actual needs.

[0126] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0127] Alternatively, the present application can also be implemented as a non-temporary machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) on which executable code (or computer program, or computer instruction code) is stored. When the executable code (or computer program, or computer instruction code) is executed by a processor of an electronic device (or electronic device, server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0128] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the application herein may be implemented as electronic hardware, computer software, or combinations of both.

[0129] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system and method according to multiple embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a part of a module, a program segment or a code, and the part of the module, the program segment or the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or the flow chart, and the combination of the square boxes in the block diagram and / or the flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0130] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A defect detection method eliminating reflection interference, characterized in that: include: Acquire a surface reflective image of the surface reflective device to be tested; Determine a first reflective region image according to the surface reflective image, wherein the first reflective region image includes an interfering reflective region and a target object reflective region of the target detection object; Eliminate the interfering reflective area according to the shape characteristics and spatial characteristics of the target detection object to obtain the reflective area of ​​the target object; Determine whether the target object has defects according to the reflective area of ​​the target object, wherein the defects include damage defects and missing defects. The shape features include roundness features and angle features; the space features include length features and area features; The interfering light-reflecting area includes a first light-reflecting interfering area and a second light-reflecting interfering area, wherein the first light-reflecting interfering area is an area with an irregular light-reflecting shape, and the second light-reflecting interfering area is an area whose light-reflecting shape matches one of the shape feature and the space feature compared with the target detection object; The target detection object includes a pipe bending core head of a pipe bending device, and the pipe bending core head is connected to one end of a pipe bending core rod of the pipe bending device.

2. The defect detection method for eliminating reflection interference according to claim 1, characterized in that: The step of eliminating the interfering reflective area according to the shape characteristics and spatial characteristics of the target detection object to obtain the reflective area of ​​the target object includes: determining the first reflective interference area according to the first reflective area image; Excluding the first reflective interference area from the first reflective area image to obtain a second reflective area image; Determining a target search area in the second reflective area image according to a preset activity range of the target detection object; Performing image enhancement processing on the target search area to obtain a target detection image; The second reflective interference area is eliminated according to the target detection image, the shape feature and the spatial feature to obtain the target object reflective area.

3. The defect detection method for eliminating reflection interference according to claim 2, characterized in that: The determining the first reflective interference area according to the first reflective area image includes: The first reflective interference area is determined in the first reflective area image by using a particle analysis algorithm.

4. The defect detection method for eliminating reflection interference according to claim 2, characterized in that: The step of excluding the first reflective interference area from the first reflective area image comprises: The first reflective interference area is excluded from the first reflective area image by performing an area difference operation.

5. The defect detection method for eliminating reflection interference according to claim 2, characterized in that: The performing image enhancement processing on the target search area includes: Contrast enhancement is performed on the target search area.

6. The defect detection method for eliminating reflection interference according to claim 3, characterized in that: The step of eliminating the second reflective interference area according to the target detection image, the shape feature, and the spatial feature includes: The target detection image is subjected to threshold segmentation processing, and the reflective area of ​​the target object is determined according to the shape feature and the spatial feature through the particle analysis algorithm, and the second reflective interference area is excluded.

7. The defect detection method for eliminating reflection interference according to claim 6, characterized in that: The determining the reflective area of ​​the target object according to the shape feature and the spatial feature by the particle analysis algorithm includes: When the target detection object is the curved pipe core head, the shape feature is the roundness feature, and the space feature is the area feature; If the area feature of the reflective area to be measured in the target detection image is greater than the area of ​​P pixels, and the roundness feature of the reflective area to be measured is greater than K and less than M, then the reflective area to be measured is determined to be the reflective area of ​​the target object; P is a positive integer, and K and M are greater than zero and less than or equal to 1.

8. The defect detection method for eliminating reflection interference according to claim 1, characterized in that: The determining whether the target object has a defect according to the reflective area of ​​the target object includes: When the target detection object is the bent tube core head, if the number of the reflective areas of the target object is an odd number, it is determined that the bent tube core head has the missing defect, and a warning message is sent; If the number of the reflective regions of the target object is an even number, an edge point set of the reflective region of the target object is obtained by a straight line extraction algorithm, and an eccentric distance between each point in the edge point set and the center point of the reflective region of the target object is determined; If the difference in eccentricity distances between any adjacent points in the edge point set is greater than a preset difference, it is determined that the elbow core head has the damage defect and the warning message is sent.

9. The defect detection method for eliminating reflection interference according to claim 6, characterized in that: The determining of the first reflective area image according to the surface reflective image comprises: The threshold segmentation process is performed on the surface reflection image to obtain the first reflection area image.

10. An electronic device, characterized in that: include: processor; as well as A memory having executable codes stored thereon, which, when executed by the processor, causes the processor to execute the method according to any one of claims 1 to 9.

11. A non-transitory machine-readable storage medium having executable codes stored thereon, which, when executed by a processor of an electronic device, causes the processor to execute the method according to any one of claims 1 to 9.

Images