CN111914508A - Component detection method and device, electronic equipment and readable storage medium - Google Patents
Component detection method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN111914508A CN111914508A CN202010834780.5A CN202010834780A CN111914508A CN 111914508 A CN111914508 A CN 111914508A CN 202010834780 A CN202010834780 A CN 202010834780A CN 111914508 A CN111914508 A CN 111914508A
- Authority
- CN
- China
- Prior art keywords
- component
- pcb
- real object
- image
- design drawing
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 35
- 238000003860 storage Methods 0.000 title claims abstract description 10
- 238000013461 design Methods 0.000 claims abstract description 68
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 23
- 238000009434 installation Methods 0.000 claims abstract description 10
- 238000000034 method Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims 1
- 238000005265 energy consumption Methods 0.000 abstract description 3
- 150000003071 polychlorinated biphenyls Chemical class 0.000 description 18
- 238000004519 manufacturing process Methods 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000005476 soldering Methods 0.000 description 2
- 238000003466 welding Methods 0.000 description 2
- 239000003990 capacitor Substances 0.000 description 1
- 230000000052 comparative effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/39—Circuit design at the physical level
- G06F30/398—Design verification or optimisation, e.g. using design rule check [DRC], layout versus schematics [LVS] or finite element methods [FEM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2115/00—Details relating to the type of the circuit
- G06F2115/12—Printed circuit boards [PCB] or multi-chip modules [MCM]
Abstract
The application provides a component detection method, a device, an electronic device and a readable storage medium, comprising: determining the position corresponding relation between a PCB design drawing and a PCB real object photo according to an artificial intelligence algorithm; for each component in the PCB design drawing, marking the identity information of the component to be installed at the corresponding position of the PCB real object photo according to the identity information of the component and the position of the component in the PCB design drawing; carrying out image recognition on the corresponding position of the PCB real object photo to obtain a recognition result; and determining whether the components at the corresponding positions of the PCB real object photos have installation problems or not according to the identification results and the identity information of the components to be installed. The corresponding relation between the design drawing and the real object photo is determined through an artificial intelligence algorithm, and compared with the artificial detection in the prior art, the artificial detection method reduces energy consumption and solves the problems that the artificial detection wastes time and labor.
Description
Technical Field
The application relates to the technical field of detection, in particular to a component detection method and device, electronic equipment and a readable storage medium.
Background
Printed Circuit boards (PCBs for short) have been widely used in various fields of social production and life since their birth. Whether the PCB works normally or not directly determines whether the product works normally or not. The components on the PCB are important components of the PCB, and the PCB realizes various complex circuit functions by welding the components. In the actual production and manufacturing process of the PCB, the problem of component installation of misconnection or missing connection sometimes occurs. When the installation problem of the components occurs, the PCB is short-circuited and broken if the components are light, and the PCB is scrapped; the fire is caused and safety accidents are caused. Therefore, it is necessary to detect the mounting condition of the component.
At present, the main detection method is realized by using a mode of identifying the circuit board by naked eyes, and time and labor are wasted.
Disclosure of Invention
An object of the embodiments of the present application is to provide a component detection method, a device, an electronic apparatus, and a readable storage medium, so as to solve the problem that manual detection in the prior art is time-consuming and labor-consuming.
In a first aspect, an embodiment of the present application provides a component detection method, where the method includes: determining the position corresponding relation between a PCB design drawing and a PCB real object photo according to an artificial intelligence algorithm; for each component in the PCB design drawing, marking the identity information of the component to be installed at the corresponding position of the PCB real object photo according to the identity information of the component and the position of the component in the PCB design drawing; carrying out image recognition on the corresponding position of the PCB real object photo to obtain a recognition result; and determining whether the components at the corresponding positions of the PCB real object photos have installation problems or not according to the identification results and the identity information of the components to be installed.
In the above embodiment, the position corresponding relationship between the PCB design drawing and the PCB real photograph can be determined according to an artificial intelligence algorithm, so that the identity information of the component to be mounted is marked at the position corresponding to the PCB design drawing in the PCB real photograph, then the PCB real photograph is subjected to image recognition, and the recognition result is compared with the identity information of the component to be mounted, so that whether the component in the PCB real photograph has a mounting problem can be determined. The corresponding relation between the design drawing and the real object photo is determined through an artificial intelligence algorithm, and compared with the artificial detection in the prior art, the artificial detection method reduces energy consumption and solves the problems that the artificial detection wastes time and labor.
In a possible design, the determining the position corresponding relationship between the PCB design drawing and the PCB real photograph according to the artificial intelligence algorithm includes: selecting at least one corner point representing the integral features of the image from the PCB design drawing and the PCB real object photo by using the artificial intelligence algorithm; acquiring an image of the at least one corner point in the PCB design drawing; acquiring an image of the at least one corner point in the PCB real object photo; and establishing the corresponding relation of corner points with the similarity higher than a similarity threshold value between the PCB design drawing and the PCB real object photo.
In the above embodiment, the corner points capable of representing the overall features of the image, that is, the corner points with obvious features, may be found out in the PCB design drawing and the PCB real photograph, and then the corresponding relationship between the corner points with obvious features may be established, so as to implement the position corresponding relationship between the PCB design drawing and the PCB real photograph. Starting from the corner points with obvious features, the speed of establishing the position corresponding relation can be improved.
In one possible design, performing image recognition on the corresponding position of the PCB real photograph to obtain a recognition result, includes: dividing the PCB real object photo according to the position of the component to be mounted to divide a plurality of sub-images, wherein each sub-image in the plurality of sub-images comprises the position of the component to be mounted; and carrying out image processing on each sub-image through a detection model to obtain the identification result of each sub-image.
In the above-described embodiment, since the real-object picture is divided and the divided sub-images are subjected to image processing, the size of the sub-images is reduced for the original real-object picture, and therefore, the difficulty of image processing is reduced for each sub-image.
In a possible design, the mounting problem includes missing connection, and determining whether the component at the corresponding position of the PCB real photo has the mounting problem according to the identification result and the identity information of the component to be mounted includes: judging whether a component is installed at a position corresponding to the component to be installed in the identification result; and if not, determining that the position corresponding to the component to be mounted has the problem of missing connection.
In the above embodiment, it may be preferentially determined whether a component is mounted at a position corresponding to the real photo, and if no component is mounted, it may be directly determined that there is a missing connection problem, and the position where the missing connection problem is located is the position corresponding to the component that should be mounted. The judgment of the existence of the component consumes less computing resources, and the judgment is carried out first, so that the computing resources can be effectively saved, and the detection speed is improved.
In one possible design, the mounting problem includes misconnection, and after determining whether a component is mounted at a position corresponding to the component to be mounted in the recognition result, the method further includes: if the position corresponding to the component to be installed is provided with the component, judging whether the identity of the installed component corresponds to the identity information of the component to be installed; and if not, determining that the position corresponding to the component to be mounted has the wrong connection problem.
In the above embodiment, on the basis of determining that the component is mounted at the position corresponding to the physical photograph, further judgment is performed to determine whether the actually mounted component is the component to be mounted, and if so, it is determined that the position does not have the problem of component mounting; if not, indicating that the component at the position is misconnected. Firstly, whether the missed connection exists is judged, and then whether the misconnection exists is judged on the basis of determining that the missed connection does not exist, and because the judgment of existence of the components consumes less computing resources, the two-step combined judgment can realize high-efficiency judgment.
In a second aspect, an embodiment of the present application provides a device for detecting a component, where the device includes: the position corresponding determination module is used for determining the position corresponding relation between the PCB design drawing and the PCB real object photo according to an artificial intelligence algorithm; the information marking module is used for marking the identity information of the components which are to be installed at the corresponding positions of the PCB real object photos for each component in the PCB design drawings according to the identity information of the components and the positions of the components in the PCB design drawings; the recognition result obtaining module is used for carrying out image recognition on the corresponding position of the PCB real object photo to obtain a recognition result; and the mounting problem determining module is used for determining whether the components at the corresponding positions of the PCB real object photos have mounting problems or not according to the identification results and the identity information of the components to be mounted.
In one possible design, the position correspondence determining module is specifically configured to select, by using the artificial intelligence algorithm, at least one corner point representing an overall feature of an image from the PCB design drawing and the PCB real photograph; acquiring an image of the at least one corner point in the PCB design drawing; acquiring an image of the at least one corner point in the PCB real object photo; and establishing the corresponding relation of corner points with the similarity higher than a similarity threshold value between the PCB design drawing and the PCB real object photo.
In a possible design, the recognition result obtaining module is specifically configured to segment the PCB real object photo according to the position of the component to be mounted, so as to segment a plurality of sub-images, where each sub-image in the plurality of sub-images includes the position of the component to be mounted; and carrying out image processing on each sub-image through a detection model to obtain the identification result of each sub-image.
In one possible design, the installation problem determination module is specifically configured to: judging whether a component is installed at a position corresponding to the component to be installed in the identification result; and if not, determining that the position corresponding to the component to be mounted has the problem of missing connection.
In one possible design, the installation problem determination module is specifically configured to: when a component is installed at a position corresponding to the component to be installed, judging whether the identity of the installed component corresponds to the identity information of the component to be installed; and if not, determining that the position corresponding to the component to be mounted has the wrong connection problem.
In a third aspect, an embodiment of the present application provides an electronic device, including the method in the first aspect or any optional implementation manner of the first aspect.
In a fourth aspect, the present application provides a readable storage medium having stored thereon an executable program which, when executed by a processor, performs the method of the first aspect or any of the optional implementations of the first aspect.
In a fifth aspect, the present application provides an executable program product which, when run on a computer, causes the computer to perform the method of the first aspect or any possible implementation manner of the first aspect.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments of the present application will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and that those skilled in the art can also obtain other related drawings based on the drawings without inventive efforts.
Fig. 1 shows a schematic flow chart of a component detection method provided in an embodiment of the present application;
FIG. 2 is a flowchart illustrating the detailed steps of step S110 in FIG. 1;
FIG. 3 is a flowchart illustrating a specific step of step S130 in FIG. 1;
FIG. 4 is a flowchart illustrating the detailed steps of step S140 in FIG. 1;
FIG. 5 shows a partial schematic view of a PCB photo album;
fig. 6 shows a schematic structural block diagram of a component detection apparatus provided in an embodiment of the present application.
Detailed Description
In the comparative example, the manufacturing process of the PCB board is as follows: first by the designer through the drawing software for example: the method comprises the following steps that (1) the Altium Designer draws a PCB, then a board making person uses a board making machine to generate a bare PCB according to the drawn circuit board, and then a worker contrasts a circuit schematic diagram and a design diagram designed by a Designer to enable a corresponding electronic component to be as follows: and the chip, the resistor, the inductor, the capacitor and the like are arranged at corresponding positions of the PCB bare board, so that the PCB is manufactured.
In the process of installing electronic components by workers, the manufacturing process is very easy to cause the phenomenon of missing connection or misconnection of the components because the components are mostly in a surface mount type at present and the number of the components on the PCB is large and the components are densely arranged. The device is in missing connection or misconnection to cause serious consequences, and if the device is in a light state, the circuit is broken, and the circuit function cannot be realized; the circuit short circuit is caused, the whole hardware circuit board including all chips on the circuit board is burnt out, and huge economic loss is caused.
At present, the main detection method is realized by using a mode of identifying the circuit board by naked eyes, and time and labor are wasted.
According to the component detection method provided by the embodiment of the application, the corresponding relation between the design drawing and the real object photo is determined through an artificial intelligence algorithm, so that the energy consumption is reduced, and the problems that manual detection wastes time and labor are solved.
Referring to fig. 1, fig. 1 shows a component detection method provided in an embodiment of the present application, where the method may be executed by an electronic device, and the method specifically includes the following steps S110 to S140:
and step S110, determining the position corresponding relation between the PCB design drawing and the PCB real object photo according to an artificial intelligence algorithm.
Optionally, an artificial intelligence algorithm may be used to perform corner detection first, and perform corner matching after the corner detection is completed.
In the corner matching, the following steps may be performed: selecting a certain point which represents the same position in the PCB design drawing and the PCB real photo, then establishing a planar rectangular coordinate system on the PCB design drawing and the PCB real photo respectively by taking the point as a coordinate origin, wherein the unit length of a vertical and horizontal coordinate axis of the planar rectangular coordinate system of the PCB design drawing is the same as the unit length of a vertical and horizontal coordinate axis of the planar rectangular coordinate system of the PCB real photo. And then, coordinate points corresponding to all components can be obtained in the planar rectangular coordinate system where the PCB design drawing is located, and then corresponding coordinate points are found in the planar rectangular coordinate system where the PCB real object photo is located, so that the position correspondence between the PCB design drawing and the PCB real object photo is realized.
Referring to fig. 2, in an embodiment, the step S110 may include the following steps:
and S111, selecting at least one corner point representing the integral characteristics of the image from the PCB design drawing and the PCB real object photo by using the artificial intelligence algorithm.
The artificial intelligence algorithm is an algorithm for extracting angular points representing the integral features of the image from the image, and specifically can be a Convolutional Neural Network (CNN) algorithm, a ResNet algorithm, a GoogleNet algorithm and the like; the angular points representing the overall features of the image can be the corner positions of objects in the image, the point-like features of the objects in the image, or the centers of circles of circular features and the like. The artificial intelligence algorithm can be trained by inputting a large number of PCB plans and PCB transaction photographs as sample images to the artificial intelligence algorithm.
Step S112, acquiring an image of the at least one corner point in the PCB design drawing.
And S113, acquiring an image of the at least one corner point in the PCB real object photo.
And step S114, establishing the corresponding relation of corner points with the similarity higher than a similarity threshold value between the PCB design drawing and the PCB real object photo.
The similarity threshold is a preset value, and if the similarity threshold is exceeded, the similarity of the characteristic corner points is high. Angular points which can represent the integral features of the image, namely the angular points with obvious features, can be found out in the PCB design drawing and the PCB real object photo, and then the corresponding relation of the angular points with obvious features is established, so that the position corresponding relation of the PCB design drawing and the PCB real object photo is realized. Starting from the corner points with obvious features, the speed of establishing the position corresponding relation can be improved.
Optionally, before step S110, a PCB real photograph may be obtained by: the PCB board is imaged using a high resolution camera. Thereby obtaining the PCB real photo.
And step S120, for each component in the PCB design drawing, marking the identity information of the component which is to be installed at the corresponding position of the PCB real object photo according to the identity information of the component and the position of the component in the PCB design drawing.
The identity information of the component can be the type and specific model of the component. In a PCB design drawing, specific identity information of components at each position is clear, for example, the position A corresponds to a resistor with the model a; position B corresponds to a chip of type B, etc. Therefore, according to the definite identity information of the components at each position in the PCB design drawing, the identity information of the components which should be installed at the position can be marked at the corresponding position of the PCB real object photo.
And step S130, carrying out image recognition on the corresponding position of the PCB real object photo to obtain a recognition result.
In a specific implementation mode, the image recognition can be directly carried out on the whole PCB real object photo, and a recognition result can be recognized from the whole PCB real object photo.
Referring to fig. 3, in another embodiment, the step S130 may also include the following steps S131 to S132:
step S131, dividing the PCB real image according to the position of the component to be mounted, and dividing into a plurality of sub-images, where each sub-image in the plurality of sub-images includes the position of the component to be mounted.
Optionally, the boundaries of the components may be detected in the PCB design drawing by means of boundary detection, and the range where the components to be mounted are located is circled in the PCB real photograph according to the same boundary, and the image in the range is divided into sub-images.
Optionally, a plurality of corners of the component may be identified in the PCB design drawing, then the plurality of corners are also identified at corresponding positions in the PCB real photograph, then the plurality of corners are connected to enclose a range where the component to be mounted is located, and an image in the range is segmented into sub-images.
Step S132, carrying out image processing on each sub-image through a detection model to obtain the identification result of each sub-image.
Optionally, the recognition result may be specific component information or prompt information of "component not detected", that is, the sub-image is recognized to obtain specific identity information of the component in the sub-image, and if the component is not recognized in the sub-image, the recognition result may also be "component not detected".
Optionally, the identification result may also include "component not detected", "consistent", or "inconsistent", and the identification result of "component not detected" may be given when the component is not identified; under the condition of determining that the components are installed, the actually installed component images can be directly compared with the component images which should be installed, whether the actually installed component images are consistent with the component images which should be installed or not is judged, and therefore the 'consistent' or 'inconsistent' identification results are directly obtained.
Because the object photo is segmented and the segmented sub-images are subjected to image processing, the volume of the sub-images is reduced as compared with the original object photo, and the difficulty of image processing is reduced for each sub-image.
And step S140, determining whether the component at the corresponding position of the PCB real object photo has installation problems or not according to the identification result and the identity information of the component to be installed.
Referring to fig. 4, in the case that the recognition result may be specific component information or "no component is detected", the step S140 may include the following steps S141 to S144:
step S141, determining whether a component is mounted at a position corresponding to the component to be mounted in the recognition result, if yes, executing step S142; if not, go to step S144.
Step S142, determining whether the identity of the mounted component corresponds to the identity information of the component that should be mounted, if not, executing step S143.
On the basis of determining that the corresponding position is provided with the component, the component can be identified, so that the specific identity of the installed component can be identified. Judging whether the identity corresponds to the identity information of the component to be installed, if so, indicating that the installation problem does not occur; if not, it indicates that the mounted component is incorrect, and step S143 is executed.
And step S143, determining that the position corresponding to the component to be mounted has the wrong connection problem.
And step S144, determining that the position corresponding to the component to be mounted has the problem of missing connection.
Optionally, the component may be fixed to the PCB by welding or by plugging, and the fixing manner of the component and the PCB should not be construed as a limitation to the present application. For convenience of explanation, if it is not assumed that the component is fixed to the PCB by soldering, the misconnection corresponds to the misconnection problem, and the missing connection corresponds to the missing soldering problem.
Referring to fig. 5, it is not assumed that the component to be mounted at the position corresponding to 502 in fig. 5 is an inductor of type c, the component to be mounted at the position corresponding to 504 is a resistor of type 103, and the component to be mounted at the position corresponding to 506 in fig. 5 is a chip of type z, so that since the component is not identified at the position corresponding to 502, the problem of missing mounting at the position corresponding to 502 can be determined; the component actually mounted at 504 is a resistor with the model number of 103, and if the component is consistent with the component to be mounted, the position corresponding to 504 can be determined to have no mounting problem; 506, if the actually mounted component is a resistor with the model number of 103 and is not consistent with the component to be mounted, the problem of wrong connection at the position corresponding to 506 can be determined.
On the basis of determining that the components are installed at the corresponding positions of the physical photos, further judgment is carried out to judge whether the actually installed components are the components which should be installed, and if yes, the situation that the installation problem of the components does not exist at the positions is shown; if not, indicating that the component at the position is misconnected. Firstly, whether the missed connection exists is judged, and then whether the misconnection exists is judged on the basis of determining that the missed connection does not exist, and because the judgment of existence of the components consumes less computing resources, the two-step combined judgment can realize high-efficiency judgment.
Optionally, for the case that the recognition result includes "no component detected", "consistent", or "inconsistent", step S140 may determine whether the component at the corresponding position of the PCB real photograph has a mounting problem directly according to the recognition result. If the identification result is that the component is not detected, the problem that the position corresponding to the component to be installed has missing connection can be determined; if the identification result is inconsistent, the problem that the position corresponding to the component to be installed is misconnected can be determined; if the recognition result is "consistent", it can be determined that there is no mounting problem at the position corresponding to the component to be mounted. Referring to fig. 6, fig. 6 shows a device inspection apparatus provided in an embodiment of the present application, where the apparatus 500 includes:
a position correspondence determining module 510, configured to determine a position correspondence between a PCB design drawing of the printed circuit board and a PCB real photograph according to an artificial intelligence algorithm;
the information marking module 520 is configured to mark, for each component in the PCB design drawing, identity information of a component to be mounted at a corresponding position of the PCB real photograph according to the identity information of the component and the position of the component in the PCB design drawing;
a recognition result obtaining module 530, configured to perform image recognition on a corresponding position of the PCB real photograph to obtain a recognition result;
and the mounting problem determining module 540 is configured to determine whether a mounting problem occurs in the component at the corresponding position of the PCB real photograph according to the identification result and the identity information of the component to be mounted.
The position correspondence determining module is specifically configured to select, by using the artificial intelligence algorithm, at least one corner point representing an overall feature of an image from the PCB design drawing and the PCB real photograph; acquiring an image of the at least one corner point in the PCB design drawing; acquiring an image of the at least one corner point in the PCB real object photo; and establishing the corresponding relation of corner points with the similarity higher than a similarity threshold value between the PCB design drawing and the PCB real object photo.
The recognition result obtaining module 530 is specifically configured to segment the PCB real object photo according to the position of the component to be mounted, and segment a plurality of sub-images, where each sub-image in the plurality of sub-images includes a position where the component to be mounted is located; and carrying out image processing on each sub-image through a detection model to obtain the identification result of each sub-image.
The mounting problem determination module 540 is specifically configured to: judging whether a component is installed at a position corresponding to the component to be installed in the identification result; and if not, determining that the position corresponding to the component to be mounted has the problem of missing connection.
The mounting problem determination module 540 is specifically configured to: when a component is installed at a position corresponding to the component to be installed, judging whether the identity of the installed component corresponds to the identity information of the component to be installed; and if not, determining that the position corresponding to the component to be mounted has the wrong connection problem.
The component detection apparatus shown in fig. 6 corresponds to the component detection method shown in fig. 1, and details thereof are not repeated here.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.
In addition, units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
Furthermore, the functional modules in the embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
The above description is only an example of the present application and is not intended to limit the scope of the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A component detection method is characterized by comprising the following steps:
determining the position corresponding relation between a PCB design drawing and a PCB real object photo according to an artificial intelligence algorithm;
for each component in the PCB design drawing, marking the identity information of the component to be installed at the corresponding position of the PCB real object photo according to the identity information of the component and the position of the component in the PCB design drawing;
carrying out image recognition on the corresponding position of the PCB real object photo to obtain a recognition result;
and determining whether the components at the corresponding positions of the PCB real object photos have installation problems or not according to the identification results and the identity information of the components to be installed.
2. The method of claim 1, wherein determining the position correspondence between the PCB design drawing and the PCB physical photograph according to the artificial intelligence algorithm comprises:
selecting at least one corner point representing the integral features of the image from the PCB design drawing and the PCB real object photo by using the artificial intelligence algorithm;
acquiring an image of the at least one corner point in the PCB design drawing;
acquiring an image of the at least one corner point in the PCB real object photo;
and establishing the corresponding relation of corner points with the similarity higher than a similarity threshold value between the PCB design drawing and the PCB real object photo.
3. The method of claim 1, wherein performing image recognition on the corresponding position of the PCB real photo to obtain a recognition result comprises:
dividing the PCB real object photo according to the position of the component to be mounted to divide a plurality of sub-images, wherein each sub-image in the plurality of sub-images comprises the position of the component to be mounted;
and carrying out image processing on each sub-image through a detection model to obtain the identification result of each sub-image.
4. The method according to claim 1, wherein the mounting problem includes missing connection, and the determining whether the component at the corresponding position of the PCB real photo has the mounting problem according to the identification result and the identity information of the component that should be mounted includes:
judging whether a component is installed at a position corresponding to the component to be installed in the identification result;
and if not, determining that the position corresponding to the component to be mounted has the problem of missing connection.
5. The method according to claim 4, wherein the mounting problem includes misconnection, and after the determination is made as to whether or not a component is mounted at a position corresponding to the component to be mounted in the recognition result, the method further comprises:
if the position corresponding to the component to be installed is provided with the component, judging whether the identity of the installed component corresponds to the identity information of the component to be installed;
and if not, determining that the position corresponding to the component to be mounted has the wrong connection problem.
6. A component detection apparatus, the apparatus comprising:
the position corresponding determination module is used for determining the position corresponding relation between the PCB design drawing and the PCB real object photo according to an artificial intelligence algorithm;
the information marking module is used for marking the identity information of the components which are to be installed at the corresponding positions of the PCB real object photos for each component in the PCB design drawings according to the identity information of the components and the positions of the components in the PCB design drawings;
the recognition result obtaining module is used for carrying out image recognition on the corresponding position of the PCB real object photo to obtain a recognition result;
and the mounting problem determining module is used for determining whether the components at the corresponding positions of the PCB real object photos have mounting problems or not according to the identification results and the identity information of the components to be mounted.
7. The apparatus according to claim 6, wherein the location correspondence determining module is specifically configured to select, using the artificial intelligence algorithm, at least one corner point representing an overall feature of the image from the PCB design drawing and the PCB physical photograph;
acquiring an image of the at least one corner point in the PCB design drawing;
acquiring an image of the at least one corner point in the PCB real object photo;
and establishing the corresponding relation of corner points with the similarity higher than a similarity threshold value between the PCB design drawing and the PCB real object photo.
8. The apparatus according to claim 7, wherein the recognition result obtaining module is specifically configured to segment the PCB real-world photograph according to the position of the component that should be mounted, so as to obtain a plurality of sub-images, where each of the plurality of sub-images includes the position of the component that should be mounted;
and carrying out image processing on each sub-image through a detection model to obtain the identification result of each sub-image.
9. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating over the bus when the electronic device is operating, the processor executing the machine-readable instructions to perform the method of any one of claims 1-5 when executed.
10. A readable storage medium, having stored thereon a computer program which, when executed by a processor, performs the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010834780.5A CN111914508A (en) | 2020-08-19 | 2020-08-19 | Component detection method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010834780.5A CN111914508A (en) | 2020-08-19 | 2020-08-19 | Component detection method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111914508A true CN111914508A (en) | 2020-11-10 |
Family
ID=73278366
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010834780.5A Pending CN111914508A (en) | 2020-08-19 | 2020-08-19 | Component detection method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111914508A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114089213A (en) * | 2021-12-03 | 2022-02-25 | 中科国微科技(深圳)有限公司 | All-digital control type high-power direct-current stabilized power supply detection method and system |
| CN114585253A (en) * | 2022-03-15 | 2022-06-03 | 杭州测质成科技有限公司 | PCB component installation and rechecking system and method based on image recognition |
| CN116362957A (en) * | 2021-12-27 | 2023-06-30 | 广州镭晨智能装备科技有限公司 | PCB card image alignment method, device, medium and electronic equipment |
| CN116362957B (en) * | 2021-12-27 | 2024-05-14 | 广州镭晨智能装备科技有限公司 | PCB card image alignment method, device, medium and electronic equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184778A (en) * | 2015-08-25 | 2015-12-23 | 广州视源电子科技股份有限公司 | Detection method and apparatus |
| CN109859164A (en) * | 2018-12-21 | 2019-06-07 | 苏州绿控传动科技股份有限公司 | A method of by Quick-type convolutional neural networks to PCBA appearance test |
| CN110070536A (en) * | 2019-04-24 | 2019-07-30 | 南京邮电大学 | A kind of pcb board component detection method based on deep learning |
| CN111260621A (en) * | 2020-01-14 | 2020-06-09 | 湖南大学 | Method for positioning and identifying surface defects of printed circuit board |
-
2020
- 2020-08-19 CN CN202010834780.5A patent/CN111914508A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105184778A (en) * | 2015-08-25 | 2015-12-23 | 广州视源电子科技股份有限公司 | Detection method and apparatus |
| CN109859164A (en) * | 2018-12-21 | 2019-06-07 | 苏州绿控传动科技股份有限公司 | A method of by Quick-type convolutional neural networks to PCBA appearance test |
| CN110070536A (en) * | 2019-04-24 | 2019-07-30 | 南京邮电大学 | A kind of pcb board component detection method based on deep learning |
| CN111260621A (en) * | 2020-01-14 | 2020-06-09 | 湖南大学 | Method for positioning and identifying surface defects of printed circuit board |
Non-Patent Citations (2)
| Title |
|---|
| 彭世亮: "基于图像处理的电路板卡缺陷检测方法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 陈小勇: "基于机器视觉的PCB缺陷检测系统的设计", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114089213A (en) * | 2021-12-03 | 2022-02-25 | 中科国微科技(深圳)有限公司 | All-digital control type high-power direct-current stabilized power supply detection method and system |
| CN116362957A (en) * | 2021-12-27 | 2023-06-30 | 广州镭晨智能装备科技有限公司 | PCB card image alignment method, device, medium and electronic equipment |
| CN116362957B (en) * | 2021-12-27 | 2024-05-14 | 广州镭晨智能装备科技有限公司 | PCB card image alignment method, device, medium and electronic equipment |
| CN114585253A (en) * | 2022-03-15 | 2022-06-03 | 杭州测质成科技有限公司 | PCB component installation and rechecking system and method based on image recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111899241B (en) | Quantitative on-line detection method and system for defects of PCB (printed Circuit Board) patches in front of furnace | |
| WO2022088663A1 (en) | Defect detection method and apparatus, electronic device, and storage medium | |
| CN106127746A (en) | Circuit board component missing part detection method and system | |
| CN105510348A (en) | Flaw detection method and device of printed circuit board and detection equipment | |
| CN111914508A (en) | Component detection method and device, electronic equipment and readable storage medium | |
| CN110346704B (en) | Method, device and equipment for determining test file in board test and storage medium | |
| CN111259891B (en) | Method, device, equipment and medium for identifying identity card in natural scene | |
| CN105320953A (en) | License plate recognition method | |
| CN116168351B (en) | Inspection method and device for power equipment | |
| CN115908420A (en) | Method, device and equipment for detecting defects of printed circuit board and storage medium | |
| CN115239683A (en) | Detection method of circuit board, model training method and device and electronic equipment | |
| CN105354816B (en) | A kind of electronic units fix method and device | |
| Mukhopadhyay et al. | PCB inspection in the context of smart manufacturing | |
| CN115775246A (en) | Method for detecting defects of PCB (printed circuit board) components | |
| Singh et al. | Image processing based automatic visual inspection system for PCBs | |
| CN113902740A (en) | Construction method of image blurring degree evaluation model | |
| CN112579810B (en) | Printed circuit board classification method, device, computer equipment and storage medium | |
| CN116993654A (en) | Camera module defect detection method, device, equipment, storage medium and product | |
| CN115829929A (en) | Method, device and equipment for detecting defects of product surface image and storage medium | |
| CN115601345A (en) | Machine vision-based large-size punching plate hole group leakage-proof detection method and device | |
| KR101383827B1 (en) | System and method for automatic extraction of soldering regions in pcb | |
| CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence | |
| CN117408209B (en) | Device extraction method, device, equipment and medium | |
| CN111539933B (en) | Direct-insert element detection method and system | |
| CN115631249B (en) | Camera correction method, device, equipment and storage medium |
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 | ||
| CB02 | Change of applicant information |
Address after: 19 / F, building B, Xingzhi science and Technology Park, 6 Xingzhi Road, Nanjing Economic and Technological Development Zone, Jiangsu Province, 210000 Applicant after: AINNOVATION (NANJING) TECHNOLOGY Co.,Ltd. Address before: Floor 19, building B, Xingzhi science and Technology Park, 6 Xingzhi Road, Jiangning Economic and Technological Development Zone, Nanjing, Jiangsu Province Applicant before: AINNOVATION (NANJING) TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information |