WO2017071406A1 - 金针类元件的引脚检测方法和系统 - Google Patents
金针类元件的引脚检测方法和系统 Download PDFInfo
- Publication number
- WO2017071406A1 WO2017071406A1 PCT/CN2016/098223 CN2016098223W WO2017071406A1 WO 2017071406 A1 WO2017071406 A1 WO 2017071406A1 CN 2016098223 W CN2016098223 W CN 2016098223W WO 2017071406 A1 WO2017071406 A1 WO 2017071406A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- gold
- pin
- gold needle
- area
- point
- Prior art date
Links
Images
Classifications
-
- 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
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color 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]
-
- 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
- G06T2207/30148—Semiconductor; IC; Wafer
Definitions
- the invention relates to the field of automatic optical detection technology, and in particular to a pin detection method and system for a gold needle component.
- AOI Automatic Optical Inspection
- the more mature AOI equipment on the market is mostly used to detect the defects of the patch.
- the AOI equipment for the mobile phone/machine plug-in link is still weak, and the gold needle component belongs to the plug-in category. In the factory, it is mainly dependent on manual visual inspection for the presence or absence of defects in the gold needle components, and the detection efficiency is low.
- a pin detection method for a gold needle component includes the following steps:
- a pin detection system for a gold needle component comprising:
- a positioning device configured to acquire a gray value of each pixel in the image, and locate an area where the pin of the gold needle component is located from the image according to the gray value, and set the area as the golden needle The gold needle body area of the component;
- a detecting device configured to obtain a projection of a pin of the gold needle component on the circuit board from the gold pin body region, and set the projection to a gold pin point for selecting the gold needle component;
- a calculating device configured to calculate an area of the gold pin point, and determine whether the pin of the gold needle component is complete according to the area of the gold pin point.
- the pin detecting method and system for the gold needle component obtains an image of the gold needle component to be tested; and locates the gold needle body region of the gold needle component according to the gray value of each pixel point in the image; The gold pin point of the gold needle component is selected in the area; and the pin of the gold pin component is judged according to the area of the gold pin point, and the automatic detection of the pin of the gold pin component is realized, thereby effectively improving the detection efficiency.
- FIG. 1 is a flow chart of a pin detecting method of a gold needle component of an embodiment
- Figure 2 is a grayscale diagram of a gold needle component of one embodiment
- Figure 3 is a candidate region of the gold needle body of one embodiment
- Figure 4 is a gold needle body area of one embodiment
- Figure 5 is a gold needle point inspection result of one embodiment
- FIG. 6 is a schematic view showing the division of a gold needle point in an embodiment
- Fig. 7 is a schematic structural view of a pin detecting system of a gold needle component of one embodiment.
- the pin detection method of the gold needle component may include the following steps:
- an image acquiring device may be perpendicular to an pin of the gold needle component to obtain an image of the gold needle component to be tested, so as to obtain a pin of the gold needle component to be tested in the image. Projected as a point.
- the image acquired by the image acquisition device may be a multi-channel color image, and at this time, the color image needs to be converted into a grayscale image.
- the gray scale of the gold needle component is shown in Figure 2.
- the image acquisition device can be a high definition camera.
- it may be a camera with a pixel of 10 million or more.
- the image acquisition device may set an auto focus function.
- the image acquired by step S1 generally includes some background information, so it is first necessary to extract the body position of the golden needle element.
- step S2 the gradation value of the image acquired in step S1 is binarized to obtain a binary image.
- the processing method is as follows:
- T 1 is the set threshold
- (x, y) is the coordinates of the pixel points in the image
- I(x, y) is the true gray value of the pixel with the coordinates (x, y)
- M(x, y) is a binarized gray value of a pixel having coordinates (x, y)
- a candidate region of the gold needle body can be obtained, as shown in FIG.
- the above candidate regions usually contain some interference information, such as a region on the background that is closer to the gray value of the gold needle main needle. Therefore, the scheme only selects the outer section of the binary image as the real gold needle body region, wherein the outer section is the largest connected region in the binary image, such as the region 301 in FIG. In FIG. 3, the area 301 is a rectangular area included in the white square in FIG. Finally, according to the rectangular region, the gold needle body region is intercepted in the original grayscale image, that is, the region corresponding to the outer segment region is extracted in the grayscale image, and the region corresponding to the outer segment region is used as the gold needle component
- the main body of the gold needle is shown in Figure 4.
- the gold pin point of the gold needle component can be further selected from the gold needle body region.
- the gold pin point of the gold needle component can be selected from the gold needle body region by a corner detection algorithm.
- the gold needle point is selected by the corner detection algorithm, which improves the accuracy of the gold needle point selection.
- other algorithms may be used to select the gold pin point of the gold needle component from the gold needle body region. The results of the gold needle check are shown in Figure 5.
- step S4 after the gold pin point is selected, the area of the gold pin point can be calculated, and whether the pin of the gold pin type component is intact is determined according to the area of the gold pin point.
- the pin distribution of the gold needle component is uniform. Therefore, the main body area of the gold needle can be divided into several sub-regions according to the actual number of pins, the maximum golden needle point of each sub-region is extracted, and the maximum golden needle point is calculated.
- the area of the largest gold needle point is the largest gold needle point in each sub-area. If the area of the largest gold pin point in a sub-area is less than a preset value, it is determined that the pin of the gold pin type component is incomplete.
- the schematic diagram of the division of the gold needle point is shown in Fig. 6.
- Fig. 6 it can be seen that there is no gold needle point in the area A1, and therefore, it is determined that there is a missing needle in the area. In fact, if there is a gold needle point in a certain area, but the area of the gold needle point is small, it can be determined that there is a broken needle in the area.
- the pin detecting method of the gold needle component obtains an image of the gold needle component; the gold needle body region of the gold needle component is located according to the gray value of each pixel in the image; and the gold needle body region is selected from the gold needle body region
- the golden needle point of the gold needle component is described; and according to the area of the gold needle point, whether the pin of the gold needle component is complete, the automatic detection of the pin of the gold needle component is realized, and the detection efficiency is effectively improved.
- Fig. 7 is a schematic structural view of a pin detecting system of a gold needle component of one embodiment.
- the pin detection system of the gold needle component of the present invention may include:
- the obtaining device 10 is configured to acquire an image of a gold needle component to be tested on the circuit board;
- the locating device 20 is configured to acquire a gradation value of each pixel in the image, and locate an area where the pin of the gold needle component is located from the image according to the gradation value, and set the area to the The gold needle body area of the gold needle component;
- a detecting device 30 configured to acquire a projection of a pin of the gold needle component on the circuit board from the gold pin body region, and set the projection to a gold pin point for selecting the gold needle component;
- the calculating device 40 is configured to calculate an area of the gold pin point, and determine whether the pin of the gold pin type component is complete according to the area of the gold pin point.
- the obtaining device 10 may include an acquiring unit 101 configured to acquire an image of the gold needle component in a direction perpendicular to a pin of the gold needle component.
- the image acquired by the image acquisition device may be a multi-channel color image.
- the pin detection system of the gold needle component further includes a pre-processing device 50, which is connected to the acquisition device 10 and the positioning device 20. And performing grayscale preprocessing on the image to obtain a grayscale image of the image.
- the positioning device 20 may include a processing unit, a selecting unit, and an extracting unit.
- the processing unit is configured to perform binarization processing on the gray value of each pixel to obtain a binary image. Extracting an outer section of the binary image; wherein the outer section is the largest connected area of the binary image; and the extracting unit is configured to extract the outer section corresponding to the gray image a region, and a region corresponding to the outer segment region is used as a gold needle body region of the gold needle component.
- the detecting device 30 may include a detecting unit for selecting a gold pin point of the gold needle component from the gold needle body region using a corner detection algorithm.
- the computing device 40 can include:
- a dividing unit configured for a pin number of the gold needle component, dividing the golden pin body region into a plurality of sub-regions
- a calculation unit configured to extract a maximum gold needle point of each sub-area, and calculate an area of the maximum gold needle point; wherein the maximum gold needle point is a gold needle point having the largest area in each sub-area;
- the determining unit is configured to determine that the pin of the gold needle component is incomplete if the area of the largest gold pin point in a sub-area is less than a preset value.
- the pin detection system of the gold needle component obtains an image of the gold needle component; locates the gold needle body region of the gold needle component according to the gray value of each pixel in the image; and selects the gold needle body region from the image
- the golden needle point of the gold needle component is described; and according to the area of the gold needle point, whether the pin of the gold needle component is complete, the automatic detection of the pin of the gold needle component is realized, and the detection efficiency is effectively improved.
- the pin detection system of the gold needle component of the present invention corresponds to the pin detection method of the gold needle component of the present invention, and the technical features and the beneficial effects described in the embodiment of the pin detection method of the gold needle component are applicable. In the embodiment of the pin detecting system of the gold needle component, it is hereby declared.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Finger-Pressure Massage (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (10)
- 一种金针类元件的引脚检测方法,其特征在于,包括以下步骤:获取电路板上待测金针类元件的图像;获取所述图像中各像素点的灰度值,根据所述灰度值从所述图像中定位金针类元件的引脚所在的区域,并将所述区域设为所述金针类元件的金针主体区域;从所述金针主体区域中获取所述金针类元件的引脚在所述电路板上的投影,并将所述投影设为所述金针类元件的金针点;计算所述金针点的面积,并根据所述金针点的面积判断所述金针类元件的引脚是否完整。
- 根据权利要求1所述的金针类元件的引脚检测方法,其特征在于,获取电路板上金针类元件的图像的步骤包括:在垂直于所述金针类元件的引脚的方向上获取所述金针类元件的图像。
- 根据权利要求1所述的金针类元件的引脚检测方法,其特征在于,根据各像素点的灰度值从所述灰度图像中定位所述金针类元件的金针主体区域的步骤包括:对各像素点的灰度值进行二值化处理,得到二值图像;选取所述二值图像的外截区域;其中,所述外截区域为所述二值图像中最大的连通区域;在所述灰度图像中提取所述外截区域对应的区域,并将所述外截区域对应的区域作为所述金针类元件的金针主体区域。
- 根据权利要求1所述的金针类元件的引脚检测方法,其特征在于,从所述金针主体区域中选取所述金针类元件的金针点的步骤包括:采用角点检测算法从所述金针主体区域中选取所述金针类元件的金针点。
- 根据权利要求1所述的金针类元件的引脚检测方法,其特征在于,根据所述金针点的面积判断所述金针类元件的引脚是否完整的步骤包括:根据金针类元件的引脚数目,将所述金针主体区域划分为多个子区域;提取每个子区域的最大金针点,并计算所述最大金针点的面积;其中,所 述最大金针点为每个子区域内面积最大的金针点;若存在一个子区域内的最大金针点的面积小于预设值,则判定为所述金针类元件的引脚不完整。
- 一种金针类元件的引脚检测系统,其特征在于,包括:获取装置,用于获取电路板上待测金针类元件的图像;定位装置,用于获取所述图像中各像素点的灰度值,根据所述灰度值从所述图像中定位金针类元件的引脚所在的区域,并将所述区域设为所述金针类元件的金针主体区域;检测装置,用于从所述金针主体区域中获取所述金针类元件的引脚在所述电路板上的投影,并将所述投影设为选取所述金针类元件的金针点;计算装置,用于计算所述金针点的面积,并根据所述金针点的面积判断所述金针类元件的引脚是否完整。
- 根据权利要求6所述的金针类元件的引脚检测系统,其特征在于,所述获取装置包括:获取单元,用于在垂直于所述金针类元件的引脚的方向上获取所述金针类元件的图像。
- 根据权利要求6所述的金针类元件的引脚检测系统,其特征在于,所述定位装置包括:处理单元,用于对各像素点的灰度值进行二值化处理,得到二值图像;选取单元,用于选取所述二值图像的外截区域;其中,所述外截区域为所述二值图像中最大的连通区域;提取单元,用于在所述灰度图像中提取所述外截区域对应的区域,并将所述外截区域对应的区域作为所述金针类元件的金针主体区域。
- 根据权利要求6所述的金针类元件的引脚检测系统,其特征在于,所述检测装置包括:检测单元,用于采用角点检测算法从所述金针主体区域中选取所述金针类元件的金针点。
- 根据权利要求6所述的金针类元件的引脚检测系统,其特征在于,所 述计算装置包括:划分单元,用于金针类元件的引脚数目,将所述金针主体区域划分为多个子区域;计算单元,用于提取每个子区域的最大金针点,并计算所述最大金针点的面积;其中,所述最大金针点为每个子区域内面积最大的金针点;判定单元,用于若存在一个子区域内的最大金针点的面积小于预设值,则判定为所述金针类元件的引脚不完整。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510708771.0A CN105303573B (zh) | 2015-10-26 | 2015-10-26 | 金针类元件的引脚检测方法和系统 |
CN201510708771.0 | 2015-10-26 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017071406A1 true WO2017071406A1 (zh) | 2017-05-04 |
Family
ID=55200795
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2016/098223 WO2017071406A1 (zh) | 2015-10-26 | 2016-09-06 | 金针类元件的引脚检测方法和系统 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN105303573B (zh) |
WO (1) | WO2017071406A1 (zh) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113033139A (zh) * | 2021-05-19 | 2021-06-25 | 福莱盈电子股份有限公司 | 一种电路板表面化金面积的计算方法 |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105303573B (zh) * | 2015-10-26 | 2018-05-25 | 广州视源电子科技股份有限公司 | 金针类元件的引脚检测方法和系统 |
CN106127746A (zh) * | 2016-06-16 | 2016-11-16 | 广州视源电子科技股份有限公司 | 电路板元件漏件检测方法和系统 |
CN110111293B (zh) * | 2018-01-29 | 2021-05-11 | 国科赛思(北京)科技有限公司 | 塑封器件的失效识别方法及装置 |
CN111208147A (zh) * | 2020-01-13 | 2020-05-29 | 普联技术有限公司 | 针脚检测方法、装置及系统 |
CN114047123B (zh) * | 2021-10-09 | 2024-04-09 | 无锡芯羿达微电子有限公司 | 一种用于集成板生产缺陷检测方法及检测系统 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH04218706A (ja) * | 1990-12-18 | 1992-08-10 | Omron Corp | 部品位置等計測装置 |
CN103745475A (zh) * | 2014-01-22 | 2014-04-23 | 哈尔滨工业大学 | 一种用于球形引脚元件的检测与定位方法 |
CN104574344A (zh) * | 2013-10-17 | 2015-04-29 | 鸿富锦精密工业(深圳)有限公司 | 电感焊接脚检测系统及方法 |
CN104574367A (zh) * | 2014-12-21 | 2015-04-29 | 浙江大学 | 一种基于机器视觉的集成芯片管脚几何尺寸检测计算方法 |
CN104933720A (zh) * | 2015-06-25 | 2015-09-23 | 哈尔滨工业大学 | 一种基于视觉的sop元件定位和缺陷检测方法 |
CN105303573A (zh) * | 2015-10-26 | 2016-02-03 | 广州视源电子科技股份有限公司 | 金针类元件的引脚检测方法和系统 |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103235939A (zh) * | 2013-05-08 | 2013-08-07 | 哈尔滨工业大学 | 基于机器视觉的基准点定位方法 |
CN104359402A (zh) * | 2014-11-17 | 2015-02-18 | 南京工业大学 | 一种用于矩形引脚元件视觉定位的检测方法 |
CN104952081B (zh) * | 2015-07-20 | 2018-01-12 | 电子科技大学 | 一种基于极值差分统计特征的cog偏移检测方法 |
-
2015
- 2015-10-26 CN CN201510708771.0A patent/CN105303573B/zh active Active
-
2016
- 2016-09-06 WO PCT/CN2016/098223 patent/WO2017071406A1/zh active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH04218706A (ja) * | 1990-12-18 | 1992-08-10 | Omron Corp | 部品位置等計測装置 |
CN104574344A (zh) * | 2013-10-17 | 2015-04-29 | 鸿富锦精密工业(深圳)有限公司 | 电感焊接脚检测系统及方法 |
CN103745475A (zh) * | 2014-01-22 | 2014-04-23 | 哈尔滨工业大学 | 一种用于球形引脚元件的检测与定位方法 |
CN104574367A (zh) * | 2014-12-21 | 2015-04-29 | 浙江大学 | 一种基于机器视觉的集成芯片管脚几何尺寸检测计算方法 |
CN104933720A (zh) * | 2015-06-25 | 2015-09-23 | 哈尔滨工业大学 | 一种基于视觉的sop元件定位和缺陷检测方法 |
CN105303573A (zh) * | 2015-10-26 | 2016-02-03 | 广州视源电子科技股份有限公司 | 金针类元件的引脚检测方法和系统 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113033139A (zh) * | 2021-05-19 | 2021-06-25 | 福莱盈电子股份有限公司 | 一种电路板表面化金面积的计算方法 |
CN113033139B (zh) * | 2021-05-19 | 2021-08-31 | 福莱盈电子股份有限公司 | 一种电路板表面化金面积的计算方法 |
Also Published As
Publication number | Publication date |
---|---|
CN105303573B (zh) | 2018-05-25 |
CN105303573A (zh) | 2016-02-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2017071406A1 (zh) | 金针类元件的引脚检测方法和系统 | |
WO2018068415A1 (zh) | 元件错件检测方法和系统 | |
CN109472271B (zh) | 印刷电路板图像轮廓提取方法及装置 | |
WO2018068417A1 (zh) | 元件缺陷检测方法和系统 | |
WO2017181724A1 (zh) | 电子元件漏件检测方法和系统 | |
US20170323435A1 (en) | Defect quantification method, defect quantification device, and defect evaluation value display device | |
WO2017067342A1 (zh) | 板卡位置检测方法及装置 | |
CN106651857B (zh) | 一种印刷电路板贴片缺陷检测方法 | |
CN106501272B (zh) | 机器视觉焊锡定位检测系统 | |
CN105718931B (zh) | 用于确定采集图像中的杂斑的系统和方法 | |
CN108445010B (zh) | 自动光学检测方法及装置 | |
TWI512284B (zh) | 玻璃氣泡瑕疵檢測系統 | |
WO2017107529A1 (zh) | 一种并排二极管的定位方法及装置 | |
JP4910128B2 (ja) | 対象物表面の欠陥検査方法 | |
WO2017181722A1 (zh) | 元件漏检方法和系统 | |
TWI496111B (zh) | 針腳彎曲檢測方法 | |
JP2005345290A (ja) | 筋状欠陥検出方法及び装置 | |
CN117589770A (zh) | Pcb贴片板检测方法、装置、设备及介质 | |
WO2018068414A1 (zh) | 色环电阻的检测方法、装置和自动光学检测系统 | |
TW201543053A (zh) | 一種線路資訊擷取方法、非線路區資訊擷取方法及運用前述方法的線路缺陷檢測方法 | |
JP2014135007A (ja) | フラットパネルディスプレイの自動ムラ検出装置および自動ムラ検出方法 | |
KR101383827B1 (ko) | 인쇄회로기판의 솔더링 영역 자동검출 시스템 및 방법 | |
CN110874837A (zh) | 一种基于局部特征分布的缺陷自动检测方法 | |
JP2010243209A (ja) | 欠陥検査方法および欠陥検出装置 | |
JP2004286708A (ja) | 欠陥検出装置、方法及びプログラム |
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: 16858842 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: 16858842 Country of ref document: EP Kind code of ref document: A1 |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 16858842 Country of ref document: EP Kind code of ref document: A1 |
|
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 22/01/2019) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 16858842 Country of ref document: EP Kind code of ref document: A1 |