WO2017080282A1 - 一种电路板的检测方法及装置 - Google Patents

一种电路板的检测方法及装置 Download PDF

Info

Publication number
WO2017080282A1
WO2017080282A1 PCT/CN2016/096889 CN2016096889W WO2017080282A1 WO 2017080282 A1 WO2017080282 A1 WO 2017080282A1 CN 2016096889 W CN2016096889 W CN 2016096889W WO 2017080282 A1 WO2017080282 A1 WO 2017080282A1
Authority
WO
WIPO (PCT)
Prior art keywords
circuit board
image
sub
solder joint
detecting
Prior art date
Application number
PCT/CN2016/096889
Other languages
English (en)
French (fr)
Inventor
韩志
Original Assignee
广州视源电子科技股份有限公司
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 广州视源电子科技股份有限公司 filed Critical 广州视源电子科技股份有限公司
Publication of WO2017080282A1 publication Critical patent/WO2017080282A1/zh

Links

Images

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • 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]

Definitions

  • the invention relates to the field of automatic optical detection, and in particular to a method and a device for detecting a circuit board.
  • Automated Optical Inspection is an effective method for industrial automation. It uses machine vision as a standard for inspection. It is widely used in LCD/TFT, transistor and PCB industrial processes, and can be extended to the security system for people's death. . Automated optical inspection is a common method commonly used in industrial processes. It uses optical methods to obtain the surface state of finished products, and image processing to detect foreign matter or pattern anomalies. Because it is a non-contact inspection, semi-finished products can be inspected in intermediate works.
  • AOI By using AOI as a tool to reduce defects, find and eliminate errors early in the assembly process to achieve good process control. Early detection of defects will avoid sending bad boards to the subsequent assembly stage, and AOI will reduce repair costs and will avoid scrapping unrepairable boards.
  • the AOI needs to program the detection target before detecting the circuit board, such as the size and position of the solder joint, so that the AOI detects the detection circuit board according to the programmed detection parameters.
  • programming is manually performed by a programmer, and the programmer needs to determine the detection parameters such as the detection area, the detection item, and the detection standard.
  • this manual programming method makes the setting of the detection parameters related to the worker's operating experience, and does not guarantee the same quality standard, resulting in low accuracy of board detection.
  • the embodiment of the invention provides a method and a device for detecting a circuit board, which can improve the accuracy of the circuit board detection.
  • Embodiments of the present invention provide a method for detecting a circuit board, including:
  • the detection circuit board is detected according to the detection parameter.
  • the image of the standard circuit board includes N sub-images; N ⁇ 1;
  • the obtaining an image of the standard circuit board specifically includes:
  • the standard circuit board is photographed by moving in four directions of up, down, left, and right;
  • the sub-image is checked each time a sub-image is taken;
  • N sub-images are sequentially captured according to the N shooting point positions, and the N sub-images are spliced into an image of the standard circuit board.
  • the positioning point and the solder joint are identified from the image of the standard circuit board, and the position information of the positioning point and the feature information of the solder joint are saved as detection parameters, specifically including:
  • the feature information of the solder joint in the sub-image is identified, and the feature information of the solder joint is saved in the solder joint detection parameter list;
  • the feature information of the solder joint includes the position of the solder joint, Size and type information;
  • the location information of the anchor point in the sub-image is identified, and the location information of the anchor point is saved in the location point detection parameter list.
  • the method further includes:
  • the shooting order of the M sub-images is set and saved, and the sub-images with the positioning points are preferentially photographed.
  • the detecting according to the detecting parameter, the detecting the circuit board, specifically includes:
  • an embodiment of the present invention further provides a device for detecting a circuit board, including:
  • An image acquisition module for acquiring an image of a standard circuit board
  • a detection parameter acquisition module configured to identify an anchor point and a solder joint from an image of the standard circuit board, and save position information of the positioning point and feature information of the solder joint as a detection parameter;
  • a detecting module configured to detect the circuit board to be detected according to the detecting parameter.
  • the image of the standard circuit board includes N sub-images; N ⁇ 1;
  • the image obtaining module specifically includes:
  • a photographing unit configured to photograph the standard circuit board by moving from the center position of the standard circuit board in sequence by four directions of up, down, left, and right directions;
  • a checking unit configured to check the sub-image every time a sub-image is taken
  • a calculating unit for detecting a sub-image without a circuit board in each moving direction, stopping shooting, and separately calculating a center point of the standard circuit board in each moving direction to the non-circuit board The shortest distance of the sub-image;
  • a boundary position acquiring unit configured to obtain a boundary position of the standard circuit board according to a shortest distance in four moving directions
  • a photographing point acquiring unit configured to calculate N photographing point positions required to photograph the standard circuit board according to the boundary position and the size of the photographed sub-image;
  • a sub-image obtaining unit configured to sequentially capture N sub-images according to the N shooting point positions, and splicing the N sub-images into an image of the standard circuit board.
  • the detecting parameter obtaining module specifically includes:
  • a judging unit configured to judge whether there is a solder joint or an anchor point in each sub-image of the standard circuit board one by one;
  • solder joint identifying unit configured to: when the determining unit determines that the sub-image has a solder joint, identify characteristic information of the solder joint in the sub-image, and save the feature information of the solder joint to the solder joint detecting parameter list
  • the characteristic information of the solder joint includes information on the position, size and type of the solder joint;
  • a positioning point identifying unit configured to: when the determining unit determines that the sub-image has an positioning point, identify location information of the positioning point in the sub-image, and save location information of the positioning point to the positioning point detection parameter list in.
  • the detecting device of the circuit board further includes:
  • a sub-image screening module configured to filter M sub-images having solder joints or anchor points from N sub-images of the standard circuit board; N ⁇ M ⁇ 1;
  • the shooting sequence setting module is configured to set and save the shooting order of the M sub-images, so that the sub-images with the positioning points are preferentially photographed.
  • the detecting module specifically includes:
  • An image capturing unit configured to photograph the to-be-detected circuit board according to a shooting order of the M sub-images
  • a detecting unit configured to detect an image captured by the circuit board to be detected according to the information in the positioning point detection parameter list and the solder joint detection parameter list.
  • the method and device for detecting a circuit board provided by the embodiment of the invention can identify the information about the positioning point and the solder joint in the standard circuit board, and save the identified information as a detection parameter, thereby directly detecting the detection parameter according to the detection parameter.
  • the circuit board performs detection, which improves the efficiency and accuracy of the detection parameter acquisition compared with the manual acquisition of the detection parameters by the programmer in the prior art, thereby improving the accuracy of the board detection.
  • the complete image of the circuit board is generally formed by splicing images taken by multiple positions, and only images with positioning points or solder joints are selected from the images taken in multiple positions for shooting, and the shooting order of the images is optimized, thereby reducing shooting.
  • FIG. 1 is a schematic flow chart of an embodiment of a method for detecting a circuit board provided by the present invention
  • step S1 is a schematic flow chart of an embodiment of step S1 in the method for detecting a circuit board provided by the present invention
  • FIG. 3 is a schematic structural view of an embodiment of a detecting device for a circuit board provided by the present invention.
  • FIG. 4 is a schematic structural view of an embodiment of an image acquisition module in a detecting device for a circuit board provided by the present invention.
  • FIG. 1 is a schematic flowchart of an embodiment of a method for detecting a circuit board provided by the present invention, including:
  • the inspector places the standard circuit board in the detected area, and captures an image of the standard circuit board through the camera.
  • Call the solder joint identification function to identify the position information of the solder joint from the image of the standard circuit board, and then call the learning or recognition function to learn each solder joint to obtain the characteristic information of the type, position, size and color of the solder joint.
  • the positioning point recognition function is called to identify the position information of the positioning point from the image of the standard circuit board.
  • the identified or learned information is saved as a detection parameter for detecting the subsequent to-be-detected circuit board.
  • the detection parameters are obtained through automatic identification without manual selection and setting by the programmer, which improves the efficiency and accuracy of the detection parameter acquisition, thereby improving the electricity.
  • the accuracy of the board detection is obtained through automatic identification without manual selection and setting by the programmer, which improves the efficiency and accuracy of the detection parameter acquisition, thereby improving the electricity. The accuracy of the board detection.
  • the image of the standard circuit board contains N sub-images; N ⁇ 1.
  • the obtaining an image of a standard circuit board specifically includes:
  • N sub-images are sequentially captured according to the N shooting point positions, and the N sub-images are spliced into an image of the standard circuit board.
  • the AOI camera used for the shooting board can only shoot more than a dozen square centimeters at a time, it is necessary to take multiple shots to capture a completed board image.
  • the board is typically placed in the center of the camera's motion so that it does not affect the automatic identification of the board size regardless of the board size.
  • the center position is not strictly the center, as long as most of the sub-images taken are boards.
  • the moving shots are taken from the top, bottom, left, and right directions, each time moving to a photographing position.
  • the sub-image taken by the camera has a length of 2 cm and a width of 3 cm.
  • the camera moves 3 cm to the right and then shoots.
  • the connectivity of the sub-image is detected to determine whether the sub-image contains a circuit board.
  • the connectivity detection includes four-direction and eight-direction connectivity tests, and detection according to a color histogram.
  • the sub-image includes a circuit board
  • the camera is returned to the center position and moved up by 2 cm for shooting.
  • the shooting is stopped, and the shortest distance of the center point of the standard board in each moving direction from the sub-image of the board is calculated, and the shortest distance is based on Distance to get the boundary position of the standard board.
  • the shortest distance between the center point of the standard board and the sub-image is 4.5 cm, and the right side of the standard board
  • the center point is 4.5cm.
  • the positioning point and the solder joint are identified from the image of the standard circuit board, and the position information of the positioning point and the feature information of the solder joint are saved as detection parameters, specifically including:
  • the feature information of the solder joint in the sub-image is identified, and the feature information of the solder joint is saved in the solder joint detection parameter list;
  • the feature information of the solder joint includes the position of the solder joint, Size and type information;
  • the location information of the anchor point in the sub-image is identified, and the location information of the anchor point is saved in the location point detection parameter list.
  • each sub-image is taken, that is, the sub-image is inspected to determine whether there is a solder joint or an anchor point on the sub-image. If there is a solder joint or an anchor point, the position information of the solder joint is saved in the solder joint detection parameter list, and the position information of the anchor point is saved in the positioning point detection parameter list. Then call the learning or recognition function to learn each solder joint in the solder joint detection parameter list, and obtain the feature information such as the type, size and position of the solder joint, and save it in the solder joint detection parameter list.
  • the method further includes:
  • the shooting order of the M sub-images is set and saved, and the sub-images with the positioning points are preferentially photographed.
  • M sub-images having solder joints or anchor points can be selected from N sub-images of the standard circuit board, and no A sub-image of the point to be detected. Set the shooting order of the M sub-images with solder joints or anchor points to optimize the shooting path and number of shots of the board to be inspected.
  • the detecting according to the detecting parameter, the detecting the circuit board, specifically includes:
  • the circuit board When detecting the circuit board to be detected, the circuit board is photographed according to the pre-storing shooting sequence, the sub-image having the positioning point is first captured, and the positioning point on the circuit board to be detected is detected according to the information in the positioning point detection parameter list. Then, according to the position information of the positioning point, the position of the circuit board is corrected, and then the sub-image with the solder joint is sequentially taken, and the solder joints in the sub-image are compared and detected according to the information in the solder joint detection parameter list.
  • the method for detecting a circuit board can identify the information about the positioning point and the solder joint in the standard circuit board, and save the identified information as a detection parameter, thereby directly detecting the circuit board according to the detection parameter.
  • the detection is performed, and the efficiency and accuracy of the detection parameter acquisition are improved compared with the manual acquisition of the detection parameters by the programmer in the prior art, thereby improving the accuracy of the detection of the circuit board; the complete image of the circuit board is generally an image taken by multiple positions.
  • the present invention also provides a detecting device for a circuit board, which can implement all the processes of the method for detecting a circuit board in the above embodiment.
  • FIG. 3 is a schematic structural diagram of an embodiment of a detecting device for a circuit board provided by the present invention, including:
  • An image acquisition module 1 for acquiring an image of a standard circuit board
  • a detection parameter acquisition module 2 configured to identify an anchor point and a solder joint from the image of the standard circuit board, and save the position information of the positioning point and the feature information of the solder joint as a detection parameter;
  • the detecting module 3 is configured to detect the circuit board to be detected according to the detecting parameter.
  • the image of the standard circuit board contains N sub-images; N ⁇ 1.
  • the image obtaining module 1 specifically includes:
  • the photographing unit 11 is configured to sequentially photograph the standard circuit board by moving from the center position of the standard circuit board through four directions of up, down, left, and right directions;
  • the checking unit 12 is configured to check the sub-image every time a sub-image is captured
  • the calculating unit 13 is configured to stop shooting when a sub-image without a circuit board is detected in each moving direction, and calculate a center point of the standard circuit board in each moving direction to the non-circuit board The shortest distance of the sub-image;
  • a boundary position acquiring unit 14 configured to obtain a boundary position of the standard circuit board according to a shortest distance in four moving directions;
  • a photographing point acquiring unit 15 configured to calculate N photographing point positions required to photograph the standard circuit board according to the boundary position and the size of the photographed sub-image;
  • the sub-image obtaining unit 16 is configured to sequentially capture N sub-images according to the N shooting point positions, and splicing the N sub-images into an image of the standard circuit board.
  • the detecting parameter obtaining module specifically includes:
  • a judging unit configured to judge whether there is a solder joint or an anchor point in each sub-image of the standard circuit board one by one;
  • solder joint identifying unit configured to: when the determining unit determines that the sub-image has a solder joint, identify characteristic information of the solder joint in the sub-image, and save the feature information of the solder joint to the solder joint detecting parameter list
  • the characteristic information of the solder joint includes information on the position, size and type of the solder joint;
  • a positioning point identifying unit configured to: when the determining unit determines that the sub-image has an positioning point, identify location information of the positioning point in the sub-image, and save location information of the positioning point to the positioning point detection parameter list in.
  • the detecting device of the circuit board further includes:
  • a sub-image screening module configured to filter M sub-images having solder joints or anchor points from N sub-images of the standard circuit board; N ⁇ M ⁇ 1;
  • the shooting sequence setting module is configured to set and save the shooting order of the M sub-images, so that the sub-images with the positioning points are preferentially photographed.
  • the detecting module specifically includes:
  • An image capturing unit configured to photograph the to-be-detected circuit board according to a shooting order of the M sub-images
  • a detecting unit configured to detect an image captured by the circuit board to be detected according to the information in the positioning point detection parameter list and the solder joint detection parameter list.
  • the device for detecting a circuit board provided by the embodiment of the invention can identify the information about the positioning point and the solder joint in the standard circuit board, and save the identified information as a detection parameter, thereby directly detecting the circuit board according to the detection parameter.
  • the detection is performed, and the efficiency and accuracy of the detection parameter acquisition are improved compared with the manual acquisition of the detection parameters by the programmer in the prior art, thereby improving the accuracy of the detection of the circuit board; the complete image of the circuit board is generally an image taken by multiple positions.

Landscapes

  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Health & Medical Sciences (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Pathology (AREA)
  • Analytical Chemistry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Image Processing (AREA)
  • Electric Connection Of Electric Components To Printed Circuits (AREA)

Abstract

本发明公开了一种电路板的检测方法，包括：获取标准电路板的图像；从所述标准电路板的图像中识别出定位点和焊点，并将所述定位点的位置信息和所述焊点的特征信息保存为检测参数；根据所述检测参数对待检测电路板进行检测。相应的，本发明还公开了一种电路板的检测装置。采用本发明实施例，能够提高电路板检测的准确率。

Description

一种电路板的检测方法及装置 技术领域
本发明涉及自动光学检测领域，尤其涉及一种电路板的检测方法及装置。
背景技术
自动光学检测(AOI，Automated Optical Inspection)为工业自动化有效的检测方法，使用机器视觉做为检测标准技术，大量应用于LCD/TFT、晶体管与PCB工业制程上，在民生用途则可延伸至保全系统。自动光学检查是工业制程中常见的代表性手法，利用光学方式取得成品的表面状态，以影像处理来检出异物或图案异常等瑕疵，因为是非接触式检查，所以可在中间工程检查半成品。
通过使用AOI作为减少缺陷的工具，在装配工艺过程的早期查找和消除错误，以实现良好的过程控制。早期发现缺陷将避免将坏板送到随后的装配阶段，AOI将减少修理成本将避免报废不可修理的电路板。
一般AOI在对电路板进行检测前需要对检测的目标进行编程，比如焊点的大小、位置等检测参数，使AOI根据编程的检测参数对待检测电路板进行检测。现有技术中是通过编程人员手动来编程，编程人员需自行确定检测区域、检测项目、检测标准等检测参数。但是，这种手动编程的方法使得检测参数的设置与工人操作经验有关，不能保证相同的品质标准，从而导致对电路板检测的准确率低。
发明内容
本发明实施例提出一种电路板的检测方法及装置，能够提高电路板检测的准确率。
本发明实施例提供一种电路板的检测方法，包括：
获取标准电路板的图像；
从所述标准电路板的图像中识别出定位点和焊点，并将所述定位点的位置信息和所述焊点的特征信息保存为检测参数；
根据所述检测参数对待检测电路板进行检测。
进一步地，所述标准电路板的图像包含N个子图像；N≥1；
所述获取标准电路板的图像，具体包括：
从所述标准电路板的中心位置开始，依次通过上下左右四个方向的移动对所述标准电路板进行拍摄；
每拍摄一个子图像时，对所述子图像进行检查；
在每个移动方向上均检查到不具有电路板的子图像时，停止拍摄，并分别计算每个移动方向上所述标准电路板的中心点到所述不具有电路板的子图像的最短距离；
根据四个移动方向上的最短距离，获得所述标准电路板的边界位置；
根据所述边界位置和拍摄的子图像的大小，计算获得拍摄所述标准电路板所需的N个拍摄点位置；
根据所述N个拍摄点位置依次拍摄出N个子图像，并将所述N个子图像拼接为所述标准电路板的图像。
进一步地，所述从所述标准电路板的图像中识别出定位点和焊点，并将所述定位点的位置信息和所述焊点的特征信息保存为检测参数，具体包括：
逐一判断所述标准电路板的每个子图像中是否具有焊点或定位点；
若具有焊点，则识别出所述子图像中焊点的特征信息，并将所述焊点的特征信息保存到焊点检测参数列表中；所述焊点的特征信息包括焊点的位置、大小和类型信息；
若具有定位点，则识别出所述子图像中定位点的位置信息，并将所述定位点的位置信息保存到定位点检测参数列表中。
进一步地，在所述从所述标准电路板的图像中识别出定位点和焊点之后，且在所述根据所述检测参数对待检测电路板进行检测之前，还包括：
从所述标准电路板的N个子图像中筛选出具有焊点或定位点的M个子图像； N≥M≥1；
设置并保存所述M个子图像的拍摄顺序，使具有定位点的子图像优先拍摄。
进一步地，所述根据所述检测参数对待检测电路板进行检测，具体包括：
按照所述M个子图像的拍摄顺序，对所述待检测电路板进行拍摄；
根据所述定位点检测参数列表和所述焊点检测参数列表中的信息，对所述待检测电路板拍摄的图像进行检测。
相应的，本发明实施例还提供一种电路板的检测装置，包括：
图像获取模块，用于获取标准电路板的图像；
检测参数获取模块，用于从所述标准电路板的图像中识别出定位点和焊点，并将所述定位点的位置信息和所述焊点的特征信息保存为检测参数；以及，
检测模块，用于根据所述检测参数对待检测电路板进行检测。
进一步地，所述标准电路板的图像包含N个子图像；N≥1；
所述图像获取模块具体包括：
拍摄单元，用于从所述标准电路板的中心位置开始，依次通过上下左右四个方向的移动对所述标准电路板进行拍摄；
检查单元，用于每拍摄一个子图像时，对所述子图像进行检查；
计算单元，用于在每个移动方向上均检查到不具有电路板的子图像时，停止拍摄，并分别计算每个移动方向上所述标准电路板的中心点到所述不具有电路板的子图像的最短距离；
边界位置获取单元，用于根据四个移动方向上的最短距离，获得所述标准电路板的边界位置；
拍摄点获取单元，用于根据所述边界位置和拍摄的子图像的大小，计算获得拍摄所述标准电路板所需的N个拍摄点位置；以及，
子图像获取单元，用于根据所述N个拍摄点位置依次拍摄出N个子图像，并将所述N个子图像拼接为所述标准电路板的图像。
进一步地，所述检测参数获取模块具体包括：
判断单元，用于逐一判断所述标准电路板的每个子图像中是否具有焊点或定位点；
焊点识别单元，用于在所述判断单元判定子图像中具有焊点时，识别出所述子图像中焊点的特征信息，并将所述焊点的特征信息保存到焊点检测参数列表中；所述焊点的特征信息包括焊点的位置、大小和类型信息；以及，
定位点识别单元，用于在所述判断单元判定子图像中具有定位点时，识别出所述子图像中定位点的位置信息，并将所述定位点的位置信息保存到定位点检测参数列表中。
进一步地，所述电路板的检测装置还包括：
子图像筛选模块，用于从所述标准电路板的N个子图像中筛选出具有焊点或定位点的M个子图像；N≥M≥1；以及，
拍摄顺序设置模块，用于设置并保存所述M个子图像的拍摄顺序，使具有定位点的子图像优先拍摄。
进一步地，所述检测模块具体包括：
图像拍摄单元，用于按照所述M个子图像的拍摄顺序，对所述待检测电路板进行拍摄；以及，
检测单元，用于根据所述定位点检测参数列表和所述焊点检测参数列表中的信息，对所述待检测电路板拍摄的图像进行检测。
实施本发明实施例，具有如下有益效果：
本发明实施例提供的电路板的检测方法及装置，能够对标准电路板中的定位点和焊点的相关信息进行识别，并将识别出的信息保存为检测参数，从而直接根据检测参数对待检测电路板进行检测，相对于现有技术中编程人员手动获取检测参数来说，提高检测参数获取的效率和准确率，从而提高电路板检测的准确率。
而且，电路板的完整图像一般是通过多位置拍摄的图像拼接而成，从多位置拍摄的图像中仅选取出具有定位点或焊点的图像进行拍摄，并优化图像的拍摄顺序，从而减少拍摄图像的数量，且提高拍摄效率。
附图说明
图1是本发明提供的电路板的检测方法的一个实施例的流程示意图；
图2是本发明提供的电路板的检测方法中步骤S1的一个实施例的流程示意图；
图3是本发明提供的电路板的检测装置的一个实施例的结构示意图；
图4是本发明提供的电路板的检测装置中图像获取模块的一个实施例的结构示意图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
参见图1，是本发明提供的电路板的检测方法的一个实施例的流程示意图，包括：
S1、获取标准电路板的图像；
S2、从所述标准电路板的图像中识别出定位点和焊点，并将所述定位点的位置信息和所述焊点的特征信息保存为检测参数；
S3、根据所述检测参数对待检测电路板进行检测。
需要说明的是，检测人员将标准电路板放置在被检测区域，通过摄像头拍摄出标准电路板的图像。调用焊点识别函数，从标准电路板的图像中识别出焊点的位置信息，进而调用学习或识别函数，对每个焊点进行学习，获得焊点的类型、位置、大小、颜色等特征信息。同时，调用定位点识别函数，从标准电路板的图像中识别出定位点的位置信息。将识别或学习到的信息保存为检测参数，以供对之后的待检测电路板进行检测。检测参数通过自动识别获得，而无需编程人员人工选取和设置，提高检测参数获取的效率和准确率，进而提高电 路板检测的准确率。
进一步地，所述标准电路板的图像包含N个子图像；N≥1。
如图2所示，所述获取标准电路板的图像，具体包括：
S21、从所述标准电路板的中心位置开始，依次通过上下左右四个方向的移动对所述标准电路板进行拍摄；
S22、每拍摄一个子图像时，对所述子图像进行检查；
S23、在每个移动方向上均检查到不具有电路板的子图像时，停止拍摄，并分别计算每个移动方向上所述标准电路板的中心点到所述不具有电路板的子图像的最短距离；
S24、根据四个移动方向上的最短距离，获得所述标准电路板的边界位置；
S25、根据所述边界位置和拍摄的子图像的大小，计算获得拍摄所述标准电路板所需的N个拍摄点位置；
S26、根据所述N个拍摄点位置依次拍摄出N个子图像，并将所述N个子图像拼接为所述标准电路板的图像。
需要说明的是，由于拍摄电路板所使用的AOI摄像头一次只能拍摄出十几个平方厘米的面积，因此想要拍摄一个完成的电路板图像需要进行多次拍摄。一般将电路板放置于摄像头运动的中心位置，这样无论电路板大小如何变化都不会影响对电路板尺寸的自动识别。
在拍摄标准电路板时，从标准电路板的中心位置开始拍摄。其中，中心位置并不是严格的正中心，只要拍摄的子图像中大部分都为电路板即可。中心位置拍摄完后，分别从上下左右四个方向进行移动拍摄，每次移动为一个拍照位置。例如，摄像头拍摄的子图像的长为2cm、宽为3cm，则中心位置拍摄完后，摄像头向右移动3cm再进行拍摄。每拍摄一个子图像后，对该子图像的连通性进行检测，判断该子图像中是否包含电路板。其中，连通性检测包括四方向、八方向连通测试，根据颜色直方图进行检测等。若该子图像中包含电路板，则继续沿着该方向移动一个拍照位置进行拍摄；若该子图像中不包含电路板，则使摄像头回到中心位置，更换移动方向来移动一个拍照位置继续进行拍摄，例 如，向右移动了两个拍照位置后，检测到当前子图像不包含电路板，则使摄像头回到中心位置并向上移动2cm进行拍摄。直到在四个移动方向上均检查到不包含电路板的子图像时，停止拍摄，并计算每个移动方向上标准电路板的中心点距离不包含电路板的子图像的最短距离，并根据最短距离获取标准电路板的边界位置。例如，摄像头从中心位置开始向右移动了6cm后，检测到不包含电路板的子图像，则标准电路板的中心点距离该子图像的最短距离为4.5cm，则标准电路板的右侧边界距离中心点为4.5cm。在获取标准电路板的边界位置后，即可知道标准电路板的四角的坐标，进而根据拍摄的子图像的大小，编写循环代码逐块对标准电路板进行拍摄，例如，从标准电路板的左上角逐块拍摄到右下角。拍摄获得的N个子图像即可拼接为完整的标准电路板的图像。
进一步地，所述从所述标准电路板的图像中识别出定位点和焊点，并将所述定位点的位置信息和所述焊点的特征信息保存为检测参数，具体包括：
逐一判断所述标准电路板的每个子图像中是否具有焊点或定位点；
若具有焊点，则识别出所述子图像中焊点的特征信息，并将所述焊点的特征信息保存到焊点检测参数列表中；所述焊点的特征信息包括焊点的位置、大小和类型信息；
若具有定位点，则识别出所述子图像中定位点的位置信息，并将所述定位点的位置信息保存到定位点检测参数列表中。
其中，在对标准电路板逐块进行拍摄时，每拍摄出一个子图像，即对该子图像进行检查，判断该子图像上是否具有焊点或定位点。若具有焊点或定位点，则将焊点的位置信息保存在焊点检测参数列表中，将定位点的位置信息保存在定位点检测参数列表中。再调用学习或识别函数，对焊点检测参数列表中每个焊点进行学习，获得焊点的类型、大小、位置等特征信息，并相应保存在焊点检测参数列表中。
进一步地，在所述从所述标准电路板的图像中识别出定位点和焊点之后，且在所述根据所述检测参数对待检测电路板进行检测之前，还包括：
从所述标准电路板的N个子图像中筛选出具有焊点或定位点的M个子图像； N≥M≥1；
设置并保存所述M个子图像的拍摄顺序，使具有定位点的子图像优先拍摄。
需要说明的是，在判断标准电路板的每个子图像中是否具有定位点或焊点后，即可从标准电路板的N个子图像中筛选出具有焊点或定位点的M个子图像，去除无待检测点的子图像。设置具有焊点或定位点的M个子图像的拍摄顺序，从而优化待检测电路板的拍摄路径和拍摄数量。
进一步地，所述根据所述检测参数对待检测电路板进行检测，具体包括：
按照所述M个子图像的拍摄顺序，对所述待检测电路板进行拍摄；
根据所述定位点检测参数列表和所述焊点检测参数列表中的信息，对所述待检测电路板拍摄的图像进行检测。
在检测待检测电路板时，根据预先保存的拍摄顺序对电路板进行拍摄，先拍摄出具有定位点的子图像，并根据定位点检测参数列表中的信息检测出待检测电路板上的定位点，进而根据定位点的位置信息来校正电路板的位置，再依次拍摄出具有焊点的子图像，并根据焊点检测参数列表中的信息对子图像中的焊点进行对比检测。
本发明实施例提供的电路板的检测方法，能够对标准电路板中的定位点和焊点的相关信息进行识别，并将识别出的信息保存为检测参数，从而直接根据检测参数对待检测电路板进行检测，相对于现有技术中编程人员手动获取检测参数来说，提高检测参数获取的效率和准确率，从而提高电路板检测的准确率；电路板的完整图像一般是通过多位置拍摄的图像拼接而成，从多位置拍摄的图像中仅选取出具有定位点或焊点的图像进行拍摄，并优化图像的拍摄顺序，从而减少拍摄图像的数量，且提高拍摄效率。
相应的，本发明还提供一种电路板的检测装置，能够实现上述实施例中的电路板的检测方法的所有流程。
参见图3，是本发明提供的电路板的检测装置的一个实施例的结构示意图，包括：
图像获取模块1，用于获取标准电路板的图像；
检测参数获取模块2，用于从所述标准电路板的图像中识别出定位点和焊点，并将所述定位点的位置信息和所述焊点的特征信息保存为检测参数；以及，
检测模块3，用于根据所述检测参数对待检测电路板进行检测。
进一步地，所述标准电路板的图像包含N个子图像；N≥1。
如图4所示，所述图像获取模块1具体包括：
拍摄单元11，用于从所述标准电路板的中心位置开始，依次通过上下左右四个方向的移动对所述标准电路板进行拍摄；
检查单元12，用于每拍摄一个子图像时，对所述子图像进行检查；
计算单元13，用于在每个移动方向上均检查到不具有电路板的子图像时，停止拍摄，并分别计算每个移动方向上所述标准电路板的中心点到所述不具有电路板的子图像的最短距离；
边界位置获取单元14，用于根据四个移动方向上的最短距离，获得所述标准电路板的边界位置；
拍摄点获取单元15，用于根据所述边界位置和拍摄的子图像的大小，计算获得拍摄所述标准电路板所需的N个拍摄点位置；以及，
子图像获取单元16，用于根据所述N个拍摄点位置依次拍摄出N个子图像，并将所述N个子图像拼接为所述标准电路板的图像。
进一步地，所述检测参数获取模块具体包括：
判断单元，用于逐一判断所述标准电路板的每个子图像中是否具有焊点或定位点；
焊点识别单元，用于在所述判断单元判定子图像中具有焊点时，识别出所述子图像中焊点的特征信息，并将所述焊点的特征信息保存到焊点检测参数列表中；所述焊点的特征信息包括焊点的位置、大小和类型信息；以及，
定位点识别单元，用于在所述判断单元判定子图像中具有定位点时，识别出所述子图像中定位点的位置信息，并将所述定位点的位置信息保存到定位点检测参数列表中。
进一步地，所述电路板的检测装置还包括：
子图像筛选模块，用于从所述标准电路板的N个子图像中筛选出具有焊点或定位点的M个子图像；N≥M≥1；以及，
拍摄顺序设置模块，用于设置并保存所述M个子图像的拍摄顺序，使具有定位点的子图像优先拍摄。
进一步地，所述检测模块具体包括：
图像拍摄单元，用于按照所述M个子图像的拍摄顺序，对所述待检测电路板进行拍摄；以及，
检测单元，用于根据所述定位点检测参数列表和所述焊点检测参数列表中的信息，对所述待检测电路板拍摄的图像进行检测。
本发明实施例提供的电路板的检测装置，能够对标准电路板中的定位点和焊点的相关信息进行识别，并将识别出的信息保存为检测参数，从而直接根据检测参数对待检测电路板进行检测，相对于现有技术中编程人员手动获取检测参数来说，提高检测参数获取的效率和准确率，从而提高电路板检测的准确率；电路板的完整图像一般是通过多位置拍摄的图像拼接而成，从多位置拍摄的图像中仅选取出具有定位点或焊点的图像进行拍摄，并优化图像的拍摄顺序，从而减少拍摄图像的数量，且提高拍摄效率。
以上所述是本发明的优选实施方式，应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明原理的前提下，还可以做出若干改进和润饰，这些改进和润饰也视为本发明的保护范围。

Claims (10)

  1. 一种电路板的检测方法，其特征在于，包括：
    获取标准电路板的图像；
    从所述标准电路板的图像中识别出定位点和焊点，并将所述定位点的位置信息和所述焊点的特征信息保存为检测参数；
    根据所述检测参数对待检测电路板进行检测。
  2. 如权利要求1所述的电路板的检测方法，其特征在于，所述标准电路板的图像包含N个子图像；N≥1；
    所述获取标准电路板的图像，具体包括：
    从所述标准电路板的中心位置开始，依次通过上下左右四个方向的移动对所述标准电路板进行拍摄；
    每拍摄一个子图像时，对所述子图像进行检查；
    在每个移动方向上均检查到不具有电路板的子图像时，停止拍摄，并分别计算每个移动方向上所述标准电路板的中心点到所述不具有电路板的子图像的最短距离；
    根据四个移动方向上的最短距离，获得所述标准电路板的边界位置；
    根据所述边界位置和拍摄的子图像的大小，计算获得拍摄所述标准电路板所需的N个拍摄点位置；
    根据所述N个拍摄点位置依次拍摄出N个子图像，并将所述N个子图像拼接为所述标准电路板的图像。
  3. 如权利要求2所述的电路板的检测方法，其特征在于，所述从所述标准电路板的图像中识别出定位点和焊点，并将所述定位点的位置信息和所述焊点的特征信息保存为检测参数，具体包括：
    逐一判断所述标准电路板的每个子图像中是否具有焊点或定位点；
    若具有焊点，则识别出所述子图像中焊点的特征信息，并将所述焊点的特 征信息保存到焊点检测参数列表中；所述焊点的特征信息包括焊点的位置、大小和类型信息；
    若具有定位点，则识别出所述子图像中定位点的位置信息，并将所述定位点的位置信息保存到定位点检测参数列表中。
  4. 如权利要求3所述的电路板的检测方法，其特征在于，在所述从所述标准电路板的图像中识别出定位点和焊点之后，且在所述根据所述检测参数对待检测电路板进行检测之前，还包括：
    从所述标准电路板的N个子图像中筛选出具有焊点或定位点的M个子图像；N≥M≥1；
    设置并保存所述M个子图像的拍摄顺序，使具有定位点的子图像优先拍摄。
  5. 如权利要求4所述的电路板的检测方法，其特征在于，所述根据所述检测参数对待检测电路板进行检测，具体包括：
    按照所述M个子图像的拍摄顺序，对所述待检测电路板进行拍摄；
    根据所述定位点检测参数列表和所述焊点检测参数列表中的信息，对所述待检测电路板拍摄的图像进行检测。
  6. 一种电路板的检测装置，其特征在于，包括：
    图像获取模块，用于获取标准电路板的图像；
    检测参数获取模块，用于从所述标准电路板的图像中识别出定位点和焊点，并将所述定位点的位置信息和所述焊点的特征信息保存为检测参数；以及，
    检测模块，用于根据所述检测参数对待检测电路板进行检测。
  7. 如权利要求6所述的电路板的检测装置，其特征在于，所述标准电路板的图像包含N个子图像；N≥1；
    所述图像获取模块具体包括：
    拍摄单元，用于从所述标准电路板的中心位置开始，依次通过上下左右四个方向的移动对所述标准电路板进行拍摄；
    检查单元，用于每拍摄一个子图像时，对所述子图像进行检查；
    计算单元，用于在每个移动方向上均检查到不具有电路板的子图像时，停止拍摄，并分别计算每个移动方向上所述标准电路板的中心点到所述不具有电路板的子图像的最短距离；
    边界位置获取单元，用于根据四个移动方向上的最短距离，获得所述标准电路板的边界位置；
    拍摄点获取单元，用于根据所述边界位置和拍摄的子图像的大小，计算获得拍摄所述标准电路板所需的N个拍摄点位置；以及，
    子图像获取单元，用于根据所述N个拍摄点位置依次拍摄出N个子图像，并将所述N个子图像拼接为所述标准电路板的图像。
  8. 如权利要求7所述的电路板的检测装置，其特征在于，所述检测参数获取模块具体包括：
    判断单元，用于逐一判断所述标准电路板的每个子图像中是否具有焊点或定位点；
    焊点识别单元，用于在所述判断单元判定子图像中具有焊点时，识别出所述子图像中焊点的特征信息，并将所述焊点的特征信息保存到焊点检测参数列表中；所述焊点的特征信息包括焊点的位置、大小和类型信息；以及，
    定位点识别单元，用于在所述判断单元判定子图像中具有定位点时，识别出所述子图像中定位点的位置信息，并将所述定位点的位置信息保存到定位点检测参数列表中。
  9. 如权利要求8所述的电路板的检测装置，其特征在于，所述电路板的检测装置还包括：
    子图像筛选模块，用于从所述标准电路板的N个子图像中筛选出具有焊点 或定位点的M个子图像；N≥M≥1；以及，
    拍摄顺序设置模块，用于设置并保存所述M个子图像的拍摄顺序，使具有定位点的子图像优先拍摄。
  10. 如权利要求9所述的电路板的检测装置，其特征在于，所述检测模块具体包括：
    图像拍摄单元，用于按照所述M个子图像的拍摄顺序，对所述待检测电路板进行拍摄；以及，
    检测单元，用于根据所述定位点检测参数列表和所述焊点检测参数列表中的信息，对所述待检测电路板拍摄的图像进行检测。
PCT/CN2016/096889 2015-11-11 2016-08-26 一种电路板的检测方法及装置 WO2017080282A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510767684.2A CN105303579B (zh) 2015-11-11 2015-11-11 一种电路板的检测方法及装置
CN201510767684.2 2015-11-11

Publications (1)

Publication Number Publication Date
WO2017080282A1 true WO2017080282A1 (zh) 2017-05-18

Family

ID=55200801

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/096889 WO2017080282A1 (zh) 2015-11-11 2016-08-26 一种电路板的检测方法及装置

Country Status (2)

Country Link
CN (1) CN105303579B (zh)
WO (1) WO2017080282A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111369517A (zh) * 2020-02-28 2020-07-03 创新奇智(合肥)科技有限公司 太阳能板自动质检方法、装置、电子设备及存储介质
CN112858303A (zh) * 2021-03-22 2021-05-28 长春工业大学 一种基于机器视觉的线柜端子通断状态检测装置
CN113340919A (zh) * 2021-07-02 2021-09-03 南通海舟电子科技有限公司 一种智能控制电路板的控制系统

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105303579B (zh) * 2015-11-11 2018-03-16 广州视源电子科技股份有限公司 一种电路板的检测方法及装置
CN106290400A (zh) * 2016-07-29 2017-01-04 广东正业科技股份有限公司 一种应用于板的检孔方法及检孔设备
CN107610088B (zh) * 2017-07-03 2021-05-04 刘胜贤 一种电路板识别方法及系统
CN107545566A (zh) * 2017-07-27 2018-01-05 深圳市易飞扬通信技术有限公司 视觉检测方法及系统
WO2019061220A1 (zh) * 2017-09-29 2019-04-04 深圳传音通讯有限公司 一种电路板、定位调整方法及计算机可读存储介质
CN107731265A (zh) * 2017-09-30 2018-02-23 上海剑桥科技股份有限公司 Ddr测试系统和方法
TWI661394B (zh) * 2018-08-22 2019-06-01 林佑學 焊點影像辨識方法
CN110010019B (zh) * 2019-04-15 2021-07-06 珠海格力智能装备有限公司 一种装配led屏的控制方法及装置
CN110310341B (zh) * 2019-07-02 2021-09-24 广州视源电子科技股份有限公司 颜色算法中默认参数的生成方法、装置、设备和存储介质
CN111060515A (zh) * 2019-12-04 2020-04-24 深圳市铭华航电工艺技术有限公司 Pcba质量检测方法、系统、计算机设备
CN111160824A (zh) * 2019-12-05 2020-05-15 深圳市铭华航电工艺技术有限公司 工程资料的检测方法、装置、计算机设备及存储介质
KR102622753B1 (ko) * 2020-02-17 2024-01-10 삼성에스디아이 주식회사 이차전지용 레이저 용접 방법 및 모니터링 방법
CN112150433B (zh) * 2020-09-22 2024-05-28 中广核核电运营有限公司 电路板晶须物质的检测方法、计算机设备和存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040184031A1 (en) * 2003-03-20 2004-09-23 Vook Dietrich W. Optical inspection system, apparatus and method for reconstructing three-dimensional images for printed circuit board and electronics manufacturing inspection
CN101793843A (zh) * 2010-03-12 2010-08-04 华东理工大学 基于连接表的印刷线路板自动光学检测算法
CN103020586A (zh) * 2012-11-13 2013-04-03 浙江省电力公司电力科学研究院 一种pcb板识别方法、装置及系统
CN105303579A (zh) * 2015-11-11 2016-02-03 广州视源电子科技股份有限公司 一种电路板的检测方法及装置

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104049812B (zh) * 2014-05-30 2017-07-25 京东方科技集团股份有限公司 显示信号输入装置、显示信号输入方法和显示系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040184031A1 (en) * 2003-03-20 2004-09-23 Vook Dietrich W. Optical inspection system, apparatus and method for reconstructing three-dimensional images for printed circuit board and electronics manufacturing inspection
CN101793843A (zh) * 2010-03-12 2010-08-04 华东理工大学 基于连接表的印刷线路板自动光学检测算法
CN103020586A (zh) * 2012-11-13 2013-04-03 浙江省电力公司电力科学研究院 一种pcb板识别方法、装置及系统
CN105303579A (zh) * 2015-11-11 2016-02-03 广州视源电子科技股份有限公司 一种电路板的检测方法及装置

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111369517A (zh) * 2020-02-28 2020-07-03 创新奇智(合肥)科技有限公司 太阳能板自动质检方法、装置、电子设备及存储介质
CN112858303A (zh) * 2021-03-22 2021-05-28 长春工业大学 一种基于机器视觉的线柜端子通断状态检测装置
CN113340919A (zh) * 2021-07-02 2021-09-03 南通海舟电子科技有限公司 一种智能控制电路板的控制系统

Also Published As

Publication number Publication date
CN105303579A (zh) 2016-02-03
CN105303579B (zh) 2018-03-16

Similar Documents

Publication Publication Date Title
WO2017080282A1 (zh) 一种电路板的检测方法及装置
CN106226325B (zh) 一种基于机器视觉的座椅表面缺陷检测系统及其方法
JP5947169B2 (ja) 外観検査装置、外観検査法およびプログラム
US10366484B2 (en) Inspection method, inspection apparatus, processing apparatus, and recording medium for detecting defects of a work
TWI621484B (zh) 輸送物檢查系統和輸送裝置
JP2017096750A (ja) 位置決め方法、位置決め装置、プログラムおよびコンピュータ可読記録媒体
CN105466951A (zh) 一种自动光学检测装置及其检测方法
CN109227352B (zh) 一种基板缺陷修复方法及系统
WO2017071406A1 (zh) 金针类元件的引脚检测方法和系统
CN114022436B (zh) 一种印制电路板的检测方法、装置及检测设备
CN109389597B (zh) 一种生产线上电路板缺陷检测系统及方法
CN105023018A (zh) 一种喷码检测方法及系统
CN105184739A (zh) 印刷线路板aoi检测的图像拼接方法
CN111929239A (zh) 一种pcb板零件缺陷的aoi检测装置及检测方法
TWI708041B (zh) 檢測與標記瑕疵的方法
CN111103306A (zh) 检测与标记瑕疵的方法
KR20130128923A (ko) 칩마운터의 실장 불량 추적 방법 및 장치
KR20150104766A (ko) 검사공정에서의 불량 이력 추적 방법
JP6387620B2 (ja) 品質管理システム
CN114392940B (zh) 一种异型元器件的针脚检测方法及装置
TW201522949A (zh) 影像資訊檢測方法
TW201623946A (zh) 印刷電路板裝配檢測系統及其檢測方法
JP6008667B2 (ja) 外観検査装置、外観検査法およびプログラム
KR100855769B1 (ko) 유리기판의 치수 측정장치
CN106934791B (zh) 一种移动终端上fpc的视觉检测方法及控制设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16863460

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16863460

Country of ref document: EP

Kind code of ref document: A1