CN115482194A - Method and system for detecting AOI (automated optical inspection) defects of special-shaped elements of PCB (printed circuit board) - Google Patents

Method and system for detecting AOI (automated optical inspection) defects of special-shaped elements of PCB (printed circuit board) Download PDF

Info

Publication number
CN115482194A
CN115482194A CN202210721181.1A CN202210721181A CN115482194A CN 115482194 A CN115482194 A CN 115482194A CN 202210721181 A CN202210721181 A CN 202210721181A CN 115482194 A CN115482194 A CN 115482194A
Authority
CN
China
Prior art keywords
pcb
image
detection
judging whether
qualified
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
Application number
CN202210721181.1A
Other languages
Chinese (zh)
Inventor
张法全
陈庭威
孙成路
周利兵
沈满德
孔德进
吴子豪
周扬
汪存超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan Textile University
Original Assignee
Wuhan Textile University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhan Textile University filed Critical Wuhan Textile University
Priority to CN202210721181.1A priority Critical patent/CN115482194A/en
Publication of CN115482194A publication Critical patent/CN115482194A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • 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]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Quality & Reliability (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The invention discloses a method and a system for detecting the AOI defect of a special-shaped element of a PCB (printed Circuit Board), wherein the method comprises the following steps: s1, shooting an image of a PCB to be tested; s2, respectively comparing the shot images of all parts in the to-be-detected PCB image with pre-stored standard template images of all parts, detecting whether all parts of the to-be-detected PCB are qualified or not according to the comparison result, and sequentially judging whether the capacitors, the connectors, the crystal oscillators, the pin headers and the terminal rows of the PCB are qualified or not in the detection process; s3, according to the photographed board surface image of the PCB, performing defect detection on the board surface of the PCB, and judging whether the board surface of the PCB is qualified or not; and S4, if the PCB is qualified in the detection in the step S2 and the detection in the step S3, sending the PCB to a qualified area, otherwise, feeding back the type of the PCB which is unqualified, and sending the PCB to an unqualified area.

Description

Method and system for detecting AOI (automated optical inspection) defects of special-shaped elements of PCB (printed circuit board)
Technical Field
The invention relates to the field of AOI detection, in particular to a method and a system for detecting AOI defects of special-shaped elements of a PCB.
Background
The defect detection of the PCB is an important step in the production process of the PCB, and the traditional manual detection method is difficult to meet the requirement. At present, a part of defects of special-shaped elements of the PCB are detected by adopting a digital image processing mode to replace manual work. In the method, image acquisition is mainly performed through the side surfaces of the acquisition capacitor, the connector, the pin header, the crystal oscillator, the connector row and the like, and related integrity detection is performed on the acquired elements through an image processing technology, but a clamping device required by the method is complex, and image processing on the two-dimensional image is complex.
The method for detecting the defects of a part of special-shaped elements of the PCB is an on-line instrument detection method, and the method is used for detecting open circuits and short circuits of the welding of the circuit board and the function detection of fault elements and components through a simulation test experiment and an electrical performance test. However, if the density of the components arranged on the electric board is too high, the arrangement of the test points has certain difficulty. In addition, the method generally needs a test fixture, but the fixture has the defects of high manufacturing cost, large using difficulty, more programming and debugging time and the like.
Disclosure of Invention
In order to solve the problems in the background art, the present invention provides a method for detecting AOI defects of a profiled element of a PCB.
In order to achieve the purpose, the invention adopts the technical scheme that: a method for detecting AOI defects of special-shaped elements of a PCB comprises the following steps:
s1, shooting an image of a PCB to be tested;
s2, respectively comparing the shot images of all parts in the to-be-detected PCB image with pre-stored standard template images of all parts, detecting whether all parts of the to-be-detected PCB are qualified or not according to the comparison result, and sequentially judging whether the capacitors, the connectors, the crystal oscillators, the pin headers and the terminal rows of the PCB are qualified or not in the detection process;
s3, according to the photographed board surface image of the PCB, performing defect detection on the board surface of the PCB, and judging whether the board surface of the PCB is qualified or not;
and S4, if the PCB is qualified in the detection in the step S2 and the detection in the step S3, sending the PCB to a qualified area, otherwise, feeding back the type of the PCB which is unqualified, and sending the PCB to an unqualified area.
In some embodiments, before step S2, the method further comprises the steps of: and (3) performing MARK point positioning on the PCB to be detected according to the image of the PCB to be detected, entering the step S2 if the positioning is successful, and directly stopping the detection of the PCB if the positioning is failed.
In some embodiments, the step of determining whether the capacitor is qualified in step S2 specifically includes:
comparing the capacitance image in the shot PCB image with a pre-stored standard capacitance template image through a template matching algorithm;
judging whether the capacitor is missing or not according to the comparison result, if so, storing capacitor missing information and finishing the capacitor detection;
if the capacitance is not lost, judging whether the angle of the capacitance is the same as the original angle of the standard template capacitance, if so, directly finishing capacitance detection, if not, storing the information that the polarity of the capacitance is incorrect, and finishing the capacitance detection.
In some embodiments, the step of determining whether the connector is qualified in step S2 specifically includes:
firstly, converting an RGB color space to an HSV color space of a PCB image to be detected to obtain the PCB image under a V channel, finding a connector image under the V channel, and then comparing the connector image obtained after processing with a pre-stored standard connector template image through a region gray value matching algorithm;
judging whether the connector is missing or not according to the comparison result, if so, saving the missing information of the connector and finishing the detection of the connector;
and if the connector is not lost, performing gray value scaling on the connector image to highlight the characteristic point area of the connector, averagely dividing the characteristic point area into an upper area and a lower area, judging whether the difference between the gray average value of the upper area and the gray average value of the lower area is greater than 0, if so, directly finishing connector detection, otherwise, storing information that the polarity of the connector is incorrect, and finishing the connector detection.
In some embodiments, the step of determining whether the crystal oscillator is qualified in step S2 specifically includes:
finding a crystal oscillator image under a V channel, and then comparing the crystal oscillator image obtained after processing with a pre-stored standard crystal oscillator template image through a regional gray value matching algorithm;
and judging whether the crystal oscillator is lost or not according to the comparison result, directly finishing the step of detecting the crystal oscillator if the crystal oscillator is not lost, and storing the crystal oscillator missing information and finishing the step of detecting the crystal oscillator if the crystal oscillator is lost.
In some embodiments, in step S2, the step of determining whether the pin arrangement is qualified specifically includes:
finding a pin header image under a V channel, and then comparing the processed pin header image with a pre-stored standard pin header template image through a regional gray value matching algorithm;
and judging whether the pin header is missing or not according to the comparison result, if not, directly ending the pin header detection step, and if so, saving pin header missing information and then ending the pin header detection step.
In some embodiments, the step of determining whether the terminal block is qualified in step S2 specifically includes:
firstly, detecting a large terminal block, finding a large terminal block image under a V channel, and then comparing the processed large terminal block image with a pre-stored standard large terminal block template image through a regional gray value matching algorithm;
judging whether the large terminal strip is missing or not according to the comparison result, if so, saving the missing information of the large terminal strip and then finishing the detection of the large terminal strip;
if the large terminal strip is not missing, performing gray value scaling on the image of the large terminal strip area so as to highlight the characteristic point area of the large terminal strip, comparing the gray value of the characteristic point area with the gray value of the characteristic point area of the standard large terminal strip template so as to judge whether the polarity of the large terminal strip is correct or not, if so, directly finishing the detection of the large terminal strip, otherwise, storing the information that the polarity of the large terminal strip is incorrect, and then finishing the detection of the large terminal strip;
then detecting the small terminal strip, finding a small terminal strip image under a V channel, and then comparing the processed small terminal strip image with a pre-stored standard small terminal strip template image through a regional gray value matching algorithm;
judging whether the small terminal strip is missing or not according to the comparison result, if so, saving missing information of the small terminal strip and then finishing the detection of the small terminal strip;
if the small terminal row is not missing, performing gray scale value scaling on the small terminal row area image so as to highlight the characteristic point area of the small terminal row, performing angle comparison on the characteristic point area and the characteristic point area of the standard small terminal row template so as to judge whether the polarity of the small terminal row is correct or not, directly finishing the detection of the small terminal row if the polarity of the small terminal row is correct, otherwise, storing the information that the polarity of the small terminal row is incorrect, and finishing the detection of the small terminal row.
In some embodiments, the step S3 specifically includes the following steps:
according to the shot board surface image of the PCB, firstly, judging whether the board surface of the PCB has a scratch or not by utilizing a Canny edge gradient detection algorithm, a template matching algorithm and Blob analysis, and if so, storing corresponding unqualified information;
and then, carrying out binarization and scaling processing on the board surface image of the PCB so as to judge whether blackening exists on the board surface of the PCB, and if the blackening exists, storing corresponding unqualified information.
The invention provides a special-shaped element AOI defect detection system of the PCB, which adopts the special-shaped element AOI defect detection method of the PCB to complete the special-shaped element AOI defect detection of the PCB and comprises an industrial personal computer, a motion control system and an image acquisition system, wherein the motion control system and the image acquisition system are electrically connected with the industrial personal computer;
the motion control system is used for controlling the automatic transmission of the PCB to be tested;
the image acquisition system is used for acquiring an image of the PCB to be detected and transmitting the image to the industrial personal computer.
In some embodiments, the image acquisition system comprises a camera and a light source, and the light source surrounds a lens of the camera from all sides;
the motion control system comprises a transmission rail, a photographing area used for isolating external illumination is arranged on the transmission rail, a camera and a light source of the image acquisition system are both arranged in the middle of the upper portion inside the photographing area, and a lens of the camera faces the middle of the transmission rail.
Compared with the prior art, the invention has the beneficial effects that:
compared with the traditional manual detection mode and other mechanical detection modes, the method and the system for detecting the AOI defects of the special-shaped elements of the PCB greatly reduce the workload of workers, improve the economic benefit of enterprises, can adapt to the detection of various special-shaped elements, have flexible and adjustable detection precision, and can adapt to different application scenes.
Drawings
FIG. 1 is a schematic flow chart illustrating the steps of the method for detecting AOI defects of profiled elements of a PCB according to the present invention;
FIG. 2 is a schematic diagram of an AOI defect detection system for a profiled element of a PCB provided by the present invention.
Detailed Description
In order to make the technical means, the creation features, the achievement purposes and the effects of the invention easy to understand, the following description further explains how the invention is implemented by combining the attached drawings and the detailed implementation modes.
Referring to fig. 1, the invention provides a method for detecting AOI defects of a profiled element of a PCB, comprising the following steps:
s1, shooting an image of a PCB to be tested;
s2, respectively comparing the shot images of all parts in the to-be-detected PCB image with pre-stored standard template images of all parts, detecting whether all parts of the to-be-detected PCB are qualified or not according to the comparison result, and sequentially judging whether the capacitors, the connectors, the crystal oscillators, the pin headers and the terminal rows of the PCB are qualified or not in the detection process;
s3, according to the shot board surface image of the PCB, carrying out defect detection on the board surface of the PCB, and judging whether the board surface of the PCB is qualified or not;
and S4, if the PCB is qualified in the detection in the step S2 and the step S3, sending the PCB to a qualified area, otherwise, feeding back the unqualified type of the PCB, and sending the PCB to an unqualified area.
Further, before step S2, the method further includes the steps of: and (3) performing MARK point positioning on the PCB to be detected according to the image of the PCB to be detected, entering the step S2 if the positioning is successful, and directly terminating the detection of the PCB if the positioning is failed, and subsequently performing manual detection.
After the MARK point positioning is successfully carried out on the image of the PCB to be detected, the positions of different components in the image can be determined according to the MARK point, so that the subsequent detection is facilitated.
Preferably, in step S2, the step of determining whether the capacitor is qualified specifically includes:
comparing the capacitance image in the shot PCB image with a pre-stored standard capacitance template image through a template matching algorithm;
judging whether the capacitor is missing or not according to the comparison result, if so, storing the missing information of the capacitor and finishing the detection of the capacitor;
if the capacitance is not lost, judging whether the angle of the capacitance is the same as the original angle of the standard template capacitance, if so, directly finishing capacitance detection, if not, storing the information that the polarity of the capacitance is incorrect, and finishing the capacitance detection.
Specifically, when the angle of the point capacitor is judged, the position of the standard template capacitor is set as E 1 (a 1 ,b 1 ,angle 1 )，a 1 ,b 1 Representing a position in two-dimensional coordinates, angle 1 Represents an angle; setting the position of the capacitance image in the shot PCB image as E o (a o ,b o ,angle o ) Let offset D = (a) o -a 1 ) 2 +(b o -b 1 ) 2 Rotation amount Ang = | angle 0 -angle 1 Setting an offset threshold D according to the process requirements o And a rotation threshold Ang o And then comparing the calculated offset amount and the rotation amount with the corresponding threshold value. It is understood that similar schemes can be used for the determination of other components, as long as appropriate thresholds and templates are preset.
Preferably, in step S2, the step of determining whether the connector is qualified specifically includes:
firstly, performing color space conversion processing on a PCB image to be detected, converting an RGB space of the PCB into an HSV space to obtain a PCB image under a V channel, finding a connector image under the V channel, and then comparing the connector image obtained after processing with a pre-stored standard connector template image through a regional gray value matching algorithm;
judging whether the connector is lost or not according to the comparison result, if so, saving the connector loss information and finishing the connector detection;
and if the connector is not lost, performing gray value scaling on the connector image to highlight the characteristic point area of the connector, averagely dividing the characteristic point area into an upper area and a lower area, judging whether the difference between the gray average value of the upper area and the gray average value of the lower area is greater than 0, if so, directly finishing connector detection, otherwise, storing information that the polarity of the connector is incorrect, and finishing the connector detection. Since the plurality of standard points of the connector are usually of fixed specification, whether the polarity is correct can be directly judged by the difference of the gray average values of the upper and lower two areas.
Preferably, in the step S2, the step of determining whether the crystal oscillator is qualified specifically includes:
finding a crystal oscillator image under a V channel, and then comparing the processed crystal oscillator image with a pre-stored standard crystal oscillator template image through a regional gray value matching algorithm;
and judging whether the crystal oscillator is lost or not according to the comparison result, directly finishing the step of detecting the crystal oscillator if the crystal oscillator is not lost, and storing the crystal oscillator missing information and finishing the step of detecting the crystal oscillator if the crystal oscillator is lost.
Preferably, in step S2, the step of determining whether the pin header is qualified specifically includes:
finding a pin header image under a V channel, and then comparing the processed pin header image with a pre-stored standard pin header template image through a regional gray value matching algorithm;
and judging whether the pin header is missing or not according to the comparison result, if not, directly ending the pin header detection step, and if so, saving pin header missing information and then ending the pin header detection step.
Preferably, in the step S2, the step of judging whether the terminal strip is qualified specifically includes:
detecting the large terminal strip to find a large terminal strip image under a V channel, and then comparing the processed large terminal strip image with a pre-stored standard large terminal strip template image through a regional gray value matching algorithm;
judging whether the large terminal strip is missing or not according to the comparison result, if so, saving the missing information of the large terminal strip and then finishing the detection of the large terminal strip;
if the large terminal row is not missing, performing gray value scaling on the image of the large terminal row area so as to highlight a characteristic point area (a concave angle area in the middle of the large terminal row) of the large terminal row, comparing the characteristic point area with the gray value of the characteristic point area of a standard large terminal row template so as to judge whether the polarity of the large terminal row is correct or not, if so, directly finishing the detection of the large terminal row, otherwise, storing the information that the polarity of the large terminal row is incorrect, and then finishing the detection of the large terminal row;
then, detecting the small terminal strip, finding a small terminal strip image under a V channel, and then comparing the small terminal strip image obtained after processing with a pre-stored standard small terminal strip template image through a regional gray value matching algorithm;
judging whether the small terminal strip is missing or not according to the comparison result, if so, saving missing information of the small terminal strip and then finishing the detection of the small terminal strip;
if the small terminal row is not missing, the gray scale value of the small terminal row area image is zoomed, so that the characteristic point area (the gap area at the upper right of the small terminal row) of the small terminal row is highlighted, the characteristic point area is compared with the characteristic point area of the standard small terminal row template in an angle mode to judge whether the polarity of the small terminal row is correct or not, if so, the detection of the small terminal row is directly finished, if not, the information that the polarity of the small terminal row is incorrect is stored, and then the detection of the small terminal row is finished.
Preferably, the step S3 specifically includes the following steps:
according to the photographed image of the surface of the PCB, firstly, judging whether the surface of the PCB has a scratch or not by using a Canny edge gradient detection algorithm, a template matching algorithm and Blob analysis, and if so, storing corresponding unqualified information;
and then, carrying out binarization and scaling processing on the board surface image of the PCB so as to judge whether blackening exists on the board surface of the PCB, and if the blackening exists, storing corresponding unqualified information.
The invention provides a special-shaped element AOI defect detection system of a PCB plate, which adopts the special-shaped element AOI defect detection method of the PCB plate to complete the special-shaped element AOI defect detection of the PCB plate and comprises an industrial personal computer 1, a motion control system 2 and an image acquisition system 3, wherein the motion control system 2 and the image acquisition system 3 are electrically connected with the industrial personal computer 1; the industrial personal computer 1 can be respectively and electrically connected with the motion control system 2 and the image acquisition system 3 through a concentrator 5; the motion control system 2 is used for controlling the automatic transmission of the PCB to be tested; the image acquisition system 3 is used for acquiring an image of the PCB to be detected and transmitting the image to the industrial personal computer 1.
Preferably, the image acquisition system 3 comprises a camera and a light source, and the light source surrounds a lens of the camera from the periphery; the motion control system 2 comprises a transmission track, a photographing area 4 used for isolating external illumination is arranged on the transmission track, a camera and a light source of the image acquisition system 3 are both arranged in the middle of the upper part inside the photographing area 4, and a lens of the camera faces the middle of the transmission track. Through the arrangement, the surface image of the PCB can be vertically irradiated by 360 degrees without dead angles, and an industrial camera can acquire clear and bright component images, so that the complexity and difficulty of subsequent algorithm processing are reduced. It can be understood that the front end of the transmission track can be connected with a front end production line of the PCB, and the rear end of the transmission track can respectively lead to a qualified area and an unqualified area so as to distinguish the PCB with qualified or unqualified detection results.
In summary, the method and system for detecting the AOI defects of the special-shaped components of the PCB provided by the present invention combine with various visual processing algorithms, greatly improve the accuracy of detecting the special-shaped components, and can mark the types of the lyric writing alarm for wrong components, missing components, reverse sticking, etc. of the PCB components, for example: bad, missing, offset, side standing, tombstone, reverse sticking, wrong, extremely reversed, missing tin and the like, and the defect detection of the PCB is realized. Compared with the traditional manual detection mode and other mechanical detection modes, the workload of workers is greatly reduced, the economic benefit of enterprises is also improved, the device can adapt to the detection of various special-shaped components, the detection precision is flexible and adjustable, the device can adapt to different application scenes, the structural characteristics of the design determine that the design can be flexibly configured on an automatic production line, and the device is in accordance with the construction of future intelligent factories, unmanned production lines and the like.
Finally, the above embodiments are only intended to illustrate the technical solution of the present invention and not to limit the same, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention, which should be covered by the claims of the present invention.

Claims (10)

1. A method for detecting the AOI defects of the special-shaped elements of the PCB is characterized by comprising the following steps:
s1, shooting an image of a PCB to be tested;
s2, comparing the shot images of all the components in the image of the PCB to be detected with pre-stored standard template images of all the components respectively, detecting whether all the components of the PCB to be detected are qualified or not according to the comparison result, and sequentially judging whether the capacitors, the connectors, the crystal oscillators, the pin headers and the terminal rows of the PCB are qualified or not in the detection process;
s3, according to the shot board surface image of the PCB, carrying out defect detection on the board surface of the PCB, and judging whether the board surface of the PCB is qualified or not;
and S4, if the PCB is qualified in the detection in the step S2 and the detection in the step S3, sending the PCB to a qualified area, otherwise, feeding back the type of the PCB which is unqualified, and sending the PCB to an unqualified area.
2. The method for detecting AOI defects of profiled elements of a PCB according to claim 1, wherein before the step S2, the method further comprises the steps of: and (3) performing MARK point positioning on the PCB to be detected according to the image of the PCB to be detected, entering the step S2 if the positioning is successful, and directly terminating the detection of the PCB if the positioning is failed.
3. The method for detecting the AOI defects of the special-shaped elements of the PCB as claimed in claim 2, wherein the step of judging whether the capacitors are qualified in the step S2 specifically comprises the following steps:
comparing the capacitance image in the shot PCB image with a pre-stored standard capacitance template image through a template matching algorithm;
judging whether the capacitor is missing or not according to the comparison result, if so, storing capacitor missing information and finishing the capacitor detection;
if the capacitance is not lost, judging whether the angle of the capacitance is the same as the original angle of the standard template capacitance, if so, directly finishing capacitance detection, if not, storing the information that the polarity of the capacitance is incorrect, and finishing the capacitance detection.
4. The AOI defect detection method for the special-shaped elements of the PCB as recited in claim 3, wherein the step of judging whether the connector is qualified in the step S2 specifically comprises the steps of:
firstly, performing color space conversion on a PCB image to be detected, converting RGB space into HSV space to obtain a PCB image under a V channel, finding a connector image under the V channel, and then comparing the connector image obtained after processing with a pre-stored standard connector template image through a regional gray value matching algorithm;
judging whether the connector is missing or not according to the comparison result, if so, saving the missing information of the connector and finishing the detection of the connector;
and if the connector is not lost, zooming the gray value of the connector image to highlight the characteristic point area of the connector, averagely dividing the characteristic point area into an upper area and a lower area, judging whether the difference between the gray average value of the upper area and the gray average value of the lower area is greater than 0, if so, directly finishing the connector detection, otherwise, storing the information that the polarity of the connector is incorrect, and finishing the connector detection.
5. The special-shaped element AOI defect detection method of the PCB of claim 4, wherein in the step S2, the step of judging whether the crystal oscillator is qualified specifically comprises the following steps:
finding a crystal oscillator image under a V channel, and then comparing the processed crystal oscillator image with a pre-stored standard crystal oscillator template image through a regional gray value matching algorithm;
and judging whether the crystal oscillator is lost or not according to the comparison result, directly finishing the step of detecting the crystal oscillator if the crystal oscillator is not lost, and storing the crystal oscillator missing information and finishing the step of detecting the crystal oscillator if the crystal oscillator is lost.
6. The special-shaped element AOI defect detection method of the PCB of claim 5, wherein in the step S2, the step of judging whether the pin header is qualified specifically comprises the following steps:
finding a pin header image under a V channel, and then comparing the processed pin header image with a pre-stored standard pin header template image through a regional gray value matching algorithm;
and judging whether the pin arrangement is lost or not according to the comparison result, if not, directly ending the pin arrangement detection step, and if so, storing pin arrangement missing information and then ending the pin arrangement detection step.
7. The AOI defect detection method for the special-shaped elements of the PCB of claim 6, wherein in the step S2, the step of judging whether the terminal strip is qualified specifically comprises the following steps:
firstly, detecting a large terminal block, finding a large terminal block image under a V channel, and then comparing the processed large terminal block image with a pre-stored standard large terminal block template image through a regional gray value matching algorithm;
judging whether the large terminal strip is missing or not according to the comparison result, if so, saving the missing information of the large terminal strip and then finishing the detection of the large terminal strip;
if the large terminal row is not missing, performing gray value scaling on the image of the large terminal row area so as to highlight the characteristic point area of the large terminal row, comparing the characteristic point area with the characteristic point area of a standard large terminal row template so as to judge whether the polarity of the large terminal row is correct or not, if so, directly finishing the detection of the large terminal row, otherwise, storing the information that the polarity of the large terminal row is incorrect, and then finishing the detection of the large terminal row;
then, detecting the small terminal strip, finding a small terminal strip image under a V channel, and then comparing the small terminal strip image obtained after processing with a pre-stored standard small terminal strip template image through a regional gray value matching algorithm;
judging whether the small terminal strip is missing or not according to the comparison result, if so, saving missing information of the small terminal strip and then finishing the detection of the small terminal strip;
if the small terminal row is not missing, performing gray scale value scaling on the small terminal row area image so as to highlight the characteristic point area of the small terminal row, performing angle comparison on the characteristic point area and the characteristic point area of the standard small terminal row template so as to judge whether the polarity of the small terminal row is correct or not, directly finishing the detection of the small terminal row if the polarity of the small terminal row is correct, otherwise, storing the information that the polarity of the small terminal row is incorrect, and finishing the detection of the small terminal row.
8. The method for detecting the AOI defects of the special-shaped elements of the PCB board as claimed in claim 1, wherein the step S3 specifically comprises the following steps:
according to the shot board surface image of the PCB, firstly, judging whether the board surface of the PCB has a scratch or not by utilizing a Canny edge gradient detection algorithm, a template matching algorithm and Blob analysis, and if so, storing corresponding unqualified information;
and then, carrying out binarization and scaling processing on the board surface image of the PCB so as to judge whether blackening exists on the board surface of the PCB, and if the blackening exists, storing corresponding unqualified information.
9. A special-shaped element AOI defect detection system of a PCB is characterized in that the special-shaped element AOI defect detection method of the PCB according to any one of claims 1 to 8 is adopted to complete the special-shaped element AOI defect detection of the PCB, and the special-shaped element AOI defect detection system comprises an industrial personal computer (1), a motion control system (2) and an image acquisition system (3), wherein the motion control system (2) and the image acquisition system are electrically connected with the industrial personal computer (1);
the motion control system (2) is used for controlling the automatic transmission of the PCB to be tested;
the image acquisition system (3) is used for acquiring an image of the PCB to be detected and transmitting the image to the industrial personal computer (1).
10. The PCB profiled AOI defect detection system of claim 9, wherein the image acquisition system (3) comprises a camera and a light source, and the light source surrounds a lens of the camera from all sides;
the motion control system (2) comprises a transmission track, a photographing area (4) used for isolating external illumination is arranged on the transmission track, a camera and a light source of the image acquisition system (3) are arranged in the middle of the upper portion inside the photographing area (4), and a lens of the camera faces the middle of the transmission track.
CN202210721181.1A 2022-06-24 2022-06-24 Method and system for detecting AOI (automated optical inspection) defects of special-shaped elements of PCB (printed circuit board) Pending CN115482194A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210721181.1A CN115482194A (en) 2022-06-24 2022-06-24 Method and system for detecting AOI (automated optical inspection) defects of special-shaped elements of PCB (printed circuit board)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210721181.1A CN115482194A (en) 2022-06-24 2022-06-24 Method and system for detecting AOI (automated optical inspection) defects of special-shaped elements of PCB (printed circuit board)

Publications (1)

Publication Number Publication Date
CN115482194A true CN115482194A (en) 2022-12-16

Family

ID=84422954

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210721181.1A Pending CN115482194A (en) 2022-06-24 2022-06-24 Method and system for detecting AOI (automated optical inspection) defects of special-shaped elements of PCB (printed circuit board)

Country Status (1)

Country Link
CN (1) CN115482194A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116152251A (en) * 2023-04-20 2023-05-23 成都数之联科技股份有限公司 Television backboard detection method, model training method, device, equipment and medium
CN117151556A (en) * 2023-11-01 2023-12-01 南方电网科学研究院有限责任公司 Hardware comparison method and device for power equipment

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116152251A (en) * 2023-04-20 2023-05-23 成都数之联科技股份有限公司 Television backboard detection method, model training method, device, equipment and medium
CN117151556A (en) * 2023-11-01 2023-12-01 南方电网科学研究院有限责任公司 Hardware comparison method and device for power equipment
CN117151556B (en) * 2023-11-01 2024-01-30 南方电网科学研究院有限责任公司 Hardware comparison method and device for power equipment

Similar Documents

Publication Publication Date Title
CN115482194A (en) Method and system for detecting AOI (automated optical inspection) defects of special-shaped elements of PCB (printed circuit board)
CN109100370A (en) A kind of pcb board defect inspection method based on sciagraphy and connected domain analysis
CN107945184A (en) A kind of mount components detection method positioned based on color images and gradient projection
CN106501272B (en) Machine vision soldering tin positioning detection system
CN110517265A (en) A kind of detection method of surface defects of products, device and storage medium
CN113269762A (en) Screen defect detection method, system and computer storage medium
CN111929239A (en) AOI detection device and detection method for PCB part defects
CN109712115B (en) Automatic PCB detection method and system
CN114813783A (en) Chip surface flaw detection method
CN114820439A (en) PCB bare board defect detection system and method based on AOI
CN114518526A (en) Automatic testing machine control system suitable for PCB board ICT
CN107248151B (en) Intelligent liquid crystal display detection method and system based on machine vision
CN112763496A (en) Mobile phone battery surface defect detection device and detection method thereof
CN115272340B (en) Industrial product defect detection method and device
CN115598136B (en) Screen gluing quality detection device
CN114392940B (en) Pin detection method and device for special-shaped component
CN116188759A (en) Multi-angle fixed point template matching-based visual positioning method for sheet tantalum capacitor
Zhang et al. Design of solder quality inspection system based on machine vision
CN114758158A (en) Quality inspection method and system for PCB
CN111899248A (en) Automatic PCB soldering paste defect detection method based on machine learning
CN112837285A (en) Edge detection method and device for panel image
Jiang et al. Energy meter patch resistance and welding spot anomaly detection method based on machine vision
CN117876376B (en) High-speed multifunctional connector quality visual detection method
CN111539933B (en) Direct-insert element detection method and system
CN117647531B (en) Deep learning-based AOI detection method and 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