CN106127746A - Circuit board component missing part detection method and system - Google Patents
Circuit board component missing part detection method and system Download PDFInfo
- Publication number
- CN106127746A CN106127746A CN201610438902.2A CN201610438902A CN106127746A CN 106127746 A CN106127746 A CN 106127746A CN 201610438902 A CN201610438902 A CN 201610438902A CN 106127746 A CN106127746 A CN 106127746A
- Authority
- CN
- China
- Prior art keywords
- pin
- image
- circuit board
- sample image
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30141—Printed circuit board [PCB]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of circuit board component missing part detection method and system, the method includes: obtain the sample image of the Pin locations of multiple circuit boards, carries out sample training according to component's feet position on described sample image, obtains pin disaggregated model；Obtain the detection image of circuit board the most to be detected, and determine the Pin locations of components and parts according to described detection image；Utilize described pin disaggregated model that the described Pin locations of detection image is detected, it is judged that the pin insert state of the components and parts of described circuit board.This technical scheme, it is possible to the missing part phenomenon of detecting element exactly, improves Detection results.
Description
Technical field
The present invention relates to electronic technology field, particularly relate to a kind of circuit board component missing part detection method and system.
Background technology
Assembling in production process at circuit board, due to the operation of workman, the reason such as mechanical shock of production line, element is often
There will be disappearance, the phenomenon of skew, thus cause element not in the position specified, cause serious quality problems.For understanding
Certainly find these defects and ensure quality, needing each element on circuit board is detected, to guarantee that each element exists
It specifies position.
At present, the method for element testing mainly includes two kinds: one is traditional algorithm, i.e. utilizes the basic calculation of image procossing
Method, such as color histogram, template matching, feature extraction etc., detects element.Another kind is intelligent algorithm, i.e. utilizes deep
Degree learning algorithm, such as CNN (Convolutional Neural Network, convolutional neural networks) etc., the training sample to collection
Originally it is trained, the method again element detected after obtaining element testing model.
But in process of production, there is open defect in above two method:
First, some element is close, the most identical with the color of circuit board base plate, and i.e. element presence or absence is the most also
Significantly difference can not be presented, so using traditional algorithm to be difficult to separate element with base plate；Intelligent algorithm is for this
Situation can not reach preferable Detection results.In process of production, the black horizontal capacitor in green circuit board, its background is also
It is black；Element in black circuit board, is also black such as diode, horizontal capacitor etc..So, utilize traditional algorithm,
As element is detected by the method such as color histogram, template matching, it is extremely difficult to preferable Detection results, as it is shown in figure 1, figure
1 exists and non-existent comparison diagram for element, there is element in upper figure, and figure below is to there is not element, by two figures
Still it is difficult to well distinguish.
Secondly as the faulty operation of workman or the mechanical vibration of production line, element there will be the situation of skew, causes unit
The pin of part is not inserted in the component pin circular hole specified, i.e. element exist but the pin of element goes out foot.
In sum, above-mentioned traditional algorithm and intelligent algorithm are used, it is difficult to detect the missing part phenomenon of element exactly, inspection
Survey effect is poor.
Summary of the invention
Based on this, it is necessary to for the problem that detection accuracy is relatively low, it is provided that a kind of circuit board component missing part detection method
And system.
A kind of circuit board component missing part detection method, comprises the steps:
Obtain the sample image of the Pin locations of multiple circuit boards；
Carry out sample training according to component's feet position on described sample image, obtain pin disaggregated model；
Obtain the detection image of circuit board the most to be detected, and determine the pin position of components and parts according to described detection image
Put；
Utilize described pin disaggregated model that the described Pin locations of detection image is detected, it is judged that described circuit board
The pin insert state of components and parts.
A kind of circuit board component missing part detecting system, including:
Sample collection module, for obtaining the sample image of the Pin locations of multiple circuit boards；
Model training module, for carrying out sample training according to component's feet position on described sample image, is drawn
Foot disaggregated model；
Pin locating module, for obtaining the detection image of circuit board the most to be detected, and according to described detection image
Determine the Pin locations of components and parts；
Pin detection module, for utilizing described pin disaggregated model to examine the described Pin locations of detection image
Survey, it is judged that the pin insert state of the components and parts of described circuit board.
Foregoing circuit panel element missing part detection method and system, the sample image of element based on circuit board, extracts it and draws
Placement of foot training pin disaggregated model, by the Pin locations of the detection image of circuit board to be detected, the unit of testing circuit plate
The pin insert state of device, the basis for estimation being element missing part with pinout information, eliminate the interference of circuit board base plate, it is possible to
The missing part phenomenon of detecting element, improves Detection results exactly.
Accompanying drawing explanation
Fig. 1 is that element exists and non-existent comparison diagram；
Fig. 2 is the circuit board component missing part detection method flow chart of an embodiment；
Fig. 3 is the schematic flow sheet of sample collection；
Fig. 4 is the schematic flow sheet of sample training；
Fig. 5 is the circuit board component missing part detecting system structure chart of an embodiment.
Detailed description of the invention
Illustrate circuit board component missing part detection method and the embodiment of system of the present invention below in conjunction with the accompanying drawings.
The solution of the present invention is applied in circuit board assembles production process, at the ring of the circular hole that element is inserted into circuit board
Joint, detects each element on circuit board, solves disappearance, the problem of skew that element occurs, promptly and accurately detects
Go out the missing part phenomenon of circuit board, to guarantee that each element specifies position at it.
With reference to shown in Fig. 2, Fig. 2 is the circuit board component missing part detection method flow chart of an embodiment, comprises the steps:
Step S10, obtains the sample image of the Pin locations of multiple circuit boards；
In this step, in the mainly sample collection stage, it is trained by the sample of the Pin locations of collecting circuit plate,
For training the grader of pin.
In one embodiment, with reference to shown in Fig. 3, Fig. 3 is the schematic flow sheet of sample collection, can include walking as follows
Rapid:
S101, according to image and the multiple sample image of Pin locations acquisition of information thereof of multiple circuit boards；
Concrete, the image of the circuit board of multiple color, model and batch can be obtained, demarcate the pin position of each element
Confidence ceases, and obtains multiple sample image；
In order to ensure the multiformity of training sample, the circuit board image of different colours, model and batch can be collected；Pass through
Demarcate the Pin locations information of each element, obtain N number of training sample, T={ (x can be designated as1,y1),(x2,y2),...,(xN,
yN)}；
Wherein, xi∈ χ=Rn,yi∈ 0,1}, i=1,2 ..., N, xiFor i-th training sample, yiFor xiClass labelling,
Work as yiWhen=0, represent xiFor not inserting the circular hole of pin；Work as yiWhen=1, represent xiFor inserting the circular hole of pin.
S102, for the training sample image of training and several are for testing to obtain several according to described sample image
Test sample image；
Concrete, described sample image can be carried out image procossing, obtain several training sample figures for training
Picture is used for the test sample image of test with several；
For the process of sample image, may include that described sample image is rotated, cutting or brightness adjustment；
Rotation can be sample image dextrorotation respectively is turn 90 degrees, 180 degree and 270 degree etc.；Shearing can be former
Beginning sample image is sheared the subimage being sized, and this sub-picture pack circular hole Han pin；Brightness adjustment can be by sample
Image carries out point processing on spatial domain, such as image enhaucament, brightness/contrast regulation or gamma value adjustment etc..
Due to the impact of various factors, the training sample image collected in reality is often limited, therefore, in order to ensure
The multiformity of sample image, the situation that covering pin is likely to occur as much as possible, by the above-mentioned sample image to having collected
Carry out rotating, cutting, the adjustment of brightness；Multiple sample images and test image can be obtained.
Step S20, carries out sample training according to component's feet position on described sample image, obtains pin classification mould
Type；
In this step, the mainly training pattern stage, utilize by collect sample be trained, thus obtain for
The grader of detection pin.
In one embodiment, with reference to shown in Fig. 4, Fig. 4 is the schematic flow sheet of sample training, can include walking as follows
Rapid:
S201, utilizes described training sample image to be trained obtaining pinouts as disaggregated model；
Concrete, the network model of pinouts picture can be defined, utilize training sample image to be trained obtaining pinouts
As disaggregated model；
Such as, after defining applicable network model as required, input training sample image data T={ (x1,y1),(x2,
y2),...,(xN,yN), then start to train pin disaggregated model, training process to be mainly two stages:
The propagated forward stage (first stage): read training sample image data T={ (x1,y1),(x2,y2),...,(xN,
yN) in any one sample data (xi,yi), by xiInput described network model, from input layer through converting step by step and transmitting
To output layer, calculate real output value oi=Fn(..(F2(F1(XiW(1))W(2))..)W(n))；
The back-propagating stage (second stage): calculate real output value oiWith corresponding idea output yiBetween difference,
Build minimization error functionAdjust weight matrix；
Through weight matrix iteration several times, when difference EiThe deconditioning when reaching the threshold value set, obtains pinouts picture
Disaggregated model.
S202, tests as disaggregated model described pinouts according to test sample image；Concrete, can be according to survey
Examination sample image sets up test set, utilizes pin not to be plugged and has been plugged the test set of two kinds of test sample image with pin to pin
The accuracy rate of image disaggregated model detects, statistics rate of false alarm and rate of failing to report, until pinouts makes a reservation for as disaggregated model meets
Requirement.
Step S30, obtains the detection image of circuit board the most to be detected, and determines components and parts according to described detection image
Pin locations；
In this step, being the application to pin disaggregated model, in preferred circuit plate image, user annotation needs detection
The pin of element；In circuit board image to be detected, positioning pins.
In one embodiment, positioning pins position, can first obtain the detection image of the circuit board of standard；Then in institute
State mark in detection image and need the pin of detecting element；In the detection image of circuit board to be detected, fixed according to described mark
The position of position pin.
Step S40, utilizes described pin disaggregated model to detect the described Pin locations of detection image, it is judged that described
The pin insert state of the components and parts of circuit board.
In this step, behind positioning pins position, detection image input pin grader is detected, testing circuit plate
The pin insert state of components and parts.
In one embodiment, the detection image input pin image disaggregated model comprising pin is detected, detection
The element missing part state of the pin circular hole of circuit board.
At pinouts as, in disaggregated model, if this pin state is 0, then the circular hole that this pin is corresponding does not insert pin, if
The state of this pin is 1, then the circular hole that pin is corresponding has inserted pin；Further, if this pin state is 0, pin is sent
It is not plugged warning, in order to related personnel checks and keeps in repair.
The scheme of summary embodiment, compared with existing traditional algorithm and intelligent algorithm, is not to pay close attention to element body
Itself, but start with from the pin of element, detecting element exist with not in the presence of the circular hole of component pin have significantly difference, only
Pay close attention to the information of pin circular hole, remove the interference of circuit board base plate, have only to when user uses specify component pin to be detected
Position, thus complete element testing element whether missing part；Scheme can efficiently solve element identical with board color time not
A difficult problem for missing part detection can be carried out, improve the recall rate of AOI equipment.
With reference to shown in Fig. 5, Fig. 5 is the circuit board component missing part detecting system structure chart of an embodiment, including:
Sample collection module 10, for obtaining the sample image of the Pin locations of multiple circuit boards；
Model training module 20, for carrying out sample training according to component's feet position on described sample image, obtains
Pin disaggregated model；
Pin locating module 30, for obtaining the detection image of circuit board the most to be detected, and according to described detection figure
As determining the Pin locations of components and parts；
Pin detection module 40, for utilizing described pin disaggregated model to examine the described Pin locations of detection image
Survey, it is judged that the pin insert state of the components and parts of described circuit board.
The circuit board component missing part detection method of the circuit board component missing part detecting system of the present invention and the present invention one a pair
Should, technical characteristic and beneficial effect thereof that the embodiment in foregoing circuit panel element missing part detection method illustrates all are applicable to circuit
In the embodiment of panel element missing part detecting system, hereby give notice that.
Each technical characteristic of embodiment described above can combine arbitrarily, for making description succinct, not to above-mentioned reality
The all possible combination of each technical characteristic executed in example is all described, but, as long as the combination of these technical characteristics is not deposited
In contradiction, all it is considered to be the scope that this specification is recorded.
Embodiment described above only have expressed the several embodiments of the present invention, and it describes more concrete and detailed, but also
Can not therefore be construed as limiting the scope of the patent.It should be pointed out that, come for those of ordinary skill in the art
Saying, without departing from the inventive concept of the premise, it is also possible to make some deformation and improvement, these broadly fall into the protection of the present invention
Scope.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (10)
1. a circuit board component missing part detection method, it is characterised in that comprise the steps:
Obtain the sample image of the Pin locations of multiple circuit boards；
Carry out sample training according to component's feet position on described sample image, obtain pin disaggregated model；
Obtain the detection image of circuit board the most to be detected, and determine the Pin locations of components and parts according to described detection image；
Utilize described pin disaggregated model that the described Pin locations of detection image is detected, it is judged that first device of described circuit board
The pin insert state of part.
Circuit board component missing part detection method the most according to claim 1, it is characterised in that according on described sample image
Component's feet position carries out sample training, and the step obtaining pin disaggregated model includes:
Image according to multiple circuit boards and the multiple sample image of Pin locations acquisition of information thereof；
For the training sample image of training and several are for the test specimens tested to obtain several according to described sample image
This image；
Carrying out sample training according to component's feet position on described sample image, the step obtaining pin disaggregated model includes:
Described training sample image is utilized to be trained obtaining pinouts as disaggregated model；
According to test sample image, described pinouts is tested as disaggregated model.
Circuit board component missing part detection method the most according to claim 1, it is characterised in that according to the figure of multiple circuit boards
The step of picture and the multiple sample image of Pin locations acquisition of information thereof includes:
Obtain the image of the circuit board of multiple color, model and batch, demarcate the Pin locations information of each element, obtain multiple
Sample image；
For the training sample image of training and several are for the test specimens tested to obtain several according to described sample image
The step of this image includes:
Described sample image is carried out image procossing, and for the training sample image of training and several are for surveying to obtain several
The test sample image of examination；
Utilize described training sample image to be trained obtaining pinouts to include as the step of disaggregated model:
The network model of definition pinouts picture, utilizes training sample image to be trained obtaining pinouts as disaggregated model；
Include according to the step that described pinouts is tested by test sample image as disaggregated model:
Set up test set according to test sample image, utilize pin not to be plugged the survey being plugged two kinds of test sample image with pin
Examination set pair pinouts detects as the accuracy rate of disaggregated model, statistics rate of false alarm and rate of failing to report, until pinouts picture classification mould
Type meets predetermined requirement.
Circuit board component missing part detection method the most according to claim 1, it is characterised in that described to described sample image
The step carrying out image procossing includes:
Sample image is rotated, original sample image is sheared the subimage being sized, or by sample image at sky
Point processing is carried out on territory.
Circuit board component missing part detection method the most according to claim 3, it is characterised in that described utilize training sample figure
Include as the step of disaggregated model as being trained obtaining pinouts:
Read training sample image data T={ (x1,y1),(x2,y2),...,(xN,yN) in any one sample data (xi,
yi), by xiInput described network model, from input layer through converting and be transferred to output layer step by step, calculate real output value oi=
Fn(..(F2(F1(XiW(1))W(2))..)W(n))；
Calculate real output value oiWith corresponding idea output yiBetween difference, build minimization error functionAdjust weight matrix；
Through weight matrix iteration several times, when difference EiThe deconditioning when reaching the threshold value set, obtains pinouts picture classification mould
Type.
Circuit board component missing part detection method the most according to claim 1, it is characterised in that obtain electricity the most to be detected
The detection image of road plate, and determine that according to described detection image the step of the Pin locations of components and parts includes:
The detection image of the circuit board of acquisition standard；
In described detection image, mark needs the pin of detecting element；
In the detection image of circuit board to be detected, according to the position of described mark positioning pins.
Circuit board component missing part detection method the most according to claim 1, it is characterised in that utilize described pin classification mould
The step that the described Pin locations of detection image is detected by type includes:
The detection image input pin image disaggregated model comprising pin is detected, the unit of the pin circular hole of testing circuit plate
Part missing part state.
Circuit board component missing part detection method the most according to claim 7, it is characterised in that drawing of described testing circuit plate
The step of the element missing part state of foot circular hole includes:
At pinouts as in disaggregated model, if this pin state is 0, then it is judged to that the circular hole that this pin is corresponding does not insert pin；
If the state of this pin is 1, then it is judged to that the circular hole that pin is corresponding has inserted pin.
Circuit board component missing part detection method the most according to claim 8, it is characterised in that also include: if this pin shape
State is 0, sends pin and is not plugged warning.
10. a circuit board component missing part detecting system, it is characterised in that including:
Sample collection module, for obtaining the sample image of the Pin locations of multiple circuit boards；
Model training module, for carrying out sample training according to component's feet position on described sample image, obtains pin and divides
Class model；
Pin locating module, for obtaining the detection image of circuit board the most to be detected, and determines according to described detection image
The Pin locations of components and parts；
Pin detection module, for utilizing described pin disaggregated model to detect the described Pin locations of detection image, sentences
The pin insert state of the components and parts of disconnected described circuit board.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610438902.2A CN106127746A (en) | 2016-06-16 | 2016-06-16 | Circuit board component missing part detection method and system |
| PCT/CN2016/113126 WO2017215241A1 (en) | 2016-06-16 | 2016-12-29 | Circuit board element missing detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610438902.2A CN106127746A (en) | 2016-06-16 | 2016-06-16 | Circuit board component missing part detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106127746A true CN106127746A (en) | 2016-11-16 |
Family
ID=57470810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610438902.2A Pending CN106127746A (en) | 2016-06-16 | 2016-06-16 | Circuit board component missing part detection method and system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106127746A (en) |
| WO (1) | WO2017215241A1 (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106525876A (en) * | 2016-12-30 | 2017-03-22 | 杭州耕德电子有限公司 | Automatic missing die-cutting part detecting system and method |
| CN106886800A (en) * | 2017-03-20 | 2017-06-23 | 上海与德科技有限公司 | The positioner and method of leakage current failure |
| WO2017215241A1 (en) * | 2016-06-16 | 2017-12-21 | 广州视源电子科技股份有限公司 | Circuit board element missing detection method and system |
| CN108827974A (en) * | 2018-06-28 | 2018-11-16 | 广东科达洁能股份有限公司 | A kind of ceramic tile defect inspection method and system |
| CN109959661A (en) * | 2017-12-25 | 2019-07-02 | 由田新技股份有限公司 | Automatic optical detection method, equipment and its deep learning system |
| CN110111293A (en) * | 2018-01-29 | 2019-08-09 | 国科赛思(北京)科技有限公司 | The failure recognition methods of plastic device and device |
| CN110415240A (en) * | 2019-08-01 | 2019-11-05 | 国信优易数据有限公司 | Sample image generation method and device, circuit board defect detection method and device |
| 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 |
| CN110967350A (en) * | 2019-11-05 | 2020-04-07 | 北京地平线机器人技术研发有限公司 | Chip testing method and device based on image recognition and electronic equipment |
| CN111784674A (en) * | 2020-07-02 | 2020-10-16 | 深圳明锐理想科技有限公司 | Component detection method, component detection device, computer equipment and storage medium |
| CN113030121A (en) * | 2021-03-11 | 2021-06-25 | 微讯智造(广州)电子有限公司 | Automatic optical detection method, system and equipment for circuit board components |
| CN113808067A (en) * | 2020-06-11 | 2021-12-17 | 广东美的白色家电技术创新中心有限公司 | Circuit board detection method, visual detection equipment and device with storage function |
| CN114202515A (en) * | 2021-11-29 | 2022-03-18 | 广州海谷电子科技有限公司 | Method for detecting defect of printed carbon line of humidity sensor |
| CN116152251A (en) * | 2023-04-20 | 2023-05-23 | 成都数之联科技股份有限公司 | Television backboard detection method, model training method, device, equipment and medium |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110309865A (en) * | 2019-06-19 | 2019-10-08 | 上海交通大学 | A kind of unmanned plane patrolling power transmission lines pin defect system image-recognizing method |
| CN111189475A (en) * | 2020-01-10 | 2020-05-22 | 珠海格力智能装备有限公司 | Neglected loading detection device |
| CN111815567A (en) * | 2020-06-15 | 2020-10-23 | 国网上海市电力公司 | Automatic labeling method and device for high-recognition-rate power equipment |
| CN112102258A (en) * | 2020-08-28 | 2020-12-18 | 无锡卡尔曼导航技术有限公司 | Air-suction type seeder seeding detection method based on machine vision |
| CN117036228A (en) * | 2022-12-05 | 2023-11-10 | 珠海祺力电子有限公司 | PCBA production flow monitoring management system and method based on Internet of things |
| CN116245882A (en) * | 2023-05-11 | 2023-06-09 | 深圳市世宗自动化设备有限公司 | Circuit board electronic element detection method and device and computer equipment |
| CN117409261B (en) * | 2023-12-14 | 2024-02-20 | 成都数之联科技股份有限公司 | Element angle classification method and system based on classification model |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060023934A1 (en) * | 2004-07-30 | 2006-02-02 | Fujitsu Limited | Component edge detecting method, component edge detecting program and component inspection apparatus |
| CN101424645A (en) * | 2008-11-20 | 2009-05-06 | 上海交通大学 | Soldered ball surface defect detection device and method based on machine vision |
| CN101915769A (en) * | 2010-06-29 | 2010-12-15 | 华南理工大学 | Automatic optical inspection method for printed circuit board comprising resistance element |
| CN103745475A (en) * | 2014-01-22 | 2014-04-23 | 哈尔滨工业大学 | Detection and positioning method used for spherical pin element |
| CN103954627A (en) * | 2014-04-21 | 2014-07-30 | 杭州电子科技大学 | Electronic component surface defect detection method based on sample library dictionary |
| CN104867145A (en) * | 2015-05-15 | 2015-08-26 | 广东工业大学 | IC element solder joint defect detection method based on VIBE model |
| CN104899871A (en) * | 2015-05-15 | 2015-09-09 | 广东工业大学 | Missing solder detection method of IC element solder joints |
| CN105303573A (en) * | 2015-10-26 | 2016-02-03 | 广州视源电子科技股份有限公司 | Method and system of pin detection of gold needle elements |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127746A (en) * | 2016-06-16 | 2016-11-16 | 广州视源电子科技股份有限公司 | Circuit board component missing part detection method and system |
-
2016
- 2016-06-16 CN CN201610438902.2A patent/CN106127746A/en active Pending
- 2016-12-29 WO PCT/CN2016/113126 patent/WO2017215241A1/en active Application Filing
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060023934A1 (en) * | 2004-07-30 | 2006-02-02 | Fujitsu Limited | Component edge detecting method, component edge detecting program and component inspection apparatus |
| CN101424645A (en) * | 2008-11-20 | 2009-05-06 | 上海交通大学 | Soldered ball surface defect detection device and method based on machine vision |
| CN101915769A (en) * | 2010-06-29 | 2010-12-15 | 华南理工大学 | Automatic optical inspection method for printed circuit board comprising resistance element |
| CN103745475A (en) * | 2014-01-22 | 2014-04-23 | 哈尔滨工业大学 | Detection and positioning method used for spherical pin element |
| CN103954627A (en) * | 2014-04-21 | 2014-07-30 | 杭州电子科技大学 | Electronic component surface defect detection method based on sample library dictionary |
| CN104867145A (en) * | 2015-05-15 | 2015-08-26 | 广东工业大学 | IC element solder joint defect detection method based on VIBE model |
| CN104899871A (en) * | 2015-05-15 | 2015-09-09 | 广东工业大学 | Missing solder detection method of IC element solder joints |
| CN105303573A (en) * | 2015-10-26 | 2016-02-03 | 广州视源电子科技股份有限公司 | Method and system of pin detection of gold needle elements |
Non-Patent Citations (1)
| Title |
|---|
| 刘阳: "基于图像处理的PCB焊接缺陷检测技术研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017215241A1 (en) * | 2016-06-16 | 2017-12-21 | 广州视源电子科技股份有限公司 | Circuit board element missing detection method and system |
| CN106525876A (en) * | 2016-12-30 | 2017-03-22 | 杭州耕德电子有限公司 | Automatic missing die-cutting part detecting system and method |
| CN106886800A (en) * | 2017-03-20 | 2017-06-23 | 上海与德科技有限公司 | The positioner and method of leakage current failure |
| CN106886800B (en) * | 2017-03-20 | 2020-10-27 | 上海科文斯集成微电有限公司 | Leakage current fault positioning device and method |
| CN109959661A (en) * | 2017-12-25 | 2019-07-02 | 由田新技股份有限公司 | Automatic optical detection method, equipment and its deep learning system |
| CN110111293B (en) * | 2018-01-29 | 2021-05-11 | 国科赛思(北京)科技有限公司 | Failure identification method and device for plastic package device |
| CN110111293A (en) * | 2018-01-29 | 2019-08-09 | 国科赛思(北京)科技有限公司 | The failure recognition methods of plastic device and device |
| CN108827974A (en) * | 2018-06-28 | 2018-11-16 | 广东科达洁能股份有限公司 | A kind of ceramic tile defect inspection method and system |
| CN108827974B (en) * | 2018-06-28 | 2024-01-09 | 广东科达洁能股份有限公司 | Ceramic tile defect detection method and system |
| CN110415240A (en) * | 2019-08-01 | 2019-11-05 | 国信优易数据有限公司 | Sample image generation method and device, circuit board defect detection method and device |
| 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 |
| CN110967350A (en) * | 2019-11-05 | 2020-04-07 | 北京地平线机器人技术研发有限公司 | Chip testing method and device based on image recognition and electronic equipment |
| CN110967350B (en) * | 2019-11-05 | 2023-04-11 | 北京地平线机器人技术研发有限公司 | Chip testing method and device based on image recognition and electronic equipment |
| CN113808067A (en) * | 2020-06-11 | 2021-12-17 | 广东美的白色家电技术创新中心有限公司 | Circuit board detection method, visual detection equipment and device with storage function |
| CN111784674A (en) * | 2020-07-02 | 2020-10-16 | 深圳明锐理想科技有限公司 | Component detection method, component detection device, computer equipment and storage medium |
| CN113030121A (en) * | 2021-03-11 | 2021-06-25 | 微讯智造(广州)电子有限公司 | Automatic optical detection method, system and equipment for circuit board components |
| CN114202515A (en) * | 2021-11-29 | 2022-03-18 | 广州海谷电子科技有限公司 | Method for detecting defect of printed carbon line of humidity sensor |
| CN116152251A (en) * | 2023-04-20 | 2023-05-23 | 成都数之联科技股份有限公司 | Television backboard detection method, model training method, device, equipment and medium |
| CN116152251B (en) * | 2023-04-20 | 2023-07-14 | 成都数之联科技股份有限公司 | Television backboard detection method, model training method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2017215241A1 (en) | 2017-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106127746A (en) | Circuit board component missing part detection method and system | |
| CN112053318B (en) | Two-dimensional PCB defect real-time automatic detection and classification device based on deep learning | |
| CN105510348B (en) | A kind of defect inspection method of printed circuit board, device and detection device | |
| CN103091331B (en) | System and method for visual inspection on burrs and stain defects of radio frequency identification (RFID) antennae | |
| Mahalingam et al. | Pcb-metal: A pcb image dataset for advanced computer vision machine learning component analysis | |
| CN111899241B (en) | Quantitative on-line detection method and system for defects of PCB (printed Circuit Board) patches in front of furnace | |
| CN105588840B (en) | A kind of electronic units fix method and device | |
| CN109946303A (en) | Check device and method | |
| CN110929720B (en) | Component detection method based on LOGO matching and OCR | |
| TWI618940B (en) | Device and method for detecting blind hole of printed circuit board | |
| CN105303573B (en) | The pin detection method and system of acupuncture needle class component | |
| US11315229B2 (en) | Method for training defect detector | |
| TWI715051B (en) | Machine learning method and automatic optical inspection device using the method thereof | |
| EP4046072A1 (en) | Image analysis system for testing in manufacturing | |
| CN104201130A (en) | Optical detection method for defect classification | |
| CN110346704A (en) | Determination method, apparatus, equipment and the storage medium of test file in board test | |
| CN105354816B (en) | A kind of electronic units fix method and device | |
| KR102174424B1 (en) | Method for Inspecting Component basesd Server and system and apparatus therefor | |
| Santoso et al. | Development of pcb defect detection system using image processing with yolo cnn method | |
| Caliskan et al. | Design and realization of an automatic optical inspection system for PCB solder joints | |
| Khare et al. | PCB-fire: Automated classification and fault detection in PCB | |
| CN113822836A (en) | Method of marking an image | |
| TWI755953B (en) | Automatic detection system and operation method thereof | |
| CN109975686B (en) | Circuit board short circuit automatic identification method based on infrared image processing | |
| CN112529902A (en) | Hole checking method of PCB (printed circuit board) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161116 |
|
| RJ01 | Rejection of invention patent application after publication |