CN117571721B - Method and device for detecting surface defects of circuit board bonding pad and storage medium - Google Patents
Method and device for detecting surface defects of circuit board bonding pad and storage medium Download PDFInfo
- Publication number
- CN117571721B CN117571721B CN202410050277.9A CN202410050277A CN117571721B CN 117571721 B CN117571721 B CN 117571721B CN 202410050277 A CN202410050277 A CN 202410050277A CN 117571721 B CN117571721 B CN 117571721B
- Authority
- CN
- China
- Prior art keywords
- pad
- bonding pad
- circuit board
- image
- information
- 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.)
- Active
Links
- 230000007547 defect Effects 0.000 title claims abstract description 98
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000001514 detection method Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 239000011889 copper foil Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 229910052594 sapphire Inorganic materials 0.000 description 1
- 239000010980 sapphire Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to a method, a device and a storage medium for detecting surface defects of a bonding pad of a circuit board, wherein the method comprises the steps of constructing a bonding pad defect identification model based on a computer vision identification method; acquiring a front image of a circuit board to be tested to obtain an original image to be tested; identifying whether the pad characteristics exist in the original image to be detected or not by using the pad defect identification model; when the pad characteristics are not in the original image to be tested, judging that the circuit board to be tested is unqualified; when the pad characteristics exist, extracting the pad characteristics by using the pad defect identification model to obtain pad characteristic information; calculating the coverage area of each bonding pad by using the bonding pad defect identification model, and correspondingly obtaining coverage area information; and judging whether the circuit board to be tested is qualified or not according to the quantity information, the bonding pad position information and the bonding pad coverage area information. The invention has the advantages of high detection speed and high efficiency, and greatly improves the productivity.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to a method and a device for detecting surface defects of a bonding pad of a circuit board and a storage medium.
Background
The bonding pad is used for welding copper foil of components or wires and the like, ensures the conduction of a circuit, is generally pasted and assembled on the surface, and is widely applied to printed circuit boards and Mini-LED products. Due to the influence of the product technology, the situation of pad defect often occurs, which seriously influences the function and use of the product.
In the prior art, the bonding pad detection mainly depends on manual work or electric performance detection, the two methods lack efficiency, errors caused by different subjective judgment standards can be introduced, and the industrial requirements can not be met simply by manual detection.
Disclosure of Invention
In order to solve the technical problems that in the prior art, the pad detection mainly depends on manual work or electric performance detection, the two methods lack efficiency, errors caused by different subjective judgment standards are introduced, and the like, the invention provides a method and a device for detecting the surface defects of a circuit board pad and a storage medium.
The technical scheme for solving the technical problems is as follows:
a method for detecting surface defects of a bonding pad of a circuit board comprises the following steps:
constructing a bonding pad defect recognition model based on a computer vision recognition method;
acquiring a front image of a circuit board to be tested to obtain an original image to be tested;
identifying whether the pad characteristics exist in the original image to be detected or not by using the pad defect identification model;
when the pad characteristics are not in the original image to be tested, judging that the circuit board to be tested is unqualified;
when the pad characteristics exist, extracting the pad characteristics by using the pad defect identification model to obtain pad characteristic information; wherein the pad characteristic information comprises quantity information and position information;
calculating the coverage area of each bonding pad by using the bonding pad defect identification model, and correspondingly obtaining coverage area information;
and judging whether the circuit board to be tested is qualified or not according to the quantity information, the bonding pad position information and the bonding pad coverage area information.
The beneficial effects of the invention are as follows: the bonding pad of the circuit board is identified by utilizing a computer vision identification method, whether the bonding pad of the circuit board has defects or not is judged according to the characteristics of the bonding pad, the detection speed is high, the efficiency is high, and the productivity is greatly improved; compared with manual detection, the computer vision recognition technology is used for detection, and is high in accuracy and beneficial to improvement of the yield of the circuit board.
On the basis of the technical scheme, the invention can be improved as follows.
Further, the pad defect recognition model is used for recognizing whether the pad features exist in the original image to be detected or not, and the method comprises the following steps:
carrying out gray processing on the original image to be detected to obtain a gray image to be detected;
judging whether a pad gray area exists in the gray scale image to be detected by using the pad defect identification model, if yes, the pad characteristics exist in the original image to be detected, and if not, the pad characteristics do not exist in the original image to be detected.
Further, the pad feature is extracted by using the pad defect recognition model to obtain pad feature information, and the method comprises the following steps:
identifying the number of the pad gray scale areas by using the pad defect identification model to obtain the number information;
and calculating the relative distance and the absolute distance of each pad gray scale region to obtain the position information.
Further, according to the quantity information, the pad position information and the pad coverage area information, judging whether the circuit board to be tested is qualified or not, including the following steps:
when the number value of the bonding pads in the number information is not equal to a preset number value, judging that the circuit board to be tested is unqualified;
when the relative distance value and/or the absolute distance value of the bonding pad in the bonding pad position information exceeds the preset distance range value, judging that the circuit board to be tested is unqualified;
when the coverage area value of the bonding pad exceeds a preset area range value in the bonding pad coverage area information, judging that the circuit board to be tested is unqualified;
and when the number value of the bonding pads is equal to the preset number value, the relative distance value and/or the absolute distance value are within the preset distance range value, and the coverage area value is within the preset area range value, judging that the circuit board to be tested is qualified.
In order to solve the technical problems, the invention also provides a device for detecting the surface defects of the bonding pad of the circuit board, which comprises the following specific technical contents:
the device comprises a model construction module, a data acquisition module and a defect judgment module;
the model construction module is used for constructing a bonding pad defect recognition model based on a computer vision recognition method;
the data acquisition module is used for acquiring a front image of the circuit board to be detected to obtain an original image to be detected;
the defect judging module is used for judging whether the defect exists in the image data,
identifying whether the pad characteristics exist in the original image to be detected or not by using the pad defect identification model;
when the pad characteristics are not in the original image to be tested, judging that the circuit board to be tested is unqualified;
when the pad characteristics exist, extracting the pad characteristics by using the pad defect identification model to obtain pad characteristic information; wherein the pad characteristic information comprises quantity information and position information;
calculating the coverage area of each bonding pad by using the bonding pad defect identification model, and correspondingly obtaining coverage area information;
and judging whether the circuit board to be tested is qualified or not according to the quantity information, the bonding pad position information and the bonding pad coverage area information.
Further, the defect judging module is specifically configured to perform gray processing on the original image to be detected to obtain a gray image to be detected; judging whether a pad gray area exists in the gray scale image to be detected by using the pad defect identification model, if yes, the pad characteristics exist in the original image to be detected, and if not, the pad characteristics do not exist in the original image to be detected.
Further, the defect judging module is further specifically configured to identify the number of the pad gray scale areas by using the pad defect identifying model, so as to obtain the number information; and calculating the relative distance and the absolute distance of each pad gray scale region to obtain the position information.
Further, the defect judging module is further specifically configured to judge that the circuit board to be tested is not qualified when the number value of the bonding pads in the number information is not equal to a preset number value;
when the relative distance value and/or the absolute distance value of the bonding pad in the bonding pad position information exceeds the preset distance range value, judging that the circuit board to be tested is unqualified;
when the coverage area value of the bonding pad exceeds a preset area range value in the bonding pad coverage area information, judging that the circuit board to be tested is unqualified;
and when the number value of the bonding pads is equal to the preset number value, the relative distance value and/or the absolute distance value are within the preset distance range value, and the coverage area value is within the preset area range value, judging that the circuit board to be tested is qualified.
In order to solve the technical problems, the invention also provides a storage medium, which comprises the following specific technical contents:
a storage medium storing a computer program or computer instructions which, when executed by a processor of a computer, implement the steps of a method for detecting surface defects of a circuit board pad as described above.
In order to solve the technical problems, the invention also provides a computer, which comprises the following specific technical contents:
a computer comprising a memory and one or more processors, said memory having executable code stored therein, one or more of said processors implementing the steps of the above-described method for detecting surface defects of a circuit board pad when executing said executable code.
Drawings
FIG. 1 is a block flow diagram of a method for detecting surface defects of a circuit board pad according to an embodiment of the present invention;
fig. 2 is a block diagram of a device for detecting surface defects of a circuit board pad according to an embodiment of the present invention.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
Example 1
As shown in fig. 1, the present embodiment provides a method for detecting surface defects of a circuit board pad, which includes the following steps:
s1, constructing a bonding pad defect recognition model based on a computer vision recognition method;
specifically, the pad defect recognition model is specifically a VGGNet deep convolutional neural network model.
S2, acquiring a front image of the circuit board to be tested to obtain an original image to be tested;
s3, identifying whether the pad features exist in the original image to be detected or not by using the pad defect identification model;
the pad defect recognition model is used for recognizing whether pad features exist in the original image to be detected or not, and the method comprises the following steps:
s301, carrying out gray processing on the original image to be detected to obtain a gray image to be detected;
s302, judging whether a pad gray area exists in the gray scale image to be detected by using the pad defect identification model, if yes, the pad characteristics exist in the original image to be detected, and if not, the pad characteristics do not exist in the original image to be detected.
S4, judging that the circuit board to be tested is unqualified when the pad characteristics are not found in the original image to be tested;
s5, when the bonding pad characteristics exist, extracting the bonding pad characteristics by using the bonding pad defect identification model to obtain bonding pad characteristic information; wherein the pad characteristic information comprises quantity information and position information;
extracting the pad characteristics by using the pad defect identification model to obtain pad characteristic information, wherein the method comprises the following steps of:
s501, recognizing the number of the pad gray scale areas by using the pad defect recognition model to obtain the number information;
specifically, the number of the pad gray scale regions is identified by using the pad defect identification model, and the number information is obtained, and the method comprises the following steps:
carrying out pad theoretical position marking on the gray scale image to be detected according to a preset pad position to obtain a plurality of pad position marking areas; the preset bonding pad positions are theoretical positions of all bonding pads of the circuit board in design; for example, the corners of the circuit board are used as reference points of the preset bonding pad positions or the two sides of the circuit board are respectively used as two coordinate references of a rectangular coordinate system of the preset bonding pad positions.
Carrying out regional image extraction on each bonding pad position mark region by utilizing an image extraction frame to obtain a plurality of segmented images; the shape of the image extraction frame is consistent with that of the bonding pad, and the area of the image extraction frame is larger than or equal to the preset area range value of the bonding pad.
Identifying features of the bonding pad on each segmented image using the bonding pad defect identification model;
and counting the number of all the divided images with the characteristics of the bonding pad to obtain the number information.
S502, calculating the relative distance and the absolute distance of each pad gray scale area to obtain the position information.
Calculating the geometric center of the gray scale region of the bonding pad in each divided image;
calculating the relative position and the absolute position of each bonding pad in the circuit board according to the coordinate position of the geometric center of the bonding pad in each divided image in the divided image; since each divided image is taken from the image extraction frame, the shape and size of each divided image are equal.
S6, calculating the coverage area of each bonding pad by using the bonding pad defect identification model, and correspondingly obtaining coverage area information;
and calculating the coverage area of each bonding pad by using the bonding pad defect identification model, and correspondingly obtaining coverage area information, namely, correspondingly obtaining the coverage area information corresponding to each divided image for the coverage area of the bonding pad in each divided image with the characteristics of the bonding pad.
And S7, judging whether the circuit board to be tested is qualified or not according to the quantity information, the bonding pad position information and the bonding pad coverage area information.
Judging whether the circuit board to be tested is qualified or not according to the quantity information, the bonding pad position information and the bonding pad coverage area information, and comprising the following steps:
s701, judging that the circuit board to be tested is unqualified when the number value of the bonding pads in the number information is not equal to a preset number value;
s702, judging that the circuit board to be tested is unqualified when the relative distance value and/or the absolute distance value of the bonding pad in the bonding pad position information exceeds a preset distance range value;
s703, judging that the circuit board to be tested is unqualified when the coverage area value of the bonding pad exceeds the preset area range value in the bonding pad coverage area information;
and S704, judging that the circuit board to be tested is qualified when the number value of the bonding pads is equal to the preset number value, the relative distance value and/or the absolute distance value are within the preset distance range value and the coverage area value is within the preset area range value.
In some embodiments, the front image of the circuit board to be tested is collected, and the obtained original image to be tested can be obtained by the following method:
the effective detection area of the circuit board of the Mini-LED product is a bonding pad area, and the object stage carrying product moves to the position right below the camera on the premise of fixing the camera. The pad portion of the product is inspected during the movement. And adopting a linear array CCD camera to scan the image of the bonding pad on the Mini-LED product so as to obtain the original image to be detected.
The linear array camera adopts CCD linear array scanning to detect the surface of the product and gathers the information of each row. The optical imaging lens enables the edge information of the product to be imaged on the CCD of the linear array camera. The image acquisition card is used for transmitting signals, and can acquire and transmit the image signals of the linear array camera to the computer. The algorithm then performs image processing and outputs the image processing results, wherein the image is transferred to the algorithm by the software.
The detection precision of the defect of the bonding pad on the Mini-LED product is higher, and a 16K linear array camera is preferably selected according to the precision test requirement. In order to match with the camera and meet the requirement of image acquisition precision, a 3.2/97 optical lens of the Xenon-Sapphire can be selected, and the lens meeting the requirement of working distance is realized.
According to the embodiment of the invention, the bonding pad of the circuit board is identified by utilizing the computer vision identification method, and whether the bonding pad of the circuit board has defects or not is judged according to the characteristics of the bonding pad, so that the detection speed is high, the efficiency is high, and the productivity is greatly improved; compared with manual detection, the computer vision recognition technology is used for detection, and is high in accuracy and beneficial to improvement of the yield of the circuit board. In the detection process of the algorithm on the defects, as the bonding pad has a fixed shape and size, the area of the bonding pad is within the threshold value by setting the threshold value range for the area of the bonding pad, which indicates that the bonding pad exists and has no defect in the product, otherwise, the bonding pad has defect. Therefore, the detection method provided by the embodiment of the invention can efficiently detect the defect condition of the bonding pad, and improves the detection efficiency.
Example 2
Referring to fig. 2, the present embodiment provides a device for detecting a surface defect of a pad of a circuit board according to embodiment 1, which includes a model building module, a data acquisition module, a defect judgment module, and an output display module.
The model construction module is used for constructing a bonding pad defect recognition model based on a computer vision recognition method; the data acquisition module is used for acquiring a front image of the circuit board to be detected to obtain an original image to be detected;
the defect judging module is used for judging whether the defect exists in the image data,
identifying whether the pad characteristics exist in the original image to be detected or not by using the pad defect identification model;
when the pad characteristics are not in the original image to be tested, judging that the circuit board to be tested is unqualified;
when the pad characteristics exist, extracting the pad characteristics by using the pad defect identification model to obtain pad characteristic information; wherein the pad characteristic information comprises quantity information and position information;
calculating the coverage area of each bonding pad by using the bonding pad defect identification model, and correspondingly obtaining coverage area information;
and judging whether the circuit board to be tested is qualified or not according to the quantity information, the bonding pad position information and the bonding pad coverage area information.
The output display module is used for outputting and displaying detection results, wherein the detection results comprise quantity information, the bonding pad position information, the bonding pad coverage area information and judgment results.
Specifically, the defect judging module is specifically configured to perform gray processing on the original image to be detected to obtain a gray image to be detected; judging whether a pad gray area exists in the gray scale image to be detected by using the pad defect identification model, if yes, the pad characteristics exist in the original image to be detected, and if not, the pad characteristics do not exist in the original image to be detected.
Specifically, the defect judging module is further specifically configured to identify the number of the pad gray scale areas by using the pad defect identifying model, so as to obtain the number information; and calculating the relative distance and the absolute distance of each pad gray scale region to obtain the position information.
Specifically, the defect judging module is further specifically configured to judge that the circuit board to be tested is not qualified when the number value of the bonding pads in the number information is not equal to a preset number value;
when the relative distance value and/or the absolute distance value of the bonding pad in the bonding pad position information exceeds the preset distance range value, judging that the circuit board to be tested is unqualified;
when the coverage area value of the bonding pad exceeds a preset area range value in the bonding pad coverage area information, judging that the circuit board to be tested is unqualified;
and when the number value of the bonding pads is equal to the preset number value, the relative distance value and/or the absolute distance value are within the preset distance range value, and the coverage area value is within the preset area range value, judging that the circuit board to be tested is qualified.
Example 3
Based on embodiment 1, this embodiment provides a storage medium storing a computer program or computer instructions which, when executed by a processor of a computer, implement the steps of the pipeline nondestructive inspection method as described in embodiment 1. The storage medium may be an internal storage unit, such as a hard disk or a memory, of any of the data processing enabled devices described in any of the previous embodiments. The storage medium may be any external storage device that has a data processing capability, for example, a plug-in hard disk, a smart memory card, an SD card, a flash memory card, or the like, which is provided on the device. Further, the storage medium may include both internal storage units and external storage devices of any data processing device. The computer readable storage medium is used for storing the computer program and other programs and data required by the arbitrary data processing apparatus, and may also be used for temporarily storing data that has been output or is to be output.
Example 4
Based on embodiment 1, the present implementation provides a computer, including a memory and one or more processors, where the memory stores executable codes, and when the one or more processors execute the executable codes, the steps of the pipeline nondestructive testing method in embodiment 1 are implemented.
The memory may be an internal storage unit of any of the data processing enabled devices described in any of the preceding embodiments, such as a hard disk or a memory. The memory may also be an external storage device of any device having data processing capabilities, such as a plug-in hard disk, a smart memory card, an SD card, a flash memory card, etc. provided on the device. Further, the memory may also include both internal storage units and external storage devices of any data processing capable device. The memory is used for storing the computer program as well as other programs and data required by the arbitrary data processing device, and may also be used for temporarily storing data that has been output or is to be output.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (6)
1. The method for detecting the surface defects of the bonding pad of the circuit board is characterized by comprising the following steps:
constructing a bonding pad defect recognition model based on a computer vision recognition method;
acquiring a front image of a circuit board to be tested to obtain an original image to be tested;
identifying whether the pad characteristics exist in the original image to be detected or not by using the pad defect identification model;
when the pad characteristics are not in the original image to be tested, judging that the circuit board to be tested is unqualified;
when the pad characteristics exist, extracting the pad characteristics by using the pad defect identification model to obtain pad characteristic information; wherein the pad characteristic information comprises quantity information and position information;
calculating the coverage area of each bonding pad by using the bonding pad defect identification model, and correspondingly obtaining coverage area information;
judging whether the circuit board to be tested is qualified or not according to the quantity information, the bonding pad position information and the bonding pad coverage area information;
identifying whether the pad characteristics exist in the original image to be detected by using the pad defect identification model, comprising the following steps:
carrying out gray processing on the original image to be detected to obtain a gray image to be detected;
judging whether a pad gray area exists in the gray scale image to be detected by using the pad defect identification model, if yes, the pad characteristics exist in the original image to be detected, and if not, the pad characteristics do not exist in the original image to be detected;
extracting the pad characteristics by using the pad defect identification model to obtain pad characteristic information, wherein the method comprises the following steps of:
identifying the number of the pad gray scale areas by using the pad defect identification model to obtain the number information;
identifying the number of the pad gray scale areas by using the pad defect identification model to obtain the number information, wherein the method comprises the following steps of:
carrying out pad theoretical position marking on the gray scale image to be detected according to a preset pad position to obtain a plurality of pad position marking areas; the preset bonding pad positions are theoretical positions of all bonding pads of the circuit board in design; specifically, the angle of the circuit board is used as a reference point of a preset bonding pad position or two sides of the circuit board are respectively used as two coordinate references of a rectangular coordinate system of the preset bonding pad position;
carrying out regional image extraction on each bonding pad position mark region by utilizing an image extraction frame to obtain a plurality of segmented images; the shape of the image extraction frame is consistent with that of the bonding pad, and the area of the image extraction frame is larger than or equal to the preset area range value of the bonding pad;
identifying features of the bonding pad on each segmented image using the bonding pad defect identification model;
obtaining the quantity information by counting the quantity of all the divided images with the characteristics of the bonding pad;
calculating the relative distance and the absolute distance of each pad gray scale region to obtain the position information;
calculating the relative distance and the absolute distance of each pad gray scale region to obtain the position information, wherein the method comprises the following steps:
calculating the geometric center of the gray scale region of the bonding pad in each divided image;
and calculating the relative position and the absolute position of each bonding pad in the circuit board according to the coordinate position of the geometric center of the bonding pad in each divided image in the divided image.
2. The method for inspecting surface defects of a circuit board pad according to claim 1, wherein determining whether the circuit board to be inspected is acceptable or not according to the number information, the pad position information, and the pad coverage area information comprises the steps of:
when the number value of the bonding pads in the number information is not equal to a preset number value, judging that the circuit board to be tested is unqualified;
when the relative distance value and/or the absolute distance value of the bonding pad in the bonding pad position information exceeds the preset distance range value, judging that the circuit board to be tested is unqualified;
when the coverage area value of the bonding pad exceeds a preset area range value in the bonding pad coverage area information, judging that the circuit board to be tested is unqualified;
and when the number value of the bonding pads is equal to the preset number value, the relative distance value and/or the absolute distance value are within the preset distance range value, and the coverage area value is within the preset area range value, judging that the circuit board to be tested is qualified.
3. The device for detecting the surface defects of the bonding pad of the circuit board is characterized by comprising a model building module, a data acquisition module and a defect judging module;
the model construction module is used for constructing a bonding pad defect recognition model based on a computer vision recognition method;
the data acquisition module is used for acquiring a front image of the circuit board to be detected to obtain an original image to be detected;
the defect judging module is used for judging whether the defect exists in the image data,
identifying whether the pad characteristics exist in the original image to be detected or not by using the pad defect identification model;
when the pad characteristics are not in the original image to be tested, judging that the circuit board to be tested is unqualified;
when the pad characteristics exist, extracting the pad characteristics by using the pad defect identification model to obtain pad characteristic information; wherein the pad characteristic information comprises quantity information and position information;
calculating the coverage area of each bonding pad by using the bonding pad defect identification model, and correspondingly obtaining coverage area information;
judging whether the circuit board to be tested is qualified or not according to the quantity information, the bonding pad position information and the bonding pad coverage area information;
the defect judging module is specifically used for carrying out gray processing on the original image to be detected to obtain a gray image to be detected; judging whether a pad gray area exists in the gray scale image to be detected by using the pad defect identification model, if yes, the pad characteristics exist in the original image to be detected, and if not, the pad characteristics do not exist in the original image to be detected;
the defect judging module is further specifically configured to identify the number of the pad gray scale regions by using the pad defect identifying model, so as to obtain the number information; calculating the relative distance and the absolute distance of each pad gray scale region to obtain the position information;
carrying out pad theoretical position marking on the gray scale image to be detected according to a preset pad position to obtain a plurality of pad position marking areas; the preset bonding pad positions are theoretical positions of all bonding pads of the circuit board in design; specifically, the angle of the circuit board is used as a reference point of a preset bonding pad position or two sides of the circuit board are respectively used as two coordinate references of a rectangular coordinate system of the preset bonding pad position;
carrying out regional image extraction on each bonding pad position mark region by utilizing an image extraction frame to obtain a plurality of segmented images; the shape of the image extraction frame is consistent with that of the bonding pad, and the area of the image extraction frame is larger than or equal to the preset area range value of the bonding pad;
identifying features of the bonding pad on each segmented image using the bonding pad defect identification model;
obtaining the quantity information by counting the quantity of all the divided images with the characteristics of the bonding pad;
calculating the geometric center of the gray scale region of the bonding pad in each divided image;
and calculating the relative position and the absolute position of each bonding pad in the circuit board according to the coordinate position of the geometric center of the bonding pad in each divided image in the divided image.
4. The device for detecting surface defects of a circuit board bonding pad according to claim 3, wherein the defect judging module is further specifically configured to judge that the circuit board to be tested is not qualified when the number value of the bonding pad in the number information is not equal to a preset number value;
when the relative distance value and/or the absolute distance value of the bonding pad in the bonding pad position information exceeds the preset distance range value, judging that the circuit board to be tested is unqualified;
when the coverage area value of the bonding pad exceeds a preset area range value in the bonding pad coverage area information, judging that the circuit board to be tested is unqualified;
and when the number value of the bonding pads is equal to the preset number value, the relative distance value and/or the absolute distance value are within the preset distance range value, and the coverage area value is within the preset area range value, judging that the circuit board to be tested is qualified.
5. A storage medium storing a computer program or computer instructions which, when executed by a processor of a computer, implement the steps of the circuit board pad surface defect detection method of any one of claims 1 to 2.
6. A computer comprising a memory and one or more processors, the memory having executable code stored therein, the one or more processors, when executing the executable code, performing the steps of the method for detecting a surface defect of a circuit board pad as claimed in any one of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410050277.9A CN117571721B (en) | 2024-01-15 | 2024-01-15 | Method and device for detecting surface defects of circuit board bonding pad and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410050277.9A CN117571721B (en) | 2024-01-15 | 2024-01-15 | Method and device for detecting surface defects of circuit board bonding pad and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117571721A CN117571721A (en) | 2024-02-20 |
| CN117571721B true CN117571721B (en) | 2024-04-05 |
Family
ID=89886478
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410050277.9A Active CN117571721B (en) | 2024-01-15 | 2024-01-15 | Method and device for detecting surface defects of circuit board bonding pad and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117571721B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101793843A (en) * | 2010-03-12 | 2010-08-04 | 华东理工大学 | Connection table based automatic optical detection algorithm of printed circuit board |
| WO2010087433A1 (en) * | 2009-01-31 | 2010-08-05 | 株式会社メガトレード | Apparatus for inspecting through hole |
| CN111798447A (en) * | 2020-07-18 | 2020-10-20 | 太原理工大学 | Deep learning plasticized material defect detection method based on fast RCNN |
| CN112419299A (en) * | 2020-12-04 | 2021-02-26 | 中冶建筑研究总院（深圳）有限公司 | Bolt loss detection method, device, equipment and storage medium |
| CN115575416A (en) * | 2022-09-06 | 2023-01-06 | 广东华恒智能科技有限公司 | Flexible circuit board pad detection method and system |
| CN115861217A (en) * | 2022-11-28 | 2023-03-28 | 华南农业大学 | System and method for detecting defects of circuit board of backlight plate based on vision |
| CN117198914A (en) * | 2023-09-13 | 2023-12-08 | 深圳市立可自动化设备有限公司 | BGA ball-mounting high-definition image acquisition device and image processing method |
| CN117274246A (en) * | 2023-11-17 | 2023-12-22 | 深圳市大族封测科技股份有限公司 | Bonding pad identification method, computer equipment and storage medium |
-
2024
- 2024-01-15 CN CN202410050277.9A patent/CN117571721B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2010087433A1 (en) * | 2009-01-31 | 2010-08-05 | 株式会社メガトレード | Apparatus for inspecting through hole |
| CN102301225A (en) * | 2009-01-31 | 2011-12-28 | 玛机统丽公司 | Apparatus for inspecting through hole |
| CN101793843A (en) * | 2010-03-12 | 2010-08-04 | 华东理工大学 | Connection table based automatic optical detection algorithm of printed circuit board |
| CN111798447A (en) * | 2020-07-18 | 2020-10-20 | 太原理工大学 | Deep learning plasticized material defect detection method based on fast RCNN |
| CN112419299A (en) * | 2020-12-04 | 2021-02-26 | 中冶建筑研究总院（深圳）有限公司 | Bolt loss detection method, device, equipment and storage medium |
| CN115575416A (en) * | 2022-09-06 | 2023-01-06 | 广东华恒智能科技有限公司 | Flexible circuit board pad detection method and system |
| CN115861217A (en) * | 2022-11-28 | 2023-03-28 | 华南农业大学 | System and method for detecting defects of circuit board of backlight plate based on vision |
| CN117198914A (en) * | 2023-09-13 | 2023-12-08 | 深圳市立可自动化设备有限公司 | BGA ball-mounting high-definition image acquisition device and image processing method |
| CN117274246A (en) * | 2023-11-17 | 2023-12-22 | 深圳市大族封测科技股份有限公司 | Bonding pad identification method, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于机器视觉的轻触开关引脚缺陷检测算法研究;蒋建东;陈培余;童一珏;WILLEM Hoogmoed;;浙江工业大学学报;20150225(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117571721A (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113763355A (en) | Defect detection method and device, electronic equipment and storage medium | |
| CN108955901B (en) | Infrared temperature measurement method and system and terminal equipment | |
| CN104634242A (en) | Point adding system and method of probe | |
| CN110260818B (en) | Electronic connector robust detection method based on binocular vision | |
| CN111311671B (en) | Workpiece measuring method and device, electronic equipment and storage medium | |
| CN113971654A (en) | Welding spot detection model training method, welding spot detection method and welding spot detection device | |
| CN115937203A (en) | Visual detection method, device, equipment and medium based on template matching | |
| CN110346704B (en) | Method, device and equipment for determining test file in board test and storage medium | |
| CN116309518A (en) | PCB (printed circuit board) detection method and system based on computer vision | |
| CN115575416A (en) | Flexible circuit board pad detection method and system | |
| CN117471392B (en) | Method and system for detecting probe tip, electronic equipment and storage medium | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN117571721B (en) | Method and device for detecting surface defects of circuit board bonding pad and storage medium | |
| CN116993654A (en) | Camera module defect detection method, device, equipment, storage medium and product | |
| CN108303640B (en) | Line detection method and device | |
| US20220180494A1 (en) | Wire shape measurement device, wire three-dimensional image generation method, and wire shape measurement method | |
| CN108871226B (en) | Method, device and system for measuring snow depth | |
| CN103837098A (en) | Screen test device and method | |
| CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence | |
| CN112415013A (en) | Copper foil defect detection system | |
| CN112730427B (en) | Product surface defect detection method and system based on machine vision | |
| CN110874837A (en) | Automatic defect detection method based on local feature distribution | |
| CN111539933B (en) | Direct-insert element detection method and system | |
| CN114441554B (en) | Detection method | |
| JP5249855B2 (en) | Electronic component terminal position detection method and electronic component terminal position detection system |
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 | ||
| GR01 | Patent grant |