CN114331954A - Defect detection method for eliminating reflection interference, electronic equipment and storage equipment - Google Patents
Defect detection method for eliminating reflection interference, electronic equipment and storage equipment Download PDFInfo
- Publication number
- CN114331954A CN114331954A CN202111334149.XA CN202111334149A CN114331954A CN 114331954 A CN114331954 A CN 114331954A CN 202111334149 A CN202111334149 A CN 202111334149A CN 114331954 A CN114331954 A CN 114331954A
- Authority
- CN
- China
- Prior art keywords
- area
- reflection
- interference
- image
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application relates to a defect detection method for eliminating reflection interference. The method comprises the following steps: acquiring a surface reflection image of surface reflection equipment to be detected; determining a first light reflection area image according to the surface light reflection image, wherein the first light reflection area image comprises an interference light reflection area and a target object light reflection area of a target detection object; excluding the interference light reflecting region according to the shape characteristic and the space characteristic of the target detection object to obtain a target object light reflecting region; and determining whether the target detection object has defects according to the light reflecting area of the target object, wherein the defects comprise damage defects and deletion defects. The scheme that this application provided can eliminate the surperficial reflection of light interference of surface reflection of light equipment, improves the detection efficiency and the detection accuracy degree of surface reflection of light equipment, promotes product quality.
Description
Technical Field
The present application relates to the field of vision inspection technologies, and in particular, to a defect detection method for eliminating reflection interference, an electronic device, and a storage device.
Background
When some equipment made of reflective materials such as metal is subjected to visual detection, the material of a target detection object in the equipment is often the reflective material, so that the visual detection is difficult to implement under the condition, manual detection is needed, the efficiency is low, the accuracy is low, and the working strength of detection personnel is high. For example, in the detection process of the pipe bending device, because the pipe bending device and the core rod for bending operation in the pipe bending device are all made of metal materials, and both of them are in a light-reflecting state under the irradiation of a light source for visual detection, and are difficult to distinguish, and the core head arranged at one end of the core rod is easy to deform, break and other damage defects after being used for pipe bending molding for a long time, the bent pipe product is deformed due to the use of the damaged core head, and the core head falling off due to the break may also fall into the bent pipe product, resulting in serious product quality problems, so that the defect condition of the core head needs to be frequently detected, but the defect condition of the core head needs to be frequently detected without an efficient detection method to replace manual detection, which is the biggest difficulty.
In the prior art, in a patent (core print detection device) with publication number CN210907546U, a suction mechanism is provided to suck a core print dropped into a bending tube by using different materials of the bending tube and the core print, so that the core print drives the bending tube to move, a sensing mechanism can sense the movement of the bending tube, and the core print of the bending tube device is determined to have dropped.
The above prior art has the following disadvantages:
this scheme need restrict the material of the pipe of bending and the material difference of core and just can accomplish the detection, is difficult to reach the detection effect promptly when the material of the pipe of bending and the material property of core are similar, can not eliminate reflection of light interference moreover. Therefore, it is necessary to develop a visual inspection method capable of excluding the interfering light-reflecting region and retaining the light-reflecting region of the target object to detect the defect of the target object.
Disclosure of Invention
In order to solve the problems in the related art, the application provides a defect detection method for eliminating reflection interference, and the defect detection method for eliminating reflection interference can eliminate the reflection interference on the surface of surface reflection equipment, improve the detection efficiency and the detection accuracy of the surface reflection equipment, and improve the product quality.
The first aspect of the present application provides a defect detection method for eliminating reflection interference, including:
acquiring a surface reflection image of surface reflection equipment to be detected;
determining a first light reflection area image according to the surface light reflection image, wherein the first light reflection area image comprises an interference light reflection area and a target object light reflection area of a target detection object;
excluding the interference light reflecting region according to the shape characteristic and the space characteristic of the target detection object to obtain a target object light reflecting region;
and determining whether the target detection object has defects according to the light reflecting area of the target object, wherein the defects comprise damage defects and deletion defects.
In one embodiment, the shape features include roundness features and angular features; the spatial features comprise length features and area features;
the interference reflection region comprises a first reflection interference region and a second reflection interference region, the first reflection interference region is a region with an irregular reflection shape, and the second reflection interference region is a region with a reflection shape matched with one of shape characteristics and space characteristics compared with a target detection object;
the target detection object comprises a bent pipe core head of the bent pipe equipment, and the bent pipe core head is connected to one end of a bent pipe core rod of the bent pipe equipment.
In one embodiment, the method for obtaining the target object light-reflecting region by excluding the interfering light-reflecting region according to the shape feature and the spatial feature of the target detection object includes:
determining a first reflection interference area according to the first reflection area image;
removing the first reflection interference area from the first reflection area image to obtain a second reflection area image;
determining a target search area in the second light reflecting area image according to the preset moving range of the target detection object;
carrying out image enhancement processing on the target search area to obtain a target detection image;
and eliminating the second light reflection interference area according to the target detection image, the shape characteristic and the space characteristic to obtain a target object light reflection area.
In one embodiment, determining a first retroreflective jam area from the first retroreflective area image includes:
a first retroreflective interference area is determined in the first retroreflective area image by a particle analysis algorithm.
In one embodiment, excluding the first retroreflective jam-zone from the first retroreflective zone image comprises:
and excluding the first reflection interference region from the first reflection region image through region difference set operation.
In one embodiment, the image enhancement processing of the target search area includes:
and carrying out contrast enhancement on the target search area.
In one embodiment, excluding the second reflective interference region according to the target detection image, the shape feature, and the spatial feature includes:
and performing threshold segmentation processing on the target detection image, determining a target object light reflection region according to the shape characteristics and the space characteristics through a particle analysis algorithm, and excluding a second light reflection interference region.
In one embodiment, the determining the target object light reflection region according to the shape feature and the spatial feature by a particle analysis algorithm includes:
when the target detection object is the bent pipe core print, the shape characteristic is a roundness characteristic, and the space characteristic is an area characteristic;
if the area characteristic of the to-be-detected light reflecting region in the target detection image is larger than the areas of the P pixel points and the roundness characteristic of the to-be-detected light reflecting region is larger than K and smaller than M, determining the to-be-detected light reflecting region as a target object light reflecting region; p is a positive integer, K and M are greater than zero and less than or equal to 1.
In one embodiment, determining whether the target detection object has a defect according to the target object reflection area comprises:
when the target detection object is the bent core print, if the number of the light reflecting areas of the target object is odd, determining that the bent core print has a missing defect, and sending warning information;
if the number of the target object light reflecting areas is an even number, acquiring an edge point set of the target object light reflecting areas through a straight line extraction algorithm, and determining the eccentric distance between each point and the central point of the target object light reflecting areas in the edge point set;
and if the difference of the eccentric distances of any adjacent points in the edge point set is larger than the preset difference, determining that the bent pipe core print has a damage defect, and sending warning information.
In one embodiment, determining a first retroreflective region image from the surface retroreflective image includes:
and performing threshold segmentation processing on the surface reflection image to obtain a first reflection area image.
A second aspect of the present application provides an electronic device, comprising:
a processor; and
a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method as described above.
A third aspect of the application provides a non-transitory machine-readable storage medium having stored thereon executable code which, when executed by a processor of an electronic device, causes the processor to perform a method as described above.
The technical scheme provided by the application can comprise the following beneficial effects:
the method comprises the steps of obtaining a surface reflection image of surface reflection equipment to be detected, determining a first reflection area image in the surface reflection image, wherein the first reflection area image comprises an interference reflection area and a target object reflection area of a target detection object, and eliminating the interference reflection area which does not accord with the shape characteristics and the space characteristics according to the shape characteristics and the space characteristics of the target detection object, so that the target object reflection area can be obtained, determining whether the target detection object has damage defects or deficiency defects according to the target object reflection area, improving the detection efficiency and the detection accuracy of the surface reflection equipment to be detected, avoiding the condition of missing detection or wrong detection caused by fatigue due to long-time manual detection of detection personnel, and improving the production quality.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The foregoing and other objects, features and advantages of the application will be apparent from the following more particular descriptions of exemplary embodiments of the application, as illustrated in the accompanying drawings wherein like reference numbers generally represent like parts throughout the exemplary embodiments of the application.
FIG. 1 is a schematic flowchart illustrating a first embodiment of a defect detection method for eliminating reflection interference according to an embodiment of the present application;
FIG. 2 is a schematic flowchart illustrating a second embodiment of a defect detection method for eliminating reflection interference according to an embodiment of the present application;
FIG. 3 is a schematic flowchart of a third embodiment of a defect detection method for eliminating reflection interference according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device shown in an embodiment of the present application.
Detailed Description
Preferred embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms "first," "second," "third," etc. may be used herein to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "a plurality" means two or more unless specifically limited otherwise.
Example one
When some equipment made of reflective materials such as metal is subjected to visual detection, the material of a target detection object in the equipment is often the reflective material, so that the visual detection is difficult to implement under the condition, manual detection is needed, the efficiency is low, the accuracy is low, and the working strength of detection personnel is high. The prior art needs to limit the material of the bending pipe and the material of the core head to be different so as to complete detection, and the detection effect is difficult to achieve when the material of the bending pipe and the material of the core head are similar, and the reflection interference cannot be eliminated. Therefore, it is necessary to develop a visual inspection method capable of excluding the interfering light-reflecting region and retaining the light-reflecting region of the target object to detect the defect of the target object.
In view of the above problems, an embodiment of the present application provides a defect detection method for eliminating reflection interference, which can eliminate the reflection interference on the surface of a surface reflection device, improve the detection efficiency and the detection accuracy of the surface reflection device, and improve the product quality.
The technical solutions of the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Referring to fig. 1, an embodiment of a defect detection method for eliminating reflection interference according to the embodiment of the present application includes:
101. acquiring a surface reflection image of surface reflection equipment to be detected;
the surface reflection device to be measured includes, but is not limited to, a device made of metal or glass and a device coated or stuck with a reflection material on the surface, and the reflection material may be a reflection film or a reflection paint. It can be understood that when the surface of the surface light reflecting device to be measured is irradiated by incident light, most of the incident light or even all of the incident light can be reflected.
In the embodiment of the application, the preset shooting position of the surface reflection equipment to be detected can be imaged under the irradiation of the strip-shaped light source through the industrial camera, so that the surface reflection image is obtained. The strip light source may be illuminated primarily at the location of the target detection object. It can be understood that the manner of acquiring the surface reflection image of the surface reflection device to be measured is various, and in practical application, the manner of acquiring the surface reflection image needs to be determined according to practical application conditions, which is not limited herein.
102. Determining a first light reflection area image according to the surface light reflection image;
in the embodiment of the application, the first light reflection area image can be extracted or segmented from the obtained surface light reflection image, and under the irradiation of incident light, the non-target detection object and the target detection object also form light reflection, so that the first light reflection area image includes an interference light reflection area and a target object light reflection area of the target detection object, where the interference light reflection area is an area formed by light reflection of the non-target detection object and can be understood as an invalid detection area, which needs to be excluded.
103. Excluding an interference light reflecting region according to the shape characteristic and the space characteristic of the target detection object;
since the target detection object has shape and spatial characteristics that are not consistent with those of the non-target detection object, by identifying the shape and spatial characteristics that are not consistent with those of the target detection object and the non-target detection object, the interfering light reflection region, that is, the light reflection region generated by the non-target detection object, can be excluded, and the target light reflection region, that is, the light reflection region generated by the target detection object, can be retained.
104. And determining whether the target detection object has defects according to the target object reflecting area.
In the embodiment of the present application, the defects include, but are not limited to, damage defects and missing defects, where a damage defect refers to a condition where the target object is damaged, and a missing defect refers to a condition where the target object is missing.
The following beneficial effects can be seen from the first embodiment:
the method comprises the steps of obtaining a surface reflection image of surface reflection equipment to be detected, determining a first reflection area image in the surface reflection image, wherein the first reflection area image comprises an interference reflection area and a target object reflection area of a target detection object, and eliminating the interference reflection area which does not accord with the shape characteristics and the space characteristics according to the shape characteristics and the space characteristics of the target detection object, so that the target object reflection area can be obtained, determining whether the target detection object has damage defects or deficiency defects according to the target object reflection area, improving the detection efficiency and the detection accuracy of the surface reflection equipment to be detected, avoiding the condition of missing detection or wrong detection caused by fatigue due to long-time manual detection of detection personnel, and improving the production quality.
Example two
For convenience of understanding, an embodiment of a defect detection method for eliminating the reflection interference is provided below for explanation, and in practical applications, in the step of eliminating the interference reflection region according to the shape feature and the spatial feature of the target detection object, a particle analysis algorithm and a region difference set operation are adopted to eliminate the interference reflection region, so as to improve the accuracy of defect detection.
Referring to fig. 2, an embodiment of the defect detection method for eliminating reflection interference according to the embodiment of the present application includes:
201. determining a first reflection interference area according to the first reflection area image;
in embodiments of the present application, shape features include, but are not limited to, roundness features and angular features; spatial features include, but are not limited to, length features and area features.
The interference light reflection area comprises a first light reflection interference area and a second light reflection interference area, the first light reflection interference area is an area with an irregular light reflection shape, and it can be understood that the area with the irregular light reflection shape is an area formed by the light reflection of the surface of the equipment around the target detection object, and a large difference exists between the shape characteristic and the space characteristic of the target detection object in both the shape characteristic and the space characteristic. The second reflective interference area is an area with a reflective shape matching one of shape characteristics and spatial characteristics compared with the target detection object, and it can be understood that the second reflective interference area is a reflective area similar to the reflective area of the target detection object.
Therefore, in the embodiment of the present application, the light reflection region of the target object may be determined by removing the first light reflection interference region and then removing the second light reflection interference region, so as to improve the accuracy of defect detection, reduce the operation cost, and improve the operation efficiency.
In the embodiment of the application, a first reflective interference area is determined in a first reflective area image through a particle analysis algorithm, wherein the particle analysis algorithm is a particle swarm algorithm, the particle swarm algorithm is fully called as a particle swarm optimization algorithm, the particle swarm algorithm is an algorithm mainly used for solving an optimization problem, and the basic principle is that an optimal solution is found through multiple iterations by generating a group of random particles. The algorithm principle of the particle swarm algorithm specifically comprises the following steps:
initializing a particle swarm, wherein the particle swarm comprises n particles, and each particle is endowed with a random initial position and speed;
calculating the adaptive value of each particle according to the fitness function;
step three, for each particle, comparing the adaptive value of the current position of the particle with the adaptive value corresponding to the historical optimal position of the particle, and if the adaptive value of the current position is higher, updating the historical optimal position by using the current position;
step four, for each particle, comparing the adaptive value of the current position of the particle with the adaptive value corresponding to the global optimal position of the particle, and if the adaptive value of the current position is higher, updating the global optimal position by using the current position;
step five, updating the speed and the position of each particle according to a speed updating formula and a position updating formula, wherein the speed updating formula can be represented by the following formula:
wherein the content of the first and second substances,
for the d-dimensional component of the velocity vector of the particle i at the kth iteration,
for the d-dimensional component, c, of the position vector of the (k-1) th iteration particle i1，c2Representing the acceleration constant for adjusting the maximum step size of learning, r1，r2Represents two random parameters with the value range of [0, 1%]Increasing the randomness of the search, w represents the inertial weight, whose value is non-negative, and is used to adjust the search range for the solution space, pbestidThe d-component, gbest, which is the optimal position that the particle i has undergonedThe d-dimension component, which refers to the best position the population of particles has experienced;
the location update formula can be expressed by the following formula:
and step six, judging whether an ending condition is met, if the ending condition is not met, returning to the step two, if the ending condition is met, ending the algorithm, and obtaining a global optimal position, namely a global optimal solution.
In the embodiment of the application, the position of the first reflection interference area is found through the particle analysis algorithm, so that the first reflection interference area can be eliminated.
202. Excluding the first retroreflective jam area from the first retroreflective area image;
and removing the first reflection interference region from the first reflection region image through region difference set operation to obtain a second reflection region image. In this embodiment, the region difference set operation means that all the pixel points of the first reflection region image are subtracted from the pixel points in the first reflection interference region, so that the first reflection interference region can be excluded from the first reflection region image.
203. Determining a target search area in the second light reflecting area image according to the preset moving range of the target detection object;
in the embodiment of the application, a moving range of a target detection object is preset, the preset moving range refers to a moving range of the target detection object in the operation process of the surface reflection equipment to be detected, a track set graph of all moving tracks of the target detection object is obtained by recording the moving range of the target detection object in each operation in a large number, and the minimum circumscribed rectangle of the track set graph can be used as the preset moving range. The minimum circumscribed rectangle is correspondingly matched with the position of the predicted moving range of the target detection object in the second light reflection area image because the detection is carried out simultaneously in the operation process, so that the minimum circumscribed rectangle can be established in the second light reflection area image as the target search area. And determining a target search area in the second light reflection area image according to the preset moving range, so that the search time of the target light reflection area is saved, and the operation efficiency is improved.
It can be understood that the preset moving range may be obtained in various manners, and the minimum bounding rectangle of the track set graph as the preset moving range is only an example, and in practical application, the preset moving range needs to be determined according to practical application conditions, and is not limited herein.
204. Carrying out image enhancement processing on the target search area;
the image enhancement processing includes, but is not limited to, contrast enhancement, hue enhancement, saturation enhancement, brightness enhancement, and the like, and in the embodiment of the present application, the target detection image is obtained by performing contrast enhancement on the target search area.
205. And eliminating the second light reflection interference area according to the target detection image, the shape characteristic and the space characteristic to obtain a target object light reflection area.
Threshold segmentation processing is carried out on the target detection image, pixel points which do not meet the gray scale threshold after contrast enhancement are eliminated, impurities of the target detection image are less, detection accuracy is improved, a target object light reflection area is determined according to shape characteristics and space characteristics through a particle analysis algorithm, and then a second light reflection interference area is eliminated.
The following beneficial effects can be seen from the second embodiment:
the target object light reflection area is determined by removing the first light reflection interference area and then removing the second light reflection interference area, so that the accuracy of defect detection is improved, the operation cost is reduced, and the operation efficiency is improved.
EXAMPLE III
For convenience of understanding, an embodiment of a defect detection method for eliminating reflection interference is provided below for explanation, in practical application, the target detection object may be a bent pipe core print of a bent pipe apparatus, and the defect of the bent pipe core print is visually detected, so that the detection efficiency and the detection accuracy can be improved, and the defect of the bent pipe core print is prevented from affecting the production quality of a bent pipe.
Referring to fig. 3, a third embodiment of the defect detection method for eliminating reflection interference according to the embodiment of the present application includes:
301. acquiring a surface reflection image of surface reflection equipment to be detected under the irradiation of a strip-shaped light source through an industrial camera;
target test objects include, but are not limited to, a core-bending head of a core-bending apparatus, the core-bending head being attached to an end of a core-bending stem of the core-bending apparatus.
When the target detection object is the elbow core print, the corresponding surface reflection device to be detected is the elbow device, the whole body of the elbow device is made of metal, in the production process, the elbow core bar can penetrate through a metal pipe to be bent, such as a copper pipe in a heat exchange device in an air conditioner, the elbow core bar extends out of the elbow core print, and the metal pipe is bent along the elbow core print, so that when a strip light source irradiates, no matter the elbow core print, the end part of one end of the elbow core bar connected with the elbow core print, or the surface of the elbow device around the elbow core print can generate reflection light. And imaging the surface of the pipe bending equipment where the pipe bending core head is positioned by an industrial camera to obtain a surface reflection image.
302. Determining a first light reflection area image according to the surface light reflection image;
and performing threshold segmentation processing on the surface reflection image, and excluding the areas without reflection to obtain a first reflection area image.
303. Eliminating an interference light reflecting region according to the shape characteristic and the space characteristic of the bent pipe core print;
when the target detection object is the elbow core print, the shape characteristic of the elbow core print which is inconsistent with the surface of the elbow device at the periphery of the elbow core print is a roundness characteristic and a space characteristic area characteristic.
Determining a first reflection interference area according to the first reflection area image, excluding the first reflection interference area from the first reflection area image, determining a target search area in the second reflection area image according to a preset moving range of a target detection object, performing image enhancement processing on the target search area to obtain a target detection image, and determining that the reflection area to be detected is the target object reflection area if the area characteristic of the reflection area to be detected in the target detection image is larger than the areas of P pixel points and the roundness characteristic of the reflection area to be detected is larger than K and smaller than M.
In the embodiment of the present application, P is a positive integer, and preferably, the value of P may be any value between 195 and 205. The roundness characteristic determination method specifically comprises the following steps: firstly, the center of a minimum circumcircle of a light reflecting region to be detected is found out, then an edge point of the light reflecting region to be detected is found out, the distance from the edge point to the center of the circle is calculated, the obtained minimum distance is divided by the maximum distance, and then the roundness characteristic can be obtained, wherein K and M are larger than zero and smaller than or equal to 1, preferably, the value of K can be 0.7, and the value of M can be 1. It should be understood that the values of P, K and M are determined by the actual application and are not limited herein.
304. And determining whether the target detection object has defects according to the target object reflecting area.
When the target object is the elbow core print, under the condition that the elbow core print is not defective, the elbow core print and the end part of one end of the elbow core rod connected with the elbow core print have matched shape characteristics and space characteristics under the condition of light reflection, so that the elbow core print and the end part of one end of the elbow core rod connected with the elbow core print are paired in the target object light reflection area under the condition that the elbow core print is not defective, namely, the target object light reflection area comprises the light reflection area of the elbow core print and the light reflection area of the end part of one end of the elbow core rod connected with the elbow core print.
Namely, if the number of the light reflecting areas of the target object is odd, the defect of the bent pipe core head can be determined, and warning information is sent;
if the number of the target object light reflection areas is even, the bent pipe core head is still connected with the bent pipe core rod, and no defect exists, an edge point set of the target object light reflection areas is obtained through a straight line extraction algorithm, and the eccentric distance between each point in the edge point set and the central point of the target object light reflection areas is determined, so that whether the bent pipe core head has a damage defect or not is judged.
If the difference of the eccentric distances of any adjacent points in the edge point set is larger than the preset difference, the edge of one light reflecting area in the light reflecting area of the target object is not smooth, and the end part of one end of the bent pipe core rod connected with the bent pipe core head is not greatly abraded in the production process, mainly the bent pipe core head is abraded, the bent pipe core head is determined to have a damage defect, and warning information is sent.
The following beneficial effects can be seen from the third embodiment:
when the target detection object is the elbow core print of the elbow device, the visual detection is carried out on the defects of the elbow core print, the detection efficiency and the detection accuracy can be improved, the condition that the detection is missed or mistakenly detected due to fatigue caused by long-time manual detection of detection personnel is avoided, and the production quality of the elbow is prevented from being influenced by the defects of the elbow core print.
Example four
Corresponding to the embodiment of the application function implementation method, the application also provides electronic equipment and a corresponding embodiment.
Fig. 4 is a schematic structural diagram of an electronic device shown in an embodiment of the present application.
Referring to fig. 4, the electronic device 1000 includes a memory 1010 and a processor 1020.
The Processor 1020 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 1010 may include various types of storage units, such as system memory, Read Only Memory (ROM), and permanent storage. Wherein the ROM may store static data or instructions that are needed by the processor 1020 or other modules of the computer. The persistent storage device may be a read-write storage device. The persistent storage may be a non-volatile storage device that does not lose stored instructions and data even after the computer is powered off. In some embodiments, the persistent storage device employs a mass storage device (e.g., magnetic or optical disk, flash memory) as the persistent storage device. In other embodiments, the permanent storage may be a removable storage device (e.g., floppy disk, optical drive). The system memory may be a read-write memory device or a volatile read-write memory device, such as a dynamic random access memory. The system memory may store instructions and data that some or all of the processors require at runtime. Further, 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), magnetic and/or optical disks, among others. In some embodiments, memory 1010 may include a removable storage device that is readable and/or writable, such as a Compact Disc (CD), a read-only digital versatile disc (e.g., DVD-ROM, dual layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (e.g., SD card, min SD card, Micro-SD card, etc.), a magnetic floppy disc, or the like. Computer-readable storage media do not contain carrier waves or transitory electronic signals transmitted by wireless or wired means.
The memory 1010 has stored thereon executable code that, when processed by the processor 1020, may cause the processor 1020 to perform some or all of the methods described above.
The aspects of the present application have been described in detail hereinabove with reference to the accompanying drawings. In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments. Those skilled in the art should also appreciate that the acts and modules referred to in the specification are not necessarily required in the present application. In addition, it can be understood that the steps in the method of the embodiment of the present application may be sequentially adjusted, combined, and deleted according to actual needs, and the modules in the device of the embodiment of the present application may be combined, divided, and deleted according to actual needs.
Furthermore, the method according to the present application may also be implemented as a computer program or computer program product comprising computer program code instructions for performing some or all of the steps of the above-described method of the present application.
Alternatively, the present application may also be embodied as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) having stored thereon executable code (or a computer program, or computer instruction code) which, when executed by a processor of an electronic device (or electronic device, server, etc.), causes the processor to perform part or all of the various steps of the above-described method according to the present application.
Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the applications disclosed herein may be implemented as electronic hardware, computer software, or combinations of both.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Having described embodiments of the present application, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (12)
1. A defect detection method for eliminating reflection interference is characterized by comprising the following steps:
acquiring a surface reflection image of surface reflection equipment to be detected;
determining a first light reflection area image according to the surface light reflection image, wherein the first light reflection area image comprises an interference light reflection area and a target object light reflection area of a target detection object;
excluding the interference light reflecting region according to the shape characteristic and the space characteristic of the target detection object to obtain the target object light reflecting region;
and determining whether the target detection object has defects according to the target object light reflecting area, wherein the defects comprise damage defects and missing defects.
2. The defect detection method of eliminating the interference of light reflection according to claim 1,
the shape features include roundness features and angle features; the spatial features comprise length features and area features;
the interference light reflecting area comprises a first light reflecting interference area and a second light reflecting interference area, the first light reflecting interference area is an area with an irregular light reflecting shape, and the second light reflecting interference area is an area with a light reflecting shape matched with one of the shape characteristic and the space characteristic compared with the target detection object;
the target detection object comprises a pipe bending core head of pipe bending equipment, and the pipe bending core head is connected to one end of a pipe bending core rod of the pipe bending equipment.
3. The defect detection method of eliminating the interference of light reflection according to claim 2,
the obtaining the target object light reflecting region by excluding the interference light reflecting region according to the shape feature and the spatial feature of the target detection object includes:
determining the first reflection interference area according to the first reflection area image;
excluding the first reflection interference area from the first reflection area image to obtain a second reflection area image;
determining a target search area in the second light reflecting area image according to the preset moving range of the target detection object;
performing image enhancement processing on the target search area to obtain a target detection image;
and excluding the second light reflection interference area according to the target detection image, the shape characteristic and the space characteristic to obtain the target object light reflection area.
4. The defect detection method of eliminating the interference of light reflection according to claim 3,
the determining the first reflection interference region according to the first reflection region image includes:
determining the first retroreflective jam area in the first retroreflective area image by a particle analysis algorithm.
5. The defect detection method of eliminating the interference of light reflection according to claim 3,
the excluding the first retroreflective jam area from the first retroreflective area image includes:
and excluding the first reflection interference region from the first reflection region image through region difference set operation.
6. The defect detection method of eliminating the interference of light reflection according to claim 3,
the image enhancement processing on the target search area comprises the following steps:
and carrying out contrast enhancement on the target search area.
7. The defect detection method of eliminating the interference of light reflection according to claim 4,
the excluding the second reflective interference region according to the target detection image, the shape feature, and the spatial feature includes:
and performing threshold segmentation processing on the target detection image, determining the target object light reflection region according to the shape feature and the space feature through the particle analysis algorithm, and excluding the second light reflection interference region.
8. The defect detection method of eliminating the interference of light reflection according to claim 7,
the determining, by the particle analysis algorithm, the target object light reflection region according to the shape feature and the spatial feature includes:
when the target detection object is the elbow core print, the shape feature is the roundness feature, and the space feature is the area feature;
if the area characteristic of a to-be-detected light reflecting area in the target detection image is larger than the areas of P pixel points, and the roundness characteristic of the to-be-detected light reflecting area is larger than K and smaller than M, determining that the to-be-detected light reflecting area is the target object light reflecting area; p is a positive integer, and K and M are greater than zero and less than or equal to 1.
9. The defect detection method of eliminating the interference of light reflection according to claim 2,
the determining whether the target detection object has defects according to the target object reflection area comprises the following steps:
when the target detection object is the bent core print, if the number of the light reflecting areas of the target object is an odd number, determining that the bent core print has the defect, and sending warning information;
if the number of the target object light reflecting areas is an even number, acquiring an edge point set of the target object light reflecting areas through a straight line extraction algorithm, and determining the eccentric distance between each point in the edge point set and the central point of the target object light reflecting area;
and if the difference of the eccentric distances of any adjacent points in the edge point set is larger than a preset difference, determining that the bent pipe core print has the damage defect, and sending the warning information.
10. The defect detection method of eliminating the interference of light reflection according to claim 7,
determining a first retroreflective area image from the surface retroreflective image includes:
and performing the threshold segmentation processing on the surface reflection image to obtain the first reflection area image.
11. An electronic device, comprising:
a processor; and
a memory having executable code stored thereon, which when executed by the processor, causes the processor to perform the method of any one of claims 1-10.
12. A non-transitory machine-readable storage medium having stored thereon executable code, which when executed by a processor of an electronic device, causes the processor to perform the method of any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111334149.XA CN114331954A (en) | 2021-11-11 | 2021-11-11 | Defect detection method for eliminating reflection interference, electronic equipment and storage equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111334149.XA CN114331954A (en) | 2021-11-11 | 2021-11-11 | Defect detection method for eliminating reflection interference, electronic equipment and storage equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114331954A true CN114331954A (en) | 2022-04-12 |
Family
ID=81044501
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111334149.XA Pending CN114331954A (en) | 2021-11-11 | 2021-11-11 | Defect detection method for eliminating reflection interference, electronic equipment and storage equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114331954A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115272134A (en) * | 2022-09-26 | 2022-11-01 | 南通睿禧智能科技有限公司 | PCB image reflection removing method based on PCB interference reflection recognition |
| CN116596928A (en) * | 2023-07-18 | 2023-08-15 | 山东金胜粮油食品有限公司 | Quick peanut oil impurity detection method based on image characteristics |
-
2021
- 2021-11-11 CN CN202111334149.XA patent/CN114331954A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115272134A (en) * | 2022-09-26 | 2022-11-01 | 南通睿禧智能科技有限公司 | PCB image reflection removing method based on PCB interference reflection recognition |
| CN115272134B (en) * | 2022-09-26 | 2022-12-16 | 南通睿禧智能科技有限公司 | PCB image reflection removing method based on PCB interference reflection recognition |
| CN116596928A (en) * | 2023-07-18 | 2023-08-15 | 山东金胜粮油食品有限公司 | Quick peanut oil impurity detection method based on image characteristics |
| CN116596928B (en) * | 2023-07-18 | 2023-10-03 | 山东金胜粮油食品有限公司 | Quick peanut oil impurity detection method based on image characteristics |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11310467B2 (en) | Object inspection system and method for inspecting an object | |
| CN116758061B (en) | Casting surface defect detection method based on computer vision | |
| CN114331954A (en) | Defect detection method for eliminating reflection interference, electronic equipment and storage equipment | |
| CN112767398B (en) | Method and device for detecting wafer defects | |
| US9171364B2 (en) | Wafer inspection using free-form care areas | |
| US9846929B2 (en) | Fast density estimation method for defect inspection application | |
| Pernkopf et al. | Visual inspection of machined metallic high-precision surfaces | |
| CN112701060B (en) | Method and device for detecting bonding wire of semiconductor chip | |
| CN116757990A (en) | Railway fastener defect online detection and identification method based on machine vision | |
| CN115063423B (en) | Self-adaptive identification method for cold and hot cracks of mechanical castings based on computer vision | |
| CN114693610A (en) | Welding seam surface defect detection method, equipment and medium based on machine vision | |
| CN108596872A (en) | The detection method of rail disease based on Gabor wavelet and SVM | |
| CN116664569B (en) | Weld flash defect detection method | |
| CN115100191A (en) | Metal casting defect identification method based on industrial detection | |
| CN111275705A (en) | Intelligent cloth inspecting method and device, electronic equipment and storage medium | |
| CN107808165B (en) | Infrared image matching method based on SUSAN corner detection | |
| Sun et al. | Unsupervised surface defect detection of aluminum sheets with combined bright-field and dark-field illumination | |
| CN113298775A (en) | Self-priming pump double-sided metal impeller appearance defect detection method, system and medium | |
| CN111833350A (en) | Machine vision detection method and system | |
| Vishwanatha et al. | A Survey on Defect Detection of Vials | |
| CN116051541A (en) | Bearing end face gentle abrasion detection method and device based on stroboscopic light source | |
| CN111473944B (en) | PIV data correction method and device for observing complex wall surface in flow field | |
| CN113393440A (en) | Method for automatically enhancing and identifying weld defects based on magneto-optical imaging | |
| WO2022162417A1 (en) | Systems and methods for paint defect detection using machine learning | |
| Ieamsaard et al. | Automatic optical inspection of solder ball burn defects on head gimbal assembly |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |