CN116818797A - Automatic detection method and system for PCB bare board based on machine vision - Google Patents
Automatic detection method and system for PCB bare board based on machine vision Download PDFInfo
- Publication number
- CN116818797A CN116818797A CN202310492178.1A CN202310492178A CN116818797A CN 116818797 A CN116818797 A CN 116818797A CN 202310492178 A CN202310492178 A CN 202310492178A CN 116818797 A CN116818797 A CN 116818797A
- Authority
- CN
- China
- Prior art keywords
- equal
- standard
- bare board
- tested
- pcb
- 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 25
- 230000007547 defect Effects 0.000 claims abstract description 17
- 238000004891 communication Methods 0.000 claims description 8
- 238000000034 method Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000007689 inspection Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 4
- 230000008094 contradictory effect Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 150000003071 polychlorinated biphenyls Chemical class 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/956—Inspecting patterns on the surface of objects
- G01N21/95607—Inspecting patterns on the surface of objects using a comparative method
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/956—Inspecting patterns on the surface of objects
- G01N21/95607—Inspecting patterns on the surface of objects using a comparative method
- G01N2021/95615—Inspecting patterns on the surface of objects using a comparative method with stored comparision signal
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/956—Inspecting patterns on the surface of objects
- G01N2021/95638—Inspecting patterns on the surface of objects for PCB's
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30141—Printed circuit board [PCB]
Abstract
The invention provides a PCB bare board automatic detection method and system based on machine vision, which combine the inherent characteristics of the machine vision, skillfully utilize the characteristics of open circuit and short circuit in the PCB bare board, and can realize the judgment of open circuit and short circuit defects only by matching judgment of the number and the shape of binarization patterns, and can further lock the positions of open circuit points and short circuit points on the PCB bare board, thereby providing great convenience for repairing the PCB bare board to be tested, which possibly has defects. In the invention, small disconnection points or short circuit points are actually amplified into connected domains to carry out pairing comparison of quantity and shape, thus greatly reducing the operation amount and being very visual.
Description
Technical Field
The invention relates to the field of industrial vision, in particular to a machine vision-based automatic detection method and system for a PCB bare board.
Background
A PCB bare board, i.e., a printed circuit board bare board, also called a printed wiring board, is an important electronic component, which is a support for electronic components and is a provider of electrical connection of the electronic components. It is called a "printed" circuit board because it is made using electronic printing.
Almost every electronic device, as small as electronic watches, calculators, as large as computers, communication electronic devices, has only electronic components such as integrated circuits, and PCBs are used for electrically interconnecting the individual components.
The wide application of PCBs means that manufacturers need to produce a large number of PCB bare boards, which brings great pressure to the manufacturer's PCB bare board defect detection. On one hand, the bare PCB is produced in a mass, so that the detection quantity is greatly improved; on the other hand, the bare PCB is often filled with a large number of circuit connections, and a defect at a tiny connection part can possibly lead to the repair of the whole bare PCB, so that the complexity of defect detection is often serious.
There may be two tiny and fatal defects of the PCB bare board, namely, open circuit and short circuit. Once there is even a small break or short point on the PCB bare board, it may result in all circuit elements on the PCB bare board not being operational or even being entirely disabled when powered on.
Therefore, accurately finding a potential disconnection point or a short circuit point on a PCB bare board becomes a serious problem in PCB bare board detection, which puts a very high requirement on detection accuracy. However, the mass of the bare PCB product determines that the detection efficiency must be sufficiently improved.
However, it is difficult to meet the requirements of both accuracy and efficiency of the PCB bare board inspection that seem contradictory and must be achieved in the prior art.
Disclosure of Invention
The invention provides a machine vision-based automatic detection system and method for a PCB bare board, which effectively meet the requirements that the accuracy and the efficiency of the detection of the PCB bare board in the prior art seem contradictory and must be achieved.
Specifically, the invention provides a machine vision-based automatic detection method for a PCB bare board, which adopts an image acquisition module to acquire images of the PCB bare board to be detected, thereby forming images to be detected; preprocessing the image to be detected by adopting an image preprocessing module, wherein the image to be detected is subjected to binarization processing, so that a binary pattern to be detected is formed, in the binary pattern to be detected, the background of a PCB bare board to be detected is divided into n mutually independent communication domains B1 and B2 … Bn to be detected by wiring, and a standard binary pattern formed by a defect-free PCB bare board is divided into k mutually independent standard communication domains A1 and A2 … Ak by wiring; if n=k, and each connected domain Bi to be detected in the binary pattern to be detected can find a standard connected domain Aj with the shape identical to that of the connected domain Aj in the standard binary pattern, judging that the bare PCB to be detected has no short circuit or disconnection defect, wherein i is more than or equal to 1 and less than or equal to n, and j is more than or equal to 1 and less than or equal to k; if n < k, directly judging that a circuit breaking point exists in the PCB bare board to be tested, then comparing n connected domains B1 and B2 … Bn with k standard connected domains A1 and A2 … Ak, excluding paired connected domains to be tested and standard connected domains with identical shapes, and once one connected domain Bi to be tested is found to be formed by splicing two standard connected domains Aj and Aj 'in shape, locking the position of the circuit breaking point on a wiring between the standard connected domains Aj and Aj', wherein i is more than or equal to 1 and less than n, j is more than or equal to 1 and less than or equal to k, j 'is more than or equal to 1 and less than or equal to k, and j is not equal to j'; if n > k, directly judging that a short circuit point exists in the PCB bare board to be tested, then comparing n connected domains B1 and B2 … Bn with k standard connected domains A1 and A2 … Ak, removing paired connected domains to be tested and standard connected domains with identical shapes, and once two connected domains Bi and Bi 'to be tested are found to be spliced into a standard connected domain Aj in shape, locking the position of the short circuit point to be in the standard connected domain Aj, wherein i is more than or equal to 1 and less than or equal to n, i' is less than or equal to 1 and less than or equal to j is less than or equal to k.
Preferably, the image acquisition module comprises an image acquisition card, a camera and a lens.
Preferably, the camera adopts a CCD 1/2 inch 43 ten thousand pixel color camera, and the lens adopts a high-definition 0.7-4.5X zoom lens, and the display resolution is 0.001 millimeter.
The invention also provides a machine vision-based automatic detection system for the PCB bare board, which is used for executing the machine vision-based automatic detection method for the PCB bare board.
The invention combines the inherent characteristics of machine vision, skillfully utilizes the characteristics of open circuit and short circuit in the PCB bare board, can realize the judgment of open circuit and short circuit defects only by matching and judging the number and the shape of the binarization patterns, can further lock the positions of the open circuit points and the short circuit points on the PCB bare board, and provides great convenience for repairing the PCB bare board to be tested, which possibly has defects. In the invention, small disconnection points or short circuit points are actually amplified into connected domains to carry out pairing comparison of quantity and shape, thus greatly reducing the operation amount and being very visual. Compared with the prior art that the circuit breaking point and the short circuit point must be detected point by point along the wiring of the PCB bare board to be detected, the invention greatly reduces the complicated degree of work and effectively improves the detection accuracy, thereby effectively meeting the requirements that the accuracy and the efficiency of the PCB bare board detection seem contradictory and must be achieved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following discussion will discuss the embodiments or the drawings required in the description of the prior art, and it is obvious that the technical solutions described in connection with the drawings are only some embodiments of the present invention, and that other embodiments and drawings thereof can be obtained according to the embodiments shown in the drawings without inventive effort for a person skilled in the art.
Fig. 1 shows a flow chart of a machine vision based automatic detection method for a PCB bare board according to the present invention;
fig. 2 is an exemplary diagram illustrating a defect-free PCB bare board to be tested under the method provided by the present invention;
fig. 3 is an exemplary diagram illustrating a circuit breaking point of a PCB bare board under test under the method and system provided by the present invention;
fig. 4 is an exemplary view illustrating a comparison of a binarization pattern with a standard binarization pattern, which is one-by-one connected domain, when a circuit breaking point occurs to a PCB bare board to be tested under the method and system provided by the present invention;
fig. 5 is a diagram schematically illustrating an example of a short circuit point occurring on a PCB bare board to be tested under the method and system provided by the present invention;
fig. 6 is an exemplary view illustrating a comparison of a binarization pattern with a standard binarization pattern connected to each other in a region when a short circuit point occurs in a PCB bare board to be tested under the method and system provided by the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made in detail with reference to the accompanying drawings, wherein it is apparent that the embodiments described are only some, but not all embodiments of the present invention. All other embodiments, which can be made by a person of ordinary skill in the art without the need for inventive faculty, are within the scope of the invention, based on the embodiments described in the present invention.
The invention provides a machine vision-based automatic detection method and system for a bare PCB. In summary, the invention forms a binary image after imaging the PCB bare board to be tested, then compares the binary image with the standard image one by one in the communication domain, especially compares the binary image with the standard image in number and shape, and determines whether the potential disconnection point and the potential short circuit point of the PCB bare board exist or not and whether the potential disconnection point and the potential short circuit point are located if the potential disconnection point and the potential short circuit point are located.
Fig. 1 shows a flowchart of a machine vision-based automatic inspection method for a bare PCB according to the present invention. As shown in fig. 1, the present invention firstly adopts an image acquisition module to acquire images of a PCB bare board to be tested, thereby forming an image to be tested. The image acquisition module can comprise an image acquisition card, a camera and a lens. The camera used here is, for example, a CCD 1/2 inch 43 ten thousand pixel color camera, and the lens is a high definition 0.7-4.5X zoom magnification lens, with a display resolution of 0.001 mm.
Then, the image preprocessing module will preprocess the image to be detected. In particular, the image to be measured is subjected to binarization processing, so that a binarized pattern to be measured is formed.
Binarization of an image, namely setting the gray value of a pixel point on the image to 0 or 255, namely, displaying the whole image with obvious visual effects of only black and white.
The PCB bare board is filled with various traces, and the traces and the background of the PCB bare board are collected together by the image to form a part of the image to be measured, thereby reflecting that in the binary pattern to be measured, the trace area forms a black effect area, and the background of the PCB bare board forms a white effect area (or vice versa, the background of the PCB bare board forms a black effect area, and the trace area forms a white effect area), as shown in fig. 2. Fig. 2 shows an example of a standard binarized pattern of a PCB bare board.
If the PCB bare board to be tested is free of defects, the binary pattern to be tested is identical to the standard binary pattern, and the background (white area display) of the PCB bare board is divided into a plurality of mutually independent communication domains by the wiring (black area display). For example, in the standard binarization pattern shown in fig. 2, the background of the PCB bare board is divided into four mutually independent connected domains A1, A2, A3, A4 by the wirings.
In other words, in the standard binary pattern, the standard PCB bare board background can be divided into k standard connected domains A1 and A2 … Ak, which are independent of each other, by the trace.
Of course, the to-be-measured binarization pattern of the to-be-measured PCB bare board can be divided into n mutually independent to-be-measured communication domains of B1, B2 … Bn by the wiring.
If the PCB bare board to be tested is free of defects, the binary pattern to be tested is identical to the standard binary pattern, k mutually independent standard connected domains A1 and A2 … Ak in the standard binary pattern are equal in number to n mutually independent connected domains B1 and B2 … Bn in the binary pattern to be tested, namely n=k, and each connected domain Bi (i is greater than or equal to 1 and less than or equal to n) to be tested in the binary pattern to be tested can be found in the standard binary pattern to find a standard connected domain Aj (1 is greater than or equal to j and less than or equal to k) with the shape identical to the standard connected domain Aj in the standard binary pattern.
In other words, if the standard communicating region and the communicating region to be tested are determined to be completely equal in number, and each communicating region to be tested can find the standard communicating region with the same shape, then the PCB bare board to be tested can be judged to be defect-free.
For example, in the case of fig. 2, the number of the standard communicating domains is four, and the shape of the communicating domain B1 to be measured is the same as that of the standard communicating domain A1, the shape of the communicating domain B2 to be measured is the same as that of the standard communicating domain A2, the shape of the communicating domain B3 to be measured is the same as that of the standard communicating domain A3, and the shape of the communicating domain B4 to be measured is the same as that of the standard communicating domain A4, so that it can be determined that the PCB to be measured shown in fig. 2 is defect-free.
The ideal situation that the bare PCB to be tested is free of defects is discussed above, and the judgment situation that the bare PCB to be tested is once the disconnection point or the short circuit point occurs will be described in detail below.
Once the wiring on the PCB bare board to be tested has a disconnection point, the wiring position on the image to be tested will also have a disconnection point, and therefore, the wiring area on the binarized pattern to be tested will also have a disconnection point. Based on fig. 2, for example, a break point occurs in the routing area between the connected areas B1 and B4 to be tested, as shown in fig. 3.
As shown in fig. 3, since the break point occurs in the routing area between the original connected-to-be-measured domains B1 and B4, the break point will present the background color of the PCB bare board, and thus, in the binary pattern to be measured, the original connected-to-be-measured domains B1 and B4 will be integrated together and converged into one integral connected-to-be-measured domain, which is denoted as B1 in fig. 3.
Fig. 4 illustrates an exemplary comparison of a connected domain to be measured with a standard connected domain in the case that a disconnection point occurs according to the technical idea of the present invention. As shown in fig. 4, a disconnection point appears between the original communicating domains B1 and B4, so that the current communicating domain B1 to be measured is converged, in this case, compared with the standard communicating domain, the current communicating domain B2 to be measured is identical in shape to the standard communicating domain A2, the current communicating domain B3 to be measured is identical in shape to the standard communicating domain A3, however, the current communicating domain B1 to be measured cannot find the corresponding identical shape in the standard communicating domains A1-A4, but it can be found that the current communicating domain B1 to be measured can be actually spliced by the standard communicating domains A1 and A4.
As can be seen from the above, when the circuit breaking point occurs on the trace of the PCB bare board, the number of the connected domains to be tested is first reduced, which is smaller than the number of the standard connected domains, for example, as shown in fig. 3 and 4, the number of the standard connected domains A1-A4 is 4, but the number of the connected domains B1-B3 to be tested is only 3. Therefore, once the number of connected domains to be tested is found to be smaller than the number of standard connected domains (i.e., n < k above), it can be rapidly determined that a circuit breaking point exists on the PCB bare board to be tested.
Secondly, after the standard communicating domain and the communicating domain to be detected (for example, A2 and B2, A3 and B3 in fig. 4) with the same shape are eliminated, once the communicating domain to be detected B1 is found to be spliced by the standard communicating domains A1 and A4 in shape, the circuit breaking point on the PCB bare board to be detected can be rapidly locked to appear on the wiring between the standard communicating domains A1 and A4.
The judgment of the break circuit point of the PCB bare board to be tested is explained above. The following continues to describe the determination of the short circuit point in the PCB bare board to be tested.
The open circuit is that the original place of the wiring is disconnected, and the short circuit is that the original place of the wiring is connected.
Still taking fig. 2 as a basic illustration. In the PCB bare board to be tested, for example, a connection between the upper and lower wires of fig. 2 occurs where the connection is not formed, so that fig. 5 is formed. Fig. 5 shows an example of the occurrence of a short defect in a PCB bare board.
As shown in fig. 5, an extra trace is formed by connecting the non-connection parts of the PCB bare board to be tested, so that the PCB bare board background is divided into five connected domains B1, B2, B3, B4, and B5 on the binary pattern to be tested.
Fig. 6 illustrates an exemplary comparison of a connected domain to be measured with a standard connected domain in the case that a short-circuit point occurs according to the technical idea of the present invention. As shown in fig. 5, a circuit breaking point appears between the original connected domains B2 to be tested, so that the connected domains B2 and B5 to be tested are split on the binary pattern to be tested, in this case, compared with the standard connected domains, the shapes of the current connected domains B1, B3 and B4 to be tested are completely the same as those of the standard connected domains A1, A3 and A4, however, the corresponding same shapes of the current connected domains B2 and B5 to be tested cannot be found in the standard connected domains A1-A4, but it can be found that the current connected domains B2 and B5 to be tested can be spliced into the standard connected domain A2 in practice.
As can be seen from the above, the occurrence of the short-circuit point on the trace of the PCB bare board means that the number of the connected domains to be tested is larger, which is larger than the number of the standard connected domains, for example, as shown in fig. 5 and 6, the number of the standard connected domains A1-A4 is 4, but the number of the connected domains B1-B5 to be tested is 5. Therefore, once the number of the connected domains to be detected is found to be greater than the number of the standard connected domains (i.e., n > k above), it can be rapidly determined that a short circuit point exists on the PCB bare board to be detected.
Secondly, after excluding the pair of standard connected domains and connected domains to be tested (for example, A1 and B1, A3 and B3, A4 and B4 in fig. 6), once the connected domains to be tested B2 and B5 are found to be spliced into the standard connected domain A2 in shape, the short circuit point on the PCB bare board to be tested can be quickly locked to appear on the standard connected domain A2.
As described above, according to the characteristics of the breaking points and the short-circuit points in the PCB bare board to be tested on the binarized pattern, a complete set of automatic detection method for the PCB bare board based on machine vision can be generalized, see fig. 1.
As shown in fig. 1, an image acquisition module is first used to acquire an image of a PCB bare board to be tested, thereby forming an image to be tested.
And then, preprocessing the image to be detected, in particular, binarizing the image to be detected by adopting an image preprocessing module, thereby forming a binarized pattern to be detected, wherein the background of the PCB bare board to be detected in the binarized pattern to be detected is divided into n mutually independent communicating domains B1 and B2 … Bn to be detected by wiring.
For comparison, the standard binary pattern formed by the defect-free PCB bare board is also divided into k standard communication domains A1 and A2 … Ak which are mutually independent by the wiring of the standard binary pattern.
If n=k, and each connected domain Bi to be detected (wherein i is greater than or equal to 1 and less than or equal to n) in the binary pattern to be detected can find a standard connected domain Aj (j is greater than or equal to 1 and less than or equal to k) with the shape identical to that of the standard connected domain Aj in the standard binary pattern, then judging that the PCB bare board to be detected has no short circuit or disconnection defect.
If n < k, directly judging that a circuit breaking point exists in the PCB bare board to be tested, then comparing n connected domains B1 and B2 … Bn with k standard connected domains A1 and A2 … Ak, excluding paired connected domains to be tested and standard connected domains with identical shapes, and once one connected domain Bi to be tested (wherein 1 is less than or equal to i is less than or equal to n) is found, being formed by splicing two standard connected domains Aj and Aj '(wherein 1 is less than or equal to k and 1 is less than or equal to j' is less than or equal to k and j is not equal to j ') in shape, locking the position of the circuit breaking point on a wiring between the standard connected domains Aj and Aj'.
If n > k, directly judging that a short-circuit point exists in the PCB bare board to be tested, then comparing n connected domains B1 and B2 … Bn with k standard connected domains A1 and A2 … Ak, excluding paired connected domains to be tested and standard connected domains with identical shapes, and once two connected domains Bi and Bi ' to be tested are found (wherein, 1 is less than or equal to i is less than or equal to n,1 is less than or equal to i ' is less than or equal to n, and i is not equal to i ') can be spliced into a standard connected domain Aj in shape (wherein, 1 is less than or equal to j is less than or equal to k), and then locking the position of the short-circuit point is within the standard connected domain Aj.
In summary, the invention combines the inherent characteristics of machine vision, skillfully utilizes the characteristics of open circuit and short circuit in the PCB bare board, and can not only realize the judgment of open circuit and short circuit defects only by the matching judgment of the number and the shape of the binarization patterns, but also further lock the positions of the open circuit points and the short circuit points on the PCB bare board, thereby providing great convenience for the repair of the PCB bare board to be tested, which may have defects. In the invention, small disconnection points or short circuit points are actually amplified into connected domains to carry out pairing comparison of quantity and shape, thus greatly reducing the operation amount and being very visual. Compared with the prior art that the circuit breaking point and the short circuit point must be detected point by point along the wiring of the PCB bare board to be detected, the invention greatly reduces the complicated degree of work and effectively improves the detection accuracy, thereby effectively meeting the requirements that the accuracy and the efficiency of the PCB bare board detection seem contradictory and must be achieved.
The foregoing description of the exemplary embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any modifications, equivalents, and variations which fall within the spirit and scope of the invention are intended to be included in the scope of the invention.
Claims (4)
1. A PCB bare board automatic detection method based on machine vision is characterized in that,
adopting an image acquisition module to acquire images of the PCB bare board to be tested, thereby forming an image to be tested;
preprocessing the image to be detected by adopting an image preprocessing module, wherein the image to be detected is subjected to binarization processing, thereby forming a binarization pattern to be detected, in the binarization pattern to be detected, the background of the PCB bare board to be detected is divided into n mutually independent communicating domains B1, B2 … Bn to be detected by wiring,
the standard binarization pattern formed by the nondefective PCB bare board is divided into k standard communication domains A1, A2 … Ak which are mutually independent by the wiring;
if n=k, and each connected domain Bi to be detected in the binary pattern to be detected can find a standard connected domain Aj with the shape identical to that of the connected domain Aj in the standard binary pattern, judging that the bare PCB to be detected has no short circuit or disconnection defect, wherein i is more than or equal to 1 and less than or equal to n, and j is more than or equal to 1 and less than or equal to k;
if n < k, directly judging that a circuit breaking point exists in the PCB bare board to be tested, then comparing n connected domains B1 and B2 … Bn with k standard connected domains A1 and A2 … Ak, excluding paired connected domains to be tested and standard connected domains with identical shapes, and once one connected domain Bi to be tested is found to be formed by splicing two standard connected domains Aj and Aj 'in shape, locking the position of the circuit breaking point on a wiring between the standard connected domains Aj and Aj', wherein i is more than or equal to 1 and less than n, j is more than or equal to 1 and less than or equal to k, j 'is more than or equal to 1 and less than or equal to k, and j is not equal to j';
if n > k, directly judging that a short circuit point exists in the PCB bare board to be tested, then comparing n connected domains B1 and B2 … Bn with k standard connected domains A1 and A2 … Ak, removing paired connected domains to be tested and standard connected domains with identical shapes, and once two connected domains Bi and Bi 'to be tested are found to be spliced into a standard connected domain Aj in shape, locking the position of the short circuit point to be in the standard connected domain Aj, wherein i is more than or equal to 1 and less than or equal to n, i' is less than or equal to 1 and less than or equal to j is less than or equal to k.
2. The machine vision-based automatic detection method for a bare PCB (printed Circuit Board) according to claim 1, wherein the image acquisition module comprises an image acquisition card, a camera and a lens.
3. The automatic detection method of the PCB bare board based on machine vision according to claim 2, wherein the camera adopts a CCD 1/2 inch 43 ten thousand pixel color camera, and the lens adopts a high-definition 0.7-4.5X zoom lens, and the display resolution is 0.001 mm.
4. A machine vision-based automatic inspection system for a PCB bare board for performing the machine vision-based automatic inspection method for a PCB bare board according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310492178.1A CN116818797A (en) | 2023-05-04 | 2023-05-04 | Automatic detection method and system for PCB bare board based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310492178.1A CN116818797A (en) | 2023-05-04 | 2023-05-04 | Automatic detection method and system for PCB bare board based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116818797A true CN116818797A (en) | 2023-09-29 |
Family
ID=88124844
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310492178.1A Pending CN116818797A (en) | 2023-05-04 | 2023-05-04 | Automatic detection method and system for PCB bare board based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116818797A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104297254A (en) * | 2014-10-08 | 2015-01-21 | 华南理工大学 | Mixing-method-based method and system applied to defect detection of printed circuit board |
| CN105092598A (en) * | 2015-09-28 | 2015-11-25 | 深圳大学 | Method and system for rapidly recognizing defects of big-breadth PCB on basis of connected areas |
| CN109100370A (en) * | 2018-06-26 | 2018-12-28 | 武汉科技大学 | A kind of pcb board defect inspection method based on sciagraphy and connected domain analysis |
| CN112116591A (en) * | 2020-11-18 | 2020-12-22 | 惠州高视科技有限公司 | Method for detecting open circuit of etching circuit |
-
2023
- 2023-05-04 CN CN202310492178.1A patent/CN116818797A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104297254A (en) * | 2014-10-08 | 2015-01-21 | 华南理工大学 | Mixing-method-based method and system applied to defect detection of printed circuit board |
| CN105092598A (en) * | 2015-09-28 | 2015-11-25 | 深圳大学 | Method and system for rapidly recognizing defects of big-breadth PCB on basis of connected areas |
| CN109100370A (en) * | 2018-06-26 | 2018-12-28 | 武汉科技大学 | A kind of pcb board defect inspection method based on sciagraphy and connected domain analysis |
| CN112116591A (en) * | 2020-11-18 | 2020-12-22 | 惠州高视科技有限公司 | Method for detecting open circuit of etching circuit |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chauhan et al. | Detection of bare PCB defects by image subtraction method using machine vision | |
| US6937004B2 (en) | Test mark and electronic device incorporating the same | |
| US20060018534A1 (en) | Technique for detecting a defect of an object by area segmentation of a color image of the object | |
| CN103063677A (en) | Multifunctional printed circuit board (PCB) test system | |
| CN112394071B (en) | Substrate defect inspection apparatus and method | |
| EP0466013A2 (en) | Method of and device for inspecting pattern of printed circuit board | |
| KR940006220B1 (en) | Method of and apparatus for inspectiong pattern on printed circuit board | |
| KR20170024650A (en) | Test socket for camera module | |
| Leta et al. | Computer vision system for printed circuit board inspection | |
| CN114529500A (en) | Defect inspection method for display substrate | |
| CN116818797A (en) | Automatic detection method and system for PCB bare board based on machine vision | |
| JP2018085486A (en) | Optical inspection method | |
| KR20130008750A (en) | Inspection method | |
| JP2745778B2 (en) | Wiring pattern inspection equipment | |
| JP2007003494A (en) | Inspection method of wiring pattern, and its device | |
| Leta et al. | Computational system to detect defects in mounted and bare PCB based on connectivity and image correlation | |
| JP2015059875A (en) | Device for generating inspection result display data, inspection result display device, substrate inspection system, and method for generating inspection result display data | |
| JP2007309703A (en) | Inspection method of pixel | |
| CN100456024C (en) | System and method for preventing mistakes in optical inspection | |
| KR102657751B1 (en) | Board inspection method using a learning model | |
| RU2811335C1 (en) | Method and device for monitoring contacts of connector sockets installed on printed circuit board | |
| WO2016093597A9 (en) | Method for inspecting terminal of component formed on substrate and substrate inspection apparatus | |
| Vaidya | Automatic Optical Inspection-Based PCB Fault Detection Using Image Processing | |
| JP2002368412A (en) | Method for inspecting printed wiring board | |
| KR20220147807A (en) | Method for inspection of board |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240103 Address after: 518000, No. 101, Tianyang 5th Road, Dongfang Community, Songgang Street, Bao'an District, Shenzhen City, Guangdong Province Applicant after: Dezhong (Shenzhen) laser Intelligent Technology Co.,Ltd. Address before: 618000 intersection of Bohai Road and Helanshan Road, Jingyang District, Deyang City, Sichuan Province Applicant before: Sichuan Dezhong Intelligent Technology Co.,Ltd. |