CN109813727B - PCB welding defect detection method based on depth information - Google Patents
PCB welding defect detection method based on depth information Download PDFInfo
- Publication number
- CN109813727B CN109813727B CN201811586190.4A CN201811586190A CN109813727B CN 109813727 B CN109813727 B CN 109813727B CN 201811586190 A CN201811586190 A CN 201811586190A CN 109813727 B CN109813727 B CN 109813727B
- Authority
- CN
- China
- Prior art keywords
- image
- welding
- detected
- pcb
- standard
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003466 welding Methods 0.000 title claims abstract description 87
- 230000007547 defect Effects 0.000 title claims abstract description 30
- 238000001514 detection method Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 26
- 238000005476 soldering Methods 0.000 claims abstract description 21
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical group [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 claims abstract description 17
- 150000003071 polychlorinated biphenyls Chemical class 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims abstract 3
- 230000007797 corrosion Effects 0.000 claims description 6
- 238000005260 corrosion Methods 0.000 claims description 6
- 238000005286 illumination Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 229910000679 solder Inorganic materials 0.000 description 1
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Electric Connection Of Electric Components To Printed Circuits (AREA)
Abstract
The invention discloses a PCB welding defect detection method based on depth information, which comprises the following steps: respectively collecting depth data of a PCB welding area to be detected and a standard PCB welding area; respectively generating corresponding depth images according to the depth data of the welding areas of the two PCBs; acquiring a standard welding image according to the standard depth image, and acquiring a welding image to be detected according to the depth image to be detected; carrying out image registration on the standard welding image and the welding image to be detected; marking a soldering tin position in the welding image to be detected, and judging whether the soldering tin position leads or not according to a ratio calculation value of the soldering tin position; performing image difference operation on the registered standard welding image and the welding image to be detected to obtain a binary image; the PCB welding defects are determined according to the binary image, the method can reduce the processed data amount, has low requirement on illumination conditions, and can reduce the false detection rate.
Description
Technical Field
The invention relates to the field of electronic component detection, in particular to a PCB welding defect detection method based on depth information.
Background art:
at present, the defect detection of the PCB in the industry is mostly based on two-dimensional color image information of the PCB, the data volume in the two-dimensional color image is too large and much useless information exists, the processing speed is low, the processing precision of shooting the two-dimensional image under the condition of poor illumination condition is low, the false detection rate is high, and the defects existing in the PCB are detected by extracting the characteristics of the color, the angular points and the like of the two-dimensional image and comparing the characteristics with a standard board.
Disclosure of Invention
The invention aims to provide a PCB welding defect detection method based on depth information, so as to solve the defects caused in the prior art.
A PCB welding defect detection method based on depth information comprises the following steps:
respectively collecting depth data of a PCB welding area to be detected and a standard PCB welding area;
respectively generating corresponding depth images according to the depth data of the welding areas of the two PCBs;
acquiring a standard welding image according to the depth image of the standard PCB, and acquiring a welding image to be detected according to the depth image of the PCB to be detected;
marking a soldering tin position in a welding image to be detected;
carrying out image registration on the standard welding image and the welding image to be detected;
performing image difference operation on the registered standard welding image and the welding image to be detected to obtain a binary image;
and determining the welding defects of the PCB according to the binary image.
Preferably, the method for generating the depth image includes: normalizing the depth data to be between 0 and 255.
Preferably, the image registration method includes: respectively detecting circle marks and circle centers of the standard welding image and the welding image to be detected by adopting a Hough transform method; and realizing image registration through coordinate rotation translation.
Preferably, the method for determining the step of outputting the foot includes: and carrying out Hough circle detection on the standard welding image, finding a circle corresponding to the soldering tin part by limiting the area of the circle, marking the corresponding soldering tin position in the welding image to be detected, and if the ratio of pixels higher than the height of the pin in the circle to pixels contained in the circle is less than a preset threshold value, indicating that no pin is out.
Preferably, the method for acquiring a binary image includes: and comparing the difference value between the standard welding image and the welding image to be detected with a preset threshold value, setting the pixel points smaller than the preset threshold value to be 0, and setting the rest pixel points to be 1, thereby obtaining a differential binary image.
Preferably, the method for calculating the difference value includes: subtracting the pixel value of the standard welding image from the pixel value corresponding to the welding image to be detected; or subtracting the pixel value of the corresponding point of the standard welding image from the pixel value of the welding image to be detected.
Preferably, the method for determining the welding defects of the PCB comprises the following steps: and carrying out corrosion operation on the binary image, wherein white areas in the image after corrosion indicate that excessive soldering defects exist.
The invention has the advantages that: according to the method, the PCB is scanned in three dimensions through the line laser, the depth information of the PCB is obtained, the data amount required to be processed is reduced, the requirement on illumination conditions is low, and the false detection rate can be reduced through three-dimensional depth data processing.
Drawings
Fig. 1 is a flowchart of a method for detecting a soldering defect of a PCB based on depth information according to an embodiment of the present invention.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific embodiments.
As shown in fig. 1, a method for detecting a welding defect of a PCB based on depth information, the method comprising the steps of:
respectively collecting depth data of a PCB welding area to be detected and a standard PCB welding area, scanning the front and back of a standard PCB by utilizing line laser, and collecting depth data of the front and back of the standard PCB;
respectively generating corresponding depth images according to the depth data of the welding areas of the two PCBs;
acquiring a standard welding image according to the depth image of the standard PCB, acquiring a welding image to be detected according to the depth image of the PCB to be detected, performing filtering operation on the acquired depth image to remove noise, generating a standard board image, and marking out different element areas;
marking a soldering tin position in a welding image to be detected;
carrying out image registration on the standard welding image and the welding image to be detected;
performing image difference operation on the registered standard welding image and the welding image to be detected to obtain a binary image;
and determining the welding defects of the PCB according to the binary image.
Notably, the method for generating the depth image includes: normalizing the depth data to be between 0 and 255.
In this embodiment, the method of image registration includes: respectively detecting circle marks and circle centers of the standard welding image and the welding image to be detected by adopting a Hough transform method; and realizing image registration through coordinate rotation translation.
In this embodiment, the method for determining the out-of-range includes: and carrying out Hough circle detection on the standard welding image, finding a circle corresponding to the soldering tin part by limiting the area of the circle, marking the corresponding soldering tin position in the welding image to be detected, and if the ratio of pixels higher than the height of the pin in the circle to pixels contained in the circle is less than a preset threshold value, indicating that no pin is out.
In this embodiment, the method for acquiring a binary image includes: setting a threshold according to the quantity of soldering tin in the element to be detected, comparing the difference value between the standard welding image and the welding image to be detected with a preset threshold, setting the pixel points smaller than the preset threshold to be 0, and setting the rest pixel points to be 1, thereby obtaining a differential binary image.
In this embodiment, the method for calculating the difference value includes: and subtracting the pixel value of the corresponding point of the welding image to be detected from the pixel value of the standard welding image or subtracting the pixel value of the corresponding point of the standard welding image from the pixel value of the welding image to be detected.
In this embodiment, the method for determining the soldering defect of the PCB includes: and carrying out corrosion operation on the binary image, wherein a white area in the corroded image indicates that excessive soldering tin defects exist, and the binary image can be more visually seen through the corrosion operation due to the fact that a large number of false defects exist in the binary image.
Based on the above, in the method, a large number of false defects exist in the binary image, so that a true defect region needs to be found out. Since the area of the true defect is much larger than that of the false defect, the differential image can be eroded. If the standard diagram minus the detection diagram has a white area, the soldering tin at the position is excessive; if the reduced map has white areas, the solder is too much at that location.
It will be appreciated by those skilled in the art that the invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The embodiments disclosed above are therefore to be considered in all respects as illustrative and not restrictive. All changes which come within the scope of or equivalence to the invention are intended to be embraced therein.
Claims (4)
1. A PCB welding defect detection method based on depth information is characterized by comprising the following steps:
respectively collecting depth data of a PCB welding area to be detected and a standard PCB welding area;
respectively generating corresponding depth images according to the depth data of the welding areas of the two PCBs;
acquiring a standard welding image according to the depth image of the standard PCB, and acquiring a welding image to be detected according to the depth image of the PCB to be detected;
carrying out image registration on the standard welding image and the welding image to be detected;
marking a soldering tin position in the welding image to be detected, and judging whether the soldering tin position leads or not according to a ratio calculation value of the soldering tin position;
performing image difference operation on the registered standard welding image and the welding image to be detected to obtain a binary image;
determining the welding defects of the PCB according to the binary image;
the generation method of the depth image comprises the following steps:
normalizing the depth data to be between 0 and 255;
the image registration method comprises the following steps:
respectively detecting circle marks and circle centers of the standard welding image and the welding image to be detected by adopting a Hough transform method;
realizing image registration through coordinate rotation translation;
the method for judging the foot output comprises the following steps: and carrying out Hough circle detection on the standard welding image, finding a circle corresponding to the soldering tin part by limiting the area of the circle, marking the corresponding soldering tin position in the welding image to be detected, and if the ratio of pixels higher than the height of the pin in the circle to pixels contained in the circle is less than a preset threshold value, indicating that no pin is out.
2. The PCB welding defect detection method based on the depth information as claimed in claim 1, wherein: the binary image acquisition method comprises the following steps:
and comparing the difference value between the standard welding image and the welding image to be detected with a preset threshold value, setting the pixel points smaller than the preset threshold value to be 0, and setting the rest pixel points to be 1, thereby obtaining a differential binary image.
3. The PCB welding defect detection method based on the depth information as claimed in claim 2, wherein: the calculation method of the difference value comprises the following steps:
subtracting the pixel value of the standard welding image from the pixel value corresponding to the welding image to be detected; or subtracting the pixel value of the corresponding point of the standard welding image from the pixel value of the welding image to be detected.
4. The PCB welding defect detection method based on the depth information as claimed in claim 1, wherein: the method for determining the welding defects of the PCB comprises the following steps: and carrying out corrosion operation on the binary image, wherein white areas in the image after corrosion indicate that excessive soldering defects exist.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811586190.4A CN109813727B (en) | 2018-12-25 | 2018-12-25 | PCB welding defect detection method based on depth information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811586190.4A CN109813727B (en) | 2018-12-25 | 2018-12-25 | PCB welding defect detection method based on depth information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109813727A CN109813727A (en) | 2019-05-28 |
| CN109813727B true CN109813727B (en) | 2021-08-03 |
Family
ID=66602363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811586190.4A Active CN109813727B (en) | 2018-12-25 | 2018-12-25 | PCB welding defect detection method based on depth information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109813727B (en) |
Families Citing this family (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110455199A (en) * | 2019-07-02 | 2019-11-15 | 深圳市格灵人工智能与机器人研究院有限公司 | Pcb board Pin needle height detection method and system |
| CN110736755A (en) * | 2019-10-30 | 2020-01-31 | 珠海格力智能装备有限公司 | Detection method and device for circuit board excess material and electronic equipment |
| CN110977292A (en) * | 2019-12-12 | 2020-04-10 | 天津博迈科海洋工程有限公司 | Automatic detection method for welding seam of ocean platform module structure |
| CN111812545B (en) * | 2020-07-07 | 2023-05-12 | 苏州精濑光电有限公司 | Line defect detection method, device, equipment and medium |
| CN112858341B (en) * | 2020-12-23 | 2022-11-18 | 北京纬百科技有限公司 | Detection method, shooting system and detection system |
| CN113192027B (en) * | 2021-04-29 | 2023-03-24 | 华南理工大学 | Detection method and application of high-power LED module packaging defects |
| CN113344929B (en) * | 2021-08-09 | 2021-11-05 | 深圳智检慧通科技有限公司 | Welding spot visual detection and identification method, readable storage medium and equipment |
| CN113781424B (en) * | 2021-09-03 | 2024-02-27 | 苏州凌云光工业智能技术有限公司 | Surface defect detection method, device and equipment |
| CN114399468B (en) * | 2021-12-15 | 2024-12-10 | 北京四方继保自动化股份有限公司 | Circuit board pin defect recognition method based on feature self-learning |
| CN114612375A (en) * | 2022-01-14 | 2022-06-10 | 佛山市国立光电科技有限公司 | PCB defect detection method, system and storage medium |
| CN114693633B (en) * | 2022-03-28 | 2025-09-23 | 深圳市深视智能科技有限公司 | Welding defect detection method, device and detection system |
| ES3034392T3 (en) | 2022-08-19 | 2025-08-18 | Contemporary Amperex Technology Hong Kong Ltd | Depth image correction method and device, and welding detection method for battery housing assembly |
| CN115830096B (en) * | 2022-08-19 | 2023-08-25 | 宁德时代新能源科技股份有限公司 | Correction method and device of depth image, welding detection method of battery housing components |
| CN115753832B (en) * | 2022-11-10 | 2023-07-11 | 合肥华焠新能源科技有限公司 | Detection method for integrated circuit board of new energy automobile |
| CN116026854A (en) * | 2023-02-08 | 2023-04-28 | 深圳市鑫三力自动化设备有限公司 | A kind of detection method of BGA packaging chip |
| CN116075148B (en) * | 2023-03-14 | 2023-06-20 | 四川易景智能终端有限公司 | PCBA board production line intelligent supervision system based on artificial intelligence |
| CN117214181A (en) * | 2023-09-18 | 2023-12-12 | 上海感图网络科技有限公司 | Material defect rechecking method, device and medium for automatic series connection of AVI |
| CN118037628B (en) * | 2023-12-25 | 2025-03-04 | 中船鹏力(南京)智能装备系统有限公司 | IC pin defect detection method based on image processing |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101887033A (en) * | 2009-05-13 | 2010-11-17 | 株式会社高永科技 | Method for measuring measurement target |
| CN103675588A (en) * | 2013-11-20 | 2014-03-26 | 中国矿业大学 | Printed circuit element polarity machine vision detection method and device |
| JP2014071094A (en) * | 2012-10-02 | 2014-04-21 | Denso Corp | Shape measurement device |
| CN104463209A (en) * | 2014-12-08 | 2015-03-25 | 厦门理工学院 | Method for recognizing digital code on PCB based on BP neural network |
| CN105264329A (en) * | 2013-06-03 | 2016-01-20 | 雅马哈发动机株式会社 | Inspection apparatus and inspection method |
| CN106897994A (en) * | 2017-01-20 | 2017-06-27 | 北京京仪仪器仪表研究总院有限公司 | A kind of pcb board defect detecting system and method based on layered image |
| CN107610085A (en) * | 2016-07-11 | 2018-01-19 | 富强 | A kind of welding point defect detecting system based on computer vision |
| CN107767379A (en) * | 2017-11-16 | 2018-03-06 | 桂林电子科技大学 | Pcb board marks print quality inspection method |
| CN108596829A (en) * | 2018-04-19 | 2018-09-28 | 广东工业大学 | A kind of PCB bare boards picture method for registering and device |
| CN109001230A (en) * | 2018-05-28 | 2018-12-14 | 中兵国铁（广东）科技有限公司 | Welding point defect detection method based on machine vision |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102025038B1 (en) * | 2014-09-11 | 2019-09-24 | 사이버옵틱스 코포레이션 | Point cloud merging from multiple cameras and sources in three-dimensional profilometry |
| WO2016144744A1 (en) * | 2015-03-09 | 2016-09-15 | Illinois Tool Works Inc. | Methods and apparatus to provide visual information associated with welding operations |
-
2018
- 2018-12-25 CN CN201811586190.4A patent/CN109813727B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101887033A (en) * | 2009-05-13 | 2010-11-17 | 株式会社高永科技 | Method for measuring measurement target |
| JP2014071094A (en) * | 2012-10-02 | 2014-04-21 | Denso Corp | Shape measurement device |
| CN105264329A (en) * | 2013-06-03 | 2016-01-20 | 雅马哈发动机株式会社 | Inspection apparatus and inspection method |
| CN103675588A (en) * | 2013-11-20 | 2014-03-26 | 中国矿业大学 | Printed circuit element polarity machine vision detection method and device |
| CN104463209A (en) * | 2014-12-08 | 2015-03-25 | 厦门理工学院 | Method for recognizing digital code on PCB based on BP neural network |
| CN107610085A (en) * | 2016-07-11 | 2018-01-19 | 富强 | A kind of welding point defect detecting system based on computer vision |
| CN106897994A (en) * | 2017-01-20 | 2017-06-27 | 北京京仪仪器仪表研究总院有限公司 | A kind of pcb board defect detecting system and method based on layered image |
| CN107767379A (en) * | 2017-11-16 | 2018-03-06 | 桂林电子科技大学 | Pcb board marks print quality inspection method |
| CN108596829A (en) * | 2018-04-19 | 2018-09-28 | 广东工业大学 | A kind of PCB bare boards picture method for registering and device |
| CN109001230A (en) * | 2018-05-28 | 2018-12-14 | 中兵国铁（广东）科技有限公司 | Welding point defect detection method based on machine vision |
Non-Patent Citations (2)
| Title |
|---|
| Feasibility study of a structured light system applied to welding inspection based on articulated coordinate measure machine data;M. Rodríguez-Martín et al.;《IEEE Sensors》;20170508;第17卷(第13期);4217-4224页 * |
| 焊接工艺的深度图像分割算法改进研究;王晓丹;《工业及工程技术》;20110427;304页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109813727A (en) | 2019-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109813727B (en) | PCB welding defect detection method based on depth information | |
| CN109472271B (en) | Printed circuit board image contour extraction method and device | |
| CN111179243A (en) | Small-size chip crack detection method and system based on computer vision | |
| CN105718931B (en) | System and method for determining clutter in acquired images | |
| CN102930266B (en) | Method for locating Mark points on PCB (printed circuit board) by utilizing outline gravity center method | |
| CN108830838A (en) | A kind of pcb board incompleteness Trigger jitter detection method of sub-pixel | |
| CN109752392B (en) | PCB defect type detection system and method | |
| CN113298776B (en) | Method for detecting appearance defects of metal closed water pump impeller | |
| JP6115012B2 (en) | Inspection device, inspection method, and inspection program | |
| CN109829886A (en) | A kind of pcb board defect inspection method based on depth information | |
| CN113077437B (en) | Workpiece quality detection method and system | |
| CN106504231A (en) | Component defect detection method and system | |
| CN109785294A (en) | A kind of pcb board defective locations detection system and method | |
| CN105243662B (en) | Terminal position determining method and terminal equipment | |
| CN116309532A (en) | A method, device, equipment and medium for quality detection of target items | |
| CN108709500A (en) | A kind of circuit board component position matching method | |
| CN105303573A (en) | Pin detection method and system for gold needle type element | |
| CN116908280A (en) | An automatic detection method and system for magnetic suspension concentration | |
| CN115272173A (en) | Tin ball defect detection method and device, computer equipment and storage medium | |
| JP5498109B2 (en) | Defect detection apparatus and defect detection method | |
| CN117274161B (en) | Film capacitor image pre-detection method and electronic equipment | |
| CN113674260A (en) | SMT welding spot defect detection method | |
| CN104570934A (en) | Product machining part detection method and system | |
| KR101383827B1 (en) | System and method for automatic extraction of soldering regions in pcb | |
| JP4821647B2 (en) | Electronic component terminal position detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: Room 101, Floor 1, Building 1, No. 15, Jiuzhou Road, Shangcheng District, Hangzhou, Zhejiang Patentee after: Zhejiang Jiangao Photoelectric Technology Co.,Ltd. Address before: 215316 room 3, No. 232, Yuanfeng Road, Yushan Town, Kunshan City, Suzhou City, Jiangsu Province Patentee before: SUZHOU JIANG'AO OPTOELECTRONICS TECHNOLOGY Co.,Ltd. |