WO2017107529A1 - 一种并排二极管的定位方法及装置 - Google Patents

一种并排二极管的定位方法及装置 Download PDF

Info

Publication number
WO2017107529A1
WO2017107529A1 PCT/CN2016/096752 CN2016096752W WO2017107529A1 WO 2017107529 A1 WO2017107529 A1 WO 2017107529A1 CN 2016096752 W CN2016096752 W CN 2016096752W WO 2017107529 A1 WO2017107529 A1 WO 2017107529A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
diode
detection area
positioning information
arranged side
Prior art date
Application number
PCT/CN2016/096752
Other languages
English (en)
French (fr)
Inventor
林建民
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 WO2017107529A1 publication Critical patent/WO2017107529A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75Organisation 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
    • G06V10/751Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/95Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
    • G01N21/956Inspecting patterns on the surface of objects
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75Organisation 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
    • G06V10/759Region-based matching

Definitions

  • the invention relates to the field of automatic optical inspection, and in particular to a positioning method and device for a side by side diode.
  • AOI Automated Optical Inspection
  • the surface state of the finished product is obtained optically, and the foreign matter or surface flaw is detected by image processing.
  • the fault, leakage and reverse detection of manual plug-in diodes is a common application in the field of board defect detection.
  • the detection method is: the machine automatically scans the board through the camera to obtain the board image, extracts a partial image of each diode element, and Through the image processing technology, it is judged whether the diode element has errors, leaks, and anti-defects, and finally the components with suspected defects are displayed or marked for convenient viewing and inspection.
  • each diode element in the side-by-side diode group is treated as a common diode element by positioning the circuit to be detected (after registration) according to the diode position information marked in the manual plate making process.
  • the search area is created at the same location of the board, and then the position of the diode is located within the search area using a template matching method.
  • the above positioning method relies extremely much on the position information of the diodes marked in the manual plate making process, and the side-by-side diode group (in the case of diodes arranged side by side in the vertical direction), especially the position of the high-pin side-by-side diode group in the vertical direction.
  • the variation is large, and the actual position of the diode on the board to be tested may be different from the position of the diode marked in the manual plate making process by the height of the two diodes. Therefore, directly searching for the position information of the diode marked in the manual plate making process is extremely prone to misalignment.
  • the position of the diode to be positioned is not the position of the diode to be positioned, but the position of the adjacent diode, thereby causing the diode.
  • the positioning is not accurate.
  • Embodiments of the present invention provide a method and apparatus for positioning side-by-side diodes, which can improve the accuracy of positioning of each diode in parallel.
  • Embodiments of the present invention provide a method for locating a side-by-side diode, including:
  • the diode group comprises N diodes arranged side by side, N ⁇ 1;
  • the extracting the detection area image of the diode group from the image of the circuit board includes:
  • the detection area of the diode group is expanded according to a preset expansion factor, and an image in the expanded detection area is extracted to obtain a detection area image of the diode group.
  • the matching the image of the detection area with the template image of each diode in the diode group, and acquiring the first positioning information of each diode arranged side by side in the image of the detection area specifically includes:
  • the pin of each of the diodes in the image of the detection area is identified, and the second positioning information of each diode arranged side by side in the image of the detection area is obtained, which specifically includes:
  • the diode group includes N diodes arranged side by side in a vertical direction;
  • the first positioning information is an abscissa of an upper left corner vertex of each diode side by side in the detection area image, and the second positioning information is An ordinate of an upper left corner vertex of each of the diodes arranged side by side in the image of the detection area;
  • the embodiment of the invention further provides a positioning device for a side by side diode, comprising:
  • An extraction module configured to extract a detection area image of the diode group from the circuit board image; wherein the diode group includes N diodes arranged side by side, N ⁇ 1;
  • a matching module configured to match the detection area image with a template image of each diode in the diode group, and acquire first positioning information of each diode side by side in the detection area image;
  • An identification module configured to identify pins of the diodes arranged side by side in the image of the detection area, and acquire second positioning information of each diode side by side in the image of the detection area;
  • a positioning module configured to locate the according to the first positioning information and the second positioning information Detect each side of the diode in the area image.
  • extracting module specifically includes:
  • a detection area acquiring unit configured to acquire a detection area of the diode group from the circuit board image according to the preset labeling information of the diode group;
  • an extracting unit configured to expand a detection area of the diode group according to a preset expansion factor, and extract an image in the expanded detection area to obtain a detection area image of the diode group.
  • the matching module specifically includes:
  • a matching unit configured to respectively perform template matching on the template image of each diode in the diode group to obtain a position parameter of an area of the detection area image that matches each template image;
  • a comparison unit configured to compare each position parameter with an annotation value of the corresponding template image, and remove a position parameter whose difference is greater than a preset first threshold
  • the first positioning information acquiring unit is configured to calculate an average value of the remaining position parameters, and use the average value as first positioning information of each diode side by side in the detection area image.
  • the identifying module specifically includes:
  • a processing unit configured to sequentially perform grayscale processing, binarization processing, and morphological processing on the image of the detection area to obtain a binarized image
  • a detecting unit configured to detect a length of each connected region in the binarized image in a radial direction of the diode group
  • An identification unit configured to remove the connected area whose length exceeds a preset second threshold, and identify each remaining connected area as a pin area of each side-by-side diode;
  • the second positioning information acquiring unit is configured to acquire a central position parameter of each pin area, and calculate second positioning information of each of the side-by-side diodes according to the central position parameter and a preset diameter length of the diode.
  • the diode group includes N diodes arranged side by side in a vertical direction;
  • the first positioning information is an abscissa of an upper left corner vertex of each diode side by side in the detection area image, and the second positioning information is An ordinate of an upper left corner vertex of each of the diodes arranged side by side in the image of the detection area;
  • the positioning method and device for the side-by-side diode provided by the embodiment of the present invention can obtain the first positioning information and the second positioning information of each diode side by side from the detection area image of the diode group through the template matching method and the pin identification method respectively.
  • the respective diodes are located according to the first positioning information and the second positioning information, which effectively solves the misalignment phenomenon of the parallel positioning of the diodes, and greatly improves the accuracy of positioning of each diode in the diode group.
  • the detection area corresponding to the label information created during the manual plate making is expanded to avoid omission due to the side-by-side diode misalignment; when the first positioning information is acquired, the detection area is removed.
  • the regional position parameter with a large difference in the image improves the accuracy of the first positioning information.
  • FIG. 1 is a schematic flow chart of an embodiment of a method for positioning a side-by-side diode provided by the present invention
  • FIG. 2 is a schematic diagram of an embodiment of a detection area image in a positioning method of a side-by-side diode provided by the present invention
  • FIG. 3 is a schematic diagram of an embodiment of a binarized image in a positioning method of a side-by-side diode provided by the present invention
  • FIG. 4 is a schematic structural view of an embodiment of a positioning device for a side-by-side diode provided by the present invention.
  • a schematic flowchart of an embodiment of a method for locating a side-by-side diode provided by the present invention includes:
  • each diode arranged side by side in the detection area image is located.
  • an image of the detection area of the diode group in which N diodes are arranged side by side is extracted from the image.
  • the detection area image is matched with the template image of each diode, and the first positioning information of each diode is detected.
  • the second positioning information of each diode is detected, and then the image of the detection area is obtained according to the two positioning information. Position the corresponding diode in the middle.
  • the embodiment can locate the image of the specific circuit board to be detected, effectively solve the misalignment phenomenon of the side-by-side diode positioning, and greatly improve the accuracy of positioning of each diode in the diode group.
  • the extracting the detection area image of the diode group from the image of the circuit board includes:
  • the detection area of the diode group is expanded according to a preset expansion factor, and an image in the expanded detection area is extracted to obtain a detection area image of the diode group.
  • the position information of the diode position prepared during the manual plate making includes the height, the diameter length and the coordinates of the top left corner of each diode in the diode group, so that the label information of the first diode arranged in the diode group and the label information of the last diode are used.
  • the first diode 22 and the second diode 23 are arranged, as well as other electronic components 24, to avoid omission of the misaligned diode.
  • the matching the image of the detection area with the template image of each diode in the diode group, and acquiring the first positioning information of each diode arranged side by side in the image of the detection area specifically includes:
  • the average value of the remaining positional parameters is calculated and used as the first positioning information of the respective diodes side by side in the image of the detection area.
  • the first positioning information is the abscissa of the top left vertex of each diode side by side in the detection area image.
  • the template matching method is used to match the detection area image with the template image ⁇ Im 1 , . . . , Im N ⁇ of each diode in the diode group stored in the manual plate making, from the detection area image.
  • the remaining positional parameters ⁇ x 1 , . . . , x k ⁇ are averaged, and the obtained average value is the abscissa of the upper left vertex of the N diodes arranged side by side in the vertical direction, that is, the first positioning information.
  • the first positioning information is the ordinate of the upper left corner vertex of each diode in the detection area image, and the first positioning information acquiring method and the diode group of the vertical direction are arranged The acquisition method of a positioning information is the same.
  • the pin of each of the diodes in the image of the detection area is identified, and the second positioning information of each diode arranged side by side in the image of the detection area is obtained, which specifically includes:
  • R, G, and B respectively represent three color (red, green, and blue) channels of the detection area image
  • Im_gray is the processed gray scale image.
  • the Ostu automatic threshold selection method is used to binarize the gray image
  • the morphological processing method (opening operation) is used to perform an iterative process on the binarized image to remove the short lines in the vertical direction. The interference of the isolated point, thereby obtaining a binarized image.
  • the structural element of the open operation is defined as a rectangular structure having a size of 12 ⁇ 3.
  • the second positioning information is the ordinate of the upper left corner vertex of each of the diodes arranged side by side in the detection area image.
  • the length of each of the connected regions in the vertical direction (Y-axis direction), that is, the length of the white pixels connected in the vertical direction, is detected. If the length exceeds the preset second threshold, the connected area is not the pin area of the diode, and the connected area is removed; if the length does not exceed the preset second threshold, the connected area is a diode pin. Area, the connected area is reserved.
  • the second threshold is preferably D/3, and D is the diameter length of the diode.
  • the ordinate of the center point of the domain is the ordinate of the center point of the diode. Based on the ordinate of the center point of the diode and the length of the diameter of the diode, the ordinate of the apex of the upper left corner of the diode is calculated, which is the second positioning information of the diode. As shown in FIG.
  • the binarized image 31 is obtained. It is detected that the binarized image 31 has the first communication region 32, the second communication region 33, and the third communication region 34, and is vertically vertical to the first communication region 32, the second communication region 33, and the third communication region 34, respectively.
  • the length in the direction is detected. Wherein, the length of the first communication region 32 and the second communication region 33 in the vertical direction is less than the second threshold, and the length of the third communication region 34 in the vertical direction is greater than the second threshold, and the third communication region 34 is removed.
  • the second positioning information can be obtained by the diameter length.
  • the second positioning information is the abscissa of the upper left corner vertex of each diode in the detection area image, and the second positioning information acquisition method and the diode group of the vertical direction are arranged.
  • the method for obtaining the second positioning information is the same.
  • the diode group includes N diodes arranged side by side in a vertical direction;
  • the first positioning information is an abscissa of an upper left corner vertex of each diode side by side in the detection area image, and the second positioning information is An ordinate of an upper left corner vertex of each of the diodes arranged side by side in the image of the detection area;
  • each side of the detection area image can be calculated.
  • the position of the diodes thus positions the individual diodes side by side.
  • the image of the detection area can be rotated by 90 degrees, and then treated and positioned as a diode group in which N diodes are arranged side by side in the vertical direction. In After positioning each side-by-side diode, rotate the image of the detection area back.
  • the positioning method of the side-by-side diode can obtain the first positioning information and the second positioning information of each diode side by side from the detection area image of the diode group through the template matching method and the pin identification method, respectively.
  • a positioning information and a second positioning information are used to locate each diode, which effectively solves the side-by-side misalignment of the diode positioning, and greatly improves the accuracy of positioning of each diode in the diode group.
  • the detection area corresponding to the label information created during the manual plate making is expanded to avoid omission due to the side-by-side diode misalignment; when the first positioning information is acquired, the detection area is removed.
  • the regional position parameter with a large difference in the image improves the accuracy of the first positioning information.
  • the present invention also provides a positioning device for a side-by-side diode, which can implement all the processes of the positioning method of the side-by-side diode in the above embodiment.
  • FIG. 4 is a schematic structural diagram of an embodiment of a positioning device for a side-by-side diode provided by the present invention, including:
  • the extraction module 1 is configured to extract a detection area image of the diode group from the circuit board image; wherein the diode group comprises N diodes arranged side by side, N ⁇ 1;
  • a matching module 2 configured to match the detection area image with a template image of each diode in the diode group, and acquire first positioning information of each diode side by side in the detection area image;
  • the identification module 3 is configured to identify pins of the diodes arranged side by side in the image of the detection area, and acquire second positioning information of each diode arranged side by side in the image of the detection area;
  • the positioning module 4 is configured to locate each diode arranged side by side in the detection area image according to the first positioning information and the second positioning information.
  • extracting module specifically includes:
  • a detection area acquiring unit configured to acquire a detection area of the diode group from the circuit board image according to the preset labeling information of the diode group;
  • an extracting unit configured to expand a detection area of the diode group according to a preset expansion factor, and extract an image in the expanded detection area to obtain a detection area image of the diode group.
  • the matching module specifically includes:
  • a matching unit configured to respectively perform template matching on the template image of each diode in the diode group to obtain a position parameter of an area of the detection area image that matches each template image;
  • a comparison unit configured to compare each position parameter with an annotation value of the corresponding template image, and remove a position parameter whose difference is greater than a preset first threshold
  • the first positioning information acquiring unit is configured to calculate an average value of the remaining position parameters, and use the average value as first positioning information of each diode side by side in the detection area image.
  • the identifying module specifically includes:
  • a processing unit configured to sequentially perform grayscale processing, binarization processing, and morphological processing on the image of the detection area to obtain a binarized image
  • a detecting unit configured to detect a length of each connected region in the binarized image in a radial direction of the diode group
  • An identification unit configured to remove the connected area whose length exceeds a preset second threshold, and identify each remaining connected area as a pin area of each side-by-side diode;
  • the second positioning information acquiring unit is configured to acquire a central position parameter of each pin area, and calculate second positioning information of each of the side-by-side diodes according to the central position parameter and a preset diameter length of the diode.
  • the diode group includes N diodes arranged side by side in a vertical direction;
  • the first positioning information is an abscissa of an upper left corner vertex of each diode side by side in the detection area image, and the second positioning information is An ordinate of an upper left corner vertex of each of the diodes arranged side by side in the image of the detection area;
  • the positioning device for the side-by-side diode provided by the embodiment of the present invention can obtain the first positioning information and the second positioning information of each diode side by side from the detection area image of the diode group through the template matching method and the pin identification method, respectively. a positioning information and a second positioning information to locate each of the two The pole tube effectively solves the misalignment of the side-by-side diode positioning, which greatly improves the accuracy of positioning of each diode in the diode group. Moreover, when acquiring the detection area image of the diode group, the detection area corresponding to the label information created during the manual plate making is expanded to avoid omission due to the side-by-side diode misalignment; when the first positioning information is acquired, the detection area is removed. The regional position parameter with a large difference in the image improves the accuracy of the first positioning information.

Landscapes

  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biochemistry (AREA)
  • Analytical Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Supply And Installment Of Electrical Components (AREA)

Abstract

一种并排二极管的定位方法,包括:从电路板图像中提取出二极管组的检测区域图像;其中,所述二极管组包含并排排列的N个二极管,N≥1(S1);将所述检测区域图像与所述二极管组中各个二极管的模板图像进行匹配,获取所述检测区域图像中并排的各个二极管的第一定位信息(S2);对所述检测区域图像中并排的各个二极管的引脚进行识别,获取所述检测区域图像中并排的各个二极管的第二定位信息(S3);根据所述第一定位信息和所述第二定位信息,定位出所述检测区域图像中的各个二极管(S4)。相应的,还公开了一种并排二极管的定位装置,能够提高并排的各个二极管定位的准确性。

Description

一种并排二极管的定位方法及装置 技术领域
本发明涉及自动光学检查领域,尤其涉及一种并排二极管的定位方法及装置。
背景技术
自动光学检查(AOI,Automated Optical Inspection)是工业制作过程的必要环节,利用光学方式取得成品的表面状态,以影像处理来检测异物或表面瑕疵。手工插件二极管的错、漏、反检测是电路板缺陷检测领域中的一种常见应用,其检测方法为:机器通过摄像头自动扫描电路板获取电路板图像,提取每个二极管元件的局部图像,并通过图像处理技术,判断二极管元件是否存在错、漏、反缺陷,最后将疑似缺陷的元件显示或标记出来,方便查看与检修。
在电路板中有许多二极管并排排列形成并排二极管组,在检测并排二极管组中的各个二极管元件的缺陷之前,需要获取电路板上并排二极管组中的各个二极管元件的位置。现有的技术方案是将并排二极管组中的各个二极管元件当作普通的二极管元件来处理,其定位方法为:根据人工制版过程中标注的二极管位置信息,在待检测的(配准后)电路板的相同位置建立搜索区域,然后,利用模板匹配方法在该搜索区域内定位出二极管的位置。
但是,上述定位方法极其依赖人工制版过程中标注的二极管位置信息,而并排二极管组(以竖直并排排列的二极管为例),特别是高引脚的并排二极管组,在竖直方向上的位置变动较大,待检测电路板上的二极管的实际位置与人工制版过程中标注的二极管位置可能相差两个二极管的高度。因此,直接利用人工制版过程中标注的二极管位置信息进行搜索,极其容易发生错位现象,如定位到的二极管位置并不是所要定位的二极管的位置,而是其相邻的二极管的位置,从而导致二极管定位不准确。
发明内容
本发明实施例提出一种并排二极管的定位方法及装置,能够提高并排的各个二极管定位的准确性。
本发明实施例提供一种并排二极管的定位方法,包括:
从电路板图像中提取出二极管组的检测区域图像;其中,所述二极管组包含并排排列的N个二极管,N≥1;
将所述检测区域图像与所述二极管组中各个二极管的模板图像进行匹配,获取所述检测区域图像中并排的各个二极管的第一定位信息;
对所述检测区域图像中并排的各个二极管的引脚进行识别,获取所述检测区域图像中并排的各个二极管的第二定位信息;
根据所述第一定位信息和所述第二定位信息,定位出所述检测区域图像中并排的各个二极管。
进一步地,所述从电路板图像中提取出二极管组的检测区域图像,具体包括:
根据预置的所述二极管组的标注信息,从电路板图像中获取所述二极管组的检测区域;
根据预置的扩展倍数,对所述二极管组的检测区域进行扩展,并提取扩展后的检测区域中的图像,获得所述二极管组的检测区域图像。
进一步地,所述将所述检测区域图像与所述二极管组中各个二极管的模板图像进行匹配,获取所述检测区域图像中并排的各个二极管的第一定位信息,具体包括:
分别将所述检测区域图像与所述二极管组中各个二极管的模板图像进行模板匹配,获得所述检测区域图像中与各个模板图像相匹配的区域的位置参数;
将每个位置参数与其对应的模板图像的标注值进行比较,去除差值大于预设的第一阈值的位置参数;
计算剩余的位置参数的平均值,并将所述平均值作为所述检测区域图像中 并排的各个二极管的第一定位信息。
进一步地,所述对所述检测区域图像中并排的各个二极管的引脚进行识别,获取所述检测区域图像中并排的各个二极管的第二定位信息,具体包括:
对所述检测区域图像依次进行灰度化处理、二值化处理和形态学处理,获得二值化图像;
检测所述二值化图像中的各个连通区域在所述二极管组的径向上的长度;
去除所述长度超过预设的第二阈值的连通区域,并将剩余的各个连通区域识别为所述并排的各个二极管的引脚区域;
获取各个引脚区域的中心位置参数,并根据所述中心位置参数和预设的二极管的直径长度,计算获得所述并排的各个二极管的第二定位信息。
优选地,所述二极管组包含竖直方向并排排列的N个二极管;所述第一定位信息为所述检测区域图像中并排的各个二极管的左上角顶点的横坐标,所述第二定位信息为所述检测区域图像中并排的各个二极管的左上角顶点的纵坐标;
根据所述第一定位信息和所述第二定位信息,定位出所述检测区域图像中并排的各个二极管,具体包括:
所述根据预设的二极管的高度、直径长度,以及所述检测区域图像中并排的各个二极管的左上角顶点的横坐标和纵坐标,定位出所述检测区域图像中并排的各个二极管。
相应的,本发明实施例还提供一种并排二极管的定位装置,包括:
提取模块,用于从电路板图像中提取出二极管组的检测区域图像;其中,所述二极管组包含并排排列的N个二极管,N≥1;
匹配模块,用于将所述检测区域图像与所述二极管组中各个二极管的模板图像进行匹配,获取所述检测区域图像中并排的各个二极管的第一定位信息;
识别模块,用于对所述检测区域图像中并排的各个二极管的引脚进行识别,获取所述检测区域图像中并排的各个二极管的第二定位信息;以及,
定位模块,用于根据所述第一定位信息和所述第二定位信息,定位出所述 检测区域图像中并排的各个二极管。
进一步地,所述提取模块具体包括:
检测区域获取单元,用于根据预置的所述二极管组的标注信息,从电路板图像中获取所述二极管组的检测区域;以及,
提取单元,用于根据预置的扩展倍数,对所述二极管组的检测区域进行扩展,并提取扩展后的检测区域中的图像,获得所述二极管组的检测区域图像。
进一步地,所述匹配模块具体包括:
匹配单元,用于分别将所述检测区域图像与所述二极管组中各个二极管的模板图像进行模板匹配,获得所述检测区域图像中与各个模板图像相匹配的区域的位置参数;
比较单元,用于将每个位置参数与其对应的模板图像的标注值进行比较,去除差值大于预设的第一阈值的位置参数;以及,
第一定位信息获取单元,用于计算剩余的位置参数的平均值,并将所述平均值作为所述检测区域图像中并排的各个二极管的第一定位信息。
进一步地,所述识别模块具体包括:
处理单元,用于对所述检测区域图像依次进行灰度化处理、二值化处理和形态学处理,获得二值化图像;
检测单元,用于检测所述二值化图像中的各个连通区域在所述二极管组的径向上的长度;
识别单元,用于去除所述长度超过预设的第二阈值的连通区域,并将剩余的各个连通区域识别为所述并排的各个二极管的引脚区域;以及,
第二定位信息获取单元,用于获取各个引脚区域的中心位置参数,并根据所述中心位置参数和预设的二极管的直径长度,计算获得所述并排的各个二极管的第二定位信息。
优选地,所述二极管组包含竖直方向并排排列的N个二极管;所述第一定位信息为所述检测区域图像中并排的各个二极管的左上角顶点的横坐标,所述第二定位信息为所述检测区域图像中并排的各个二极管的左上角顶点的纵坐标;
所述根据预设的二极管的高度、直径长度,以及所述检测区域图像中并排的各个二极管的左上角顶点的横坐标和纵坐标,定位出所述检测区域图像中并排的各个二极管。
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并排二极管的定位方法及装置,能够分别通过模板匹配方法、引脚识别方法从二极管组的检测区域图像中获取并排的各个二极管的第一定位信息和第二定位信息,进而根据第一定位信息和第二定位信息来定位出各个二极管,有效解决并排的二极管定位的错位现象,极大提高二极管组中各个二极管定位的准确性。
而且,在获取二极管组的检测区域图像时,对人工制版时制作的标注信息所对应的检测区域进行扩展,避免由于并排的二极管错位而导致的遗漏;在获取第一定位信息时,去除检测区域图像中差值较大的区域位置参数,提高第一定位信息的准确性。
附图说明
图1是本发明提供的并排二极管的定位方法的一个实施例的流程示意图;
图2是本发明提供的并排二极管的定位方法中检测区域图像的一个实施例的示意图;
图3是本发明提供的并排二极管的定位方法中二值化图像的一个实施例的示意图;
图4是本发明提供的并排二极管的定位装置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,本发明提供的并排二极管的定位方法的一个实施例的流程示意图,包括:
S1、从电路板图像中提取出二极管组的检测区域图像;其中,所述二极管组包含并排排列的N个二极管,N≥1;
S2、将所述检测区域图像与所述二极管组中各个二极管的模板图像进行匹配,获取所述检测区域图像中并排的各个二极管的第一定位信息;
S3、对所述检测区域图像中并排的各个二极管的引脚进行识别,获取所述检测区域图像中并排的各个二极管的第二定位信息;
S4、根据所述第一定位信息和所述第二定位信息,定位出所述检测区域图像中并排的各个二极管。
需要说明的是,通过摄像头自动扫描出待检测的电路板的图像后,从图像中提取出由N个二极管并排排列的二极管组的检测区域图像。检测区域图像通过与各个二极管的模板图像进行匹配,检测出各个二极管的第一定位信息,通过对引脚的识别,检测出各个二极管的第二定位信息,进而根据两个定位信息从检测区域图像中定位出相应的二极管。本实施例能够针对具体的待检测电路板的图像进行定位,有效解决并排的二极管定位的错位现象,极大提高二极管组中各个二极管定位的准确性。
进一步地,所述从电路板图像中提取出二极管组的检测区域图像,具体包括:
根据预置的所述二极管组的标注信息,从电路板图像中获取所述二极管组的检测区域;
根据预置的扩展倍数,对所述二极管组的检测区域进行扩展,并提取扩展后的检测区域中的图像,获得所述二极管组的检测区域图像。
其中,人工制版时制作的二极管位置标注信息包含二极管组中各个二极管的高度、直径长度和左上角顶点的坐标,从而根据二极管组中排列的第一个二极管的标注信息和最后一个二极管的标注信息,计算出二极管组的区域大小,从而获得二极管组所在的检测区域。在获得二极管组的检测区域后,对该检测 区域进行扩展。如图2所示,对二极管组的检测区域在竖直方向(Y轴方向)上扩展1.5倍,在水平方向(X轴方向)扩展0.5倍后,获取的检测区域图像21包括竖直方向并排排列的第一二极管22和第二二极管23,以及其他电子元件24,从而避免错位二极管的遗漏。
进一步地,所述将所述检测区域图像与所述二极管组中各个二极管的模板图像进行匹配,获取所述检测区域图像中并排的各个二极管的第一定位信息,具体包括:
分别将所述检测区域图像与所述二极管组中各个二极管的模板图像进行模板匹配,获得所述检测区域图像中与各个模板图像相匹配的区域的位置参数;
将每个位置参数与其对应的模板图像的标注值进行比较,去除差值大于预设的第一阈值的位置参数;
计算剩余的位置参数的平均值,并将所述平均值作为所述检测区域图像中并排的各个二极管的第一定位信息。
需要说明的是,若二极管组包含竖直方向并排排列的N个二极管,则第一定位信息为检测区域图像中并排的各个二极管的左上角顶点的横坐标。在获取第一定位信息时,采用模板匹配方法,将检测区域图像分别与人工制版时存储的二极管组中各个二极管的模板图像{Im1,...,ImN}进行匹配,从检测区域图像中找到与各个模板图像相匹配的区域,以获取各个相匹配区域的左上角顶点的坐标{(x1,y1),...,(xN,yN)},并保留各个相匹配区域的左上角顶点的横坐标{x1,...,xN},即为各个相匹配区域的位置参数。然后,将各个位置参数与其对应的模板图像的标注值,即模板图像的左上角顶点的横坐标进行比较,去除相差较大的位置参数,例如,去除相差大于10个像素的位置参数,从而获得剩余的位置参数{x1,...,xk}。对剩余的位置参数{x1,...,xk}取平均值,获得的平均值为竖直方向并排排列的N个二极管的左上角顶点的横坐标,即第一定位信息。若二极管组包含水平方向并排排列的N个二极管,则第一定位信息为检测区域图像中各个二极管的左上角顶点的纵坐标,其第一定位信息获取方法与竖直方向排列的二极管组的第一定位信息的获取方法相同。
进一步地,所述对所述检测区域图像中并排的各个二极管的引脚进行识别,获取所述检测区域图像中并排的各个二极管的第二定位信息,具体包括:
对所述检测区域图像依次进行灰度化处理、二值化处理和形态学处理,获得二值化图像;
检测所述二值化图像中的各个连通区域在所述二极管组的径向上的长度;
去除所述长度超过预设的第二阈值的连通区域,并将剩余的各个连通区域识别为所述并排的各个二极管的引脚区域;
获取各个引脚区域的中心位置参数,并根据所述中心位置参数和预设的二极管的直径长度,计算获得所述并排的各个二极管的第二定位信息。
需要说明的是,在获取各个二极管的第二定位信息时,先对检测区域图像进行灰度化处理,其公式为Im_gray=0.3*R+0.59*G+0.11*B。其中,R、G、B分别表示检测区域图像的三个彩色(红、绿、蓝)通道,Im_gray为处理后的灰度图像。然后,采用Ostu自动阈值选择方法对灰度图像进行二值化处理,并采用形态学处理方法(开运算)对二值化处理后的图像进行一次迭代处理,去除掉竖直方向的短线、一些孤立点的干扰,从而获得二值化图像。其中,开运算的结构元素定义为大小为12×3的矩形结构。在形态学处理之后,采用Hough变换方法对二值化图像进行直线检测,检测出二值化图像中为直线型的连通区域。
若二极管组包含竖直方向并排排列的N个二极管,则第二定位信息为检测区域图像中并排的各个二极管的左上角顶点的纵坐标。在检测出各个连通区域后,检测各个连通区域在竖直方向(Y轴方向)的长度,即在竖直方向上相连白色像素所具有的长度。若该长度超过预设的第二阈值,则说明该连通区域不是二极管的引脚区域,去除该连通区域;若该长度未超过预设的第二阈值,则说明该连通区域是二极管的引脚区域,保留该连通区域。其中,第二阈值优选为D/3,D为二极管的直径长度。在检测出各个二极管的引脚区域后,对每个引脚区域,获取竖直方向上的所有纵坐标,进而求取所有纵坐标的平均值,获取该引脚区域的中心点的纵坐标作为该引脚区域的中心位置参数。其中,引脚区 域的中心点的纵坐标即为二极管中心点的纵坐标,再根据二极管中心点的纵坐标和二极管的直径长度,计算出二极管左上角顶点的纵坐标,即为二极管的第二定位信息。如图3所示,在对检测区域图像进行灰度化处理、二值化处理和形态学处理后,获得二值化图像31。检测出二值化图像31中具有第一连通区域32、第二连通区域33和第三连通区域34,并分别对第一连通区域32、第二连通区域33和第三连通区域34在竖直方向上的长度进行检测。其中,第一连通区域32和第二连通区域33在竖直方向上的长度小于第二阈值,第三连通区域34在竖直方向上的长度大于第二阈值,则去除第三连通区域34。分别计算第一连通区域32和第二连通区域33的中心点的纵坐标,即为其对应的第一二极管22和第二二极管23的中心点的纵坐标,进而再根据二极管的直径长度即可获取第二定位信息。
若二极管组包含水平方向并排排列的N个二极管,则第二定位信息为检测区域图像中各个二极管的左上角顶点的横坐标,其第二定位信息获取方法与竖直方向排列的二极管组的第二定位信息的获取方法相同。
优选地,所述二极管组包含竖直方向并排排列的N个二极管;所述第一定位信息为所述检测区域图像中并排的各个二极管的左上角顶点的横坐标,所述第二定位信息为所述检测区域图像中并排的各个二极管的左上角顶点的纵坐标;
根据所述第一定位信息和所述第二定位信息,定位出所述检测区域图像中并排的各个二极管,具体包括:
所述根据预设的二极管的高度、直径长度,以及所述检测区域图像中并排的各个二极管的左上角顶点的横坐标和纵坐标,定位出所述检测区域图像中并排的各个二极管。
需要说明的是,在检测出二极管组中各个二极管的左上角顶点的横坐标和纵坐标后,再根据人工制版时的各个二极管的高度和直径长度,即可计算出检测区域图像中并排的各个二极管的位置,从而定位出并排的各个二极管。另外,针对N个二极管水平方向并排排列的二极管组,可将其检测区域图像旋转90度后,将其当做N个二极管竖直方向并排排列的二极管组来进行处理和定位。在 定位出并排的各个二极管后,再将其检测区域图像旋转回去即可。
本发明实施例提供的并排二极管的定位方法,能够分别通过模板匹配方法、引脚识别方法从二极管组的检测区域图像中获取并排的各个二极管的第一定位信息和第二定位信息,进而根据第一定位信息和第二定位信息来定位出各个二极管,有效解决并排的二极管定位的错位现象,极大提高二极管组中各个二极管定位的准确性。而且,在获取二极管组的检测区域图像时,对人工制版时制作的标注信息所对应的检测区域进行扩展,避免由于并排的二极管错位而导致的遗漏;在获取第一定位信息时,去除检测区域图像中差值较大的区域位置参数,提高第一定位信息的准确性。
相应的,本发明还提供一种并排二极管的定位装置,能够实现上述实施例中的并排二极管的定位方法的所有流程。
参见图4,是本发明提供的并排二极管的定位装置的一个实施例的结构示意图,包括:
提取模块1,用于从电路板图像中提取出二极管组的检测区域图像;其中,所述二极管组包含并排排列的N个二极管,N≥1;
匹配模块2,用于将所述检测区域图像与所述二极管组中各个二极管的模板图像进行匹配,获取所述检测区域图像中并排的各个二极管的第一定位信息;
识别模块3,用于对所述检测区域图像中并排的各个二极管的引脚进行识别,获取所述检测区域图像中并排的各个二极管的第二定位信息;以及,
定位模块4,用于根据所述第一定位信息和所述第二定位信息,定位出所述检测区域图像中并排的各个二极管。
进一步地,所述提取模块具体包括:
检测区域获取单元,用于根据预置的所述二极管组的标注信息,从电路板图像中获取所述二极管组的检测区域;以及,
提取单元,用于根据预置的扩展倍数,对所述二极管组的检测区域进行扩展,并提取扩展后的检测区域中的图像,获得所述二极管组的检测区域图像。
进一步地,所述匹配模块具体包括:
匹配单元,用于分别将所述检测区域图像与所述二极管组中各个二极管的模板图像进行模板匹配,获得所述检测区域图像中与各个模板图像相匹配的区域的位置参数;
比较单元,用于将每个位置参数与其对应的模板图像的标注值进行比较,去除差值大于预设的第一阈值的位置参数;以及,
第一定位信息获取单元,用于计算剩余的位置参数的平均值,并将所述平均值作为所述检测区域图像中并排的各个二极管的第一定位信息。
进一步地,所述识别模块具体包括:
处理单元,用于对所述检测区域图像依次进行灰度化处理、二值化处理和形态学处理,获得二值化图像;
检测单元,用于检测所述二值化图像中的各个连通区域在所述二极管组的径向上的长度;
识别单元,用于去除所述长度超过预设的第二阈值的连通区域,并将剩余的各个连通区域识别为所述并排的各个二极管的引脚区域;以及,
第二定位信息获取单元,用于获取各个引脚区域的中心位置参数,并根据所述中心位置参数和预设的二极管的直径长度,计算获得所述并排的各个二极管的第二定位信息。
优选地,所述二极管组包含竖直方向并排排列的N个二极管;所述第一定位信息为所述检测区域图像中并排的各个二极管的左上角顶点的横坐标,所述第二定位信息为所述检测区域图像中并排的各个二极管的左上角顶点的纵坐标;
所述根据预设的二极管的高度、直径长度,以及所述检测区域图像中并排的各个二极管的左上角顶点的横坐标和纵坐标,定位出所述检测区域图像中并排的各个二极管。
本发明实施例提供的并排二极管的定位装置,能够分别通过模板匹配方法、引脚识别方法从二极管组的检测区域图像中获取并排的各个二极管的第一定位信息和第二定位信息,进而根据第一定位信息和第二定位信息来定位出各个二 极管,有效解决并排的二极管定位的错位现象,极大提高二极管组中各个二极管定位的准确性。而且,在获取二极管组的检测区域图像时,对人工制版时制作的标注信息所对应的检测区域进行扩展,避免由于并排的二极管错位而导致的遗漏;在获取第一定位信息时,去除检测区域图像中差值较大的区域位置参数,提高第一定位信息的准确性。
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. 一种并排二极管的定位方法,其特征在于,包括:
    从电路板图像中提取出二极管组的检测区域图像;其中,所述二极管组包含并排排列的N个二极管,N≥1;
    将所述检测区域图像与所述二极管组中各个二极管的模板图像进行匹配,获取所述检测区域图像中并排的各个二极管的第一定位信息;
    对所述检测区域图像中并排的各个二极管的引脚进行识别,获取所述检测区域图像中并排的各个二极管的第二定位信息;
    根据所述第一定位信息和所述第二定位信息,定位出所述检测区域图像中并排的各个二极管。
  2. 如权利要求1所述的并排二极管的定位方法,其特征在于,所述从电路板图像中提取出二极管组的检测区域图像,具体包括:
    根据预置的所述二极管组的标注信息,从电路板图像中获取所述二极管组的检测区域;
    根据预置的扩展倍数,对所述二极管组的检测区域进行扩展,并提取扩展后的检测区域中的图像,获得所述二极管组的检测区域图像。
  3. 如权利要求1所述的并排二极管的定位方法,其特征在于,所述将所述检测区域图像与所述二极管组中各个二极管的模板图像进行匹配,获取所述检测区域图像中并排的各个二极管的第一定位信息,具体包括:
    分别将所述检测区域图像与所述二极管组中各个二极管的模板图像进行模板匹配,获得所述检测区域图像中与各个模板图像相匹配的区域的位置参数;
    将每个位置参数与其对应的模板图像的标注值进行比较,去除差值大于预设的第一阈值的位置参数;
    计算剩余的位置参数的平均值,并将所述平均值作为所述检测区域图像中并排的各个二极管的第一定位信息。
  4. 如权利要求1所述的并排二极管的定位方法,其特征在于,所述对所述检测区域图像中并排的各个二极管的引脚进行识别,获取所述检测区域图像中并排的各个二极管的第二定位信息,具体包括:
    对所述检测区域图像依次进行灰度化处理、二值化处理和形态学处理,获得二值化图像;
    检测所述二值化图像中的各个连通区域在所述二极管组的径向上的长度;
    去除所述长度超过预设的第二阈值的连通区域,并将剩余的各个连通区域识别为所述并排的各个二极管的引脚区域;
    获取各个引脚区域的中心位置参数,并根据所述中心位置参数和预设的二极管的直径长度,计算获得所述并排的各个二极管的第二定位信息。
  5. 如权利要求1至4任一项所述的并排二极管的定位方法,其特征在于,所述二极管组包含竖直方向并排排列的N个二极管;所述第一定位信息为所述检测区域图像中并排的各个二极管的左上角顶点的横坐标,所述第二定位信息为所述检测区域图像中并排的各个二极管的左上角顶点的纵坐标;
    根据所述第一定位信息和所述第二定位信息,定位出所述检测区域图像中并排的各个二极管,具体包括:
    所述根据预设的二极管的高度、直径长度,以及所述检测区域图像中并排的各个二极管的左上角顶点的横坐标和纵坐标,定位出所述检测区域图像中并排的各个二极管。
  6. 一种并排二极管的定位装置,其特征在于,包括:
    提取模块,用于从电路板图像中提取出二极管组的检测区域图像;其中,所述二极管组包含并排排列的N个二极管,N≥1;
    匹配模块,用于将所述检测区域图像与所述二极管组中各个二极管的模板图像进行匹配,获取所述检测区域图像中并排的各个二极管的第一定位信息;
    识别模块,用于对所述检测区域图像中并排的各个二极管的引脚进行识别,获取所述检测区域图像中并排的各个二极管的第二定位信息;以及,
    定位模块,用于根据所述第一定位信息和所述第二定位信息,定位出所述检测区域图像中并排的各个二极管。
  7. 如权利要求6所述的并排二极管的定位装置,其特征在于,所述提取模块具体包括:
    检测区域获取单元,用于根据预置的所述二极管组的标注信息,从电路板图像中获取所述二极管组的检测区域;以及,
    提取单元,用于根据预置的扩展倍数,对所述二极管组的检测区域进行扩展,并提取扩展后的检测区域中的图像,获得所述二极管组的检测区域图像。
  8. 如权利要求6所述的并排二极管的定位装置,其特征在于,所述匹配模块具体包括:
    匹配单元,用于分别将所述检测区域图像与所述二极管组中各个二极管的模板图像进行模板匹配,获得所述检测区域图像中与各个模板图像相匹配的区域的位置参数;
    比较单元,用于将每个位置参数与其对应的模板图像的标注值进行比较,去除差值大于预设的第一阈值的位置参数;以及,
    第一定位信息获取单元,用于计算剩余的位置参数的平均值,并将所述平均值作为所述检测区域图像中并排的各个二极管的第一定位信息。
  9. 如权利要求6所述的并排二极管的定位装置,其特征在于,所述识别模块具体包括:
    处理单元,用于对所述检测区域图像依次进行灰度化处理、二值化处理和形态学处理,获得二值化图像;
    检测单元,用于检测所述二值化图像中的各个连通区域在所述二极管组的 径向上的长度;
    识别单元,用于去除所述长度超过预设的第二阈值的连通区域,并将剩余的各个连通区域识别为所述并排的各个二极管的引脚区域;以及,
    第二定位信息获取单元,用于获取各个引脚区域的中心位置参数,并根据所述中心位置参数和预设的二极管的直径长度,计算获得所述并排的各个二极管的第二定位信息。
  10. 如权利要求6至9任一项所述的并排二极管的定位装置,其特征在于,所述二极管组包含竖直方向并排排列的N个二极管;所述第一定位信息为所述检测区域图像中并排的各个二极管的左上角顶点的横坐标,所述第二定位信息为所述检测区域图像中并排的各个二极管的左上角顶点的纵坐标;
    所述根据预设的二极管的高度、直径长度,以及所述检测区域图像中并排的各个二极管的左上角顶点的横坐标和纵坐标,定位出所述检测区域图像中并排的各个二极管。
PCT/CN2016/096752 2015-12-22 2016-08-25 一种并排二极管的定位方法及装置 WO2017107529A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510981722.4A CN105404900B (zh) 2015-12-22 2015-12-22 一种并排二极管的定位方法及装置
CN201510981722.4 2015-12-22

Publications (1)

Publication Number Publication Date
WO2017107529A1 true WO2017107529A1 (zh) 2017-06-29

Family

ID=55470375

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/096752 WO2017107529A1 (zh) 2015-12-22 2016-08-25 一种并排二极管的定位方法及装置

Country Status (2)

Country Link
CN (1) CN105404900B (zh)
WO (1) WO2017107529A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112991323A (zh) * 2021-04-10 2021-06-18 河南巨捷电子科技有限公司 基于视觉感知的光伏电站组件阵列错位检测方法与系统

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105404900B (zh) * 2015-12-22 2017-12-19 广州视源电子科技股份有限公司 一种并排二极管的定位方法及装置
CN106503737B (zh) * 2016-10-20 2019-03-05 广州视源电子科技股份有限公司 一种电子元件定位方法及装置
CN108072662A (zh) * 2017-11-10 2018-05-25 长春理工大学 基于机器视觉的排针缺损检测方法及装置
CN114757872A (zh) * 2021-01-08 2022-07-15 长鑫存储技术有限公司 芯片采集方法和芯片定位方法

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101477063A (zh) * 2009-01-22 2009-07-08 北京星河泰视特科技有限公司 印刷电路板的检测方法及光学检测仪
CN101995223A (zh) * 2009-08-25 2011-03-30 比亚迪股份有限公司 一种芯片外观检测方法及系统
US20130114882A1 (en) * 2011-11-07 2013-05-09 Omron Corporation System, device, and method for assisting visual check operation of inspection result
CN103413291A (zh) * 2013-06-07 2013-11-27 西华大学 一种图像定位方法
US20140369593A1 (en) * 2012-03-08 2014-12-18 Kla-Tencor Corporation Detection of thin lines for selective sensitivity during reticle inspection using processed images
CN104459421A (zh) * 2014-12-30 2015-03-25 广州视源电子科技股份有限公司 一种二极管极性检测方法与系统
CN105139399A (zh) * 2015-08-25 2015-12-09 广州视源电子科技股份有限公司 一种二极管极性检测方法及装置
CN105404900A (zh) * 2015-12-22 2016-03-16 广州视源电子科技股份有限公司 一种并排二极管的定位方法及装置

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140064596A1 (en) * 2012-08-29 2014-03-06 Micron Technology, Inc. Descriptor guided fast marching method for analyzing images and systems using the same
JP2014119427A (ja) * 2012-12-19 2014-06-30 Fujitsu Semiconductor Ltd スポット探索装置、スポット探索方法
CN104463178A (zh) * 2014-12-29 2015-03-25 广州视源电子科技股份有限公司 电子元件识别方法和系统

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101477063A (zh) * 2009-01-22 2009-07-08 北京星河泰视特科技有限公司 印刷电路板的检测方法及光学检测仪
CN101995223A (zh) * 2009-08-25 2011-03-30 比亚迪股份有限公司 一种芯片外观检测方法及系统
US20130114882A1 (en) * 2011-11-07 2013-05-09 Omron Corporation System, device, and method for assisting visual check operation of inspection result
US20140369593A1 (en) * 2012-03-08 2014-12-18 Kla-Tencor Corporation Detection of thin lines for selective sensitivity during reticle inspection using processed images
CN103413291A (zh) * 2013-06-07 2013-11-27 西华大学 一种图像定位方法
CN104459421A (zh) * 2014-12-30 2015-03-25 广州视源电子科技股份有限公司 一种二极管极性检测方法与系统
CN105139399A (zh) * 2015-08-25 2015-12-09 广州视源电子科技股份有限公司 一种二极管极性检测方法及装置
CN105404900A (zh) * 2015-12-22 2016-03-16 广州视源电子科技股份有限公司 一种并排二极管的定位方法及装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112991323A (zh) * 2021-04-10 2021-06-18 河南巨捷电子科技有限公司 基于视觉感知的光伏电站组件阵列错位检测方法与系统
CN112991323B (zh) * 2021-04-10 2022-12-13 中电(福建)电力开发有限公司 基于视觉感知的光伏电站组件阵列错位检测方法与系统

Also Published As

Publication number Publication date
CN105404900B (zh) 2017-12-19
CN105404900A (zh) 2016-03-16

Similar Documents

Publication Publication Date Title
WO2017107529A1 (zh) 一种并排二极管的定位方法及装置
TWI757825B (zh) 基於假點缺陷檢測之pcb檢修系統及檢修方法
TWI787296B (zh) 光學檢測方法、光學檢測裝置及光學檢測系統
WO2017020559A1 (zh) 一种基于行列直线聚类的多类型bga芯片视觉识别方法
WO2018010391A1 (zh) 一种板卡的检测方法及装置
CN109472271B (zh) 印刷电路板图像轮廓提取方法及装置
CN109900711A (zh) 基于机器视觉的工件缺陷检测方法
WO2017181724A1 (zh) 电子元件漏件检测方法和系统
WO2017092427A1 (zh) 一种电子元件定位方法及装置
WO2017177717A1 (zh) 基于颜色和梯度的元件定位方法和系统
CN106651857B (zh) 一种印刷电路板贴片缺陷检测方法
WO2018068417A1 (zh) 元件缺陷检测方法和系统
WO2017071406A1 (zh) 金针类元件的引脚检测方法和系统
TWI667470B (zh) Wafer chipping defect detection method
CN108445010B (zh) 自动光学检测方法及装置
TW201741649A (zh) 缺陷檢查方法及缺陷檢查系統
WO2017050088A1 (zh) 一种电子元件定位方法及装置
CN116168218A (zh) 一种基于图像识别技术的电路板故障诊断方法
WO2014103617A1 (ja) 位置合せ装置、欠陥検査装置、位置合せ方法、及び制御プログラム
WO2022222467A1 (zh) 开口圆环工件外观缺陷检测方法、系统及计算机存储介质
JP6253490B2 (ja) 巻線検査方法および巻線検査装置
WO2017067320A1 (zh) 一种焊点定位方法及装置
WO2018068414A1 (zh) 色环电阻的检测方法、装置和自动光学检测系统
CN105548210B (zh) 基于机器视觉的美标电源延长线的检测方法
CN110148141A (zh) 一种丝印滤光片小片检测计数方法及设备

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: 16877341

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 16/11/2018)

122 Ep: pct application non-entry in european phase

Ref document number: 16877341

Country of ref document: EP

Kind code of ref document: A1