CN105092598B - A kind of large format pcb board defect method for quickly identifying and system based on connected domain - Google Patents
A kind of large format pcb board defect method for quickly identifying and system based on connected domain Download PDFInfo
- Publication number
- CN105092598B CN105092598B CN201510629501.0A CN201510629501A CN105092598B CN 105092598 B CN105092598 B CN 105092598B CN 201510629501 A CN201510629501 A CN 201510629501A CN 105092598 B CN105092598 B CN 105092598B
- Authority
- CN
- China
- Prior art keywords
- connected domain
- defect
- standard picture
- scan image
- judge
- 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
Abstract
The present invention is applied to printed circuit board monitoring field, provide a kind of large format pcb board defect method for quickly identifying based on connected domain, the connected domain of respective all target areas is extracted respectively, and it is identified, calculating sifting is carried out according to the characteristic quantity of connected domain, delete some essentially identical connected domains in the range of allowable error, the defects of filtering out defect connected domain scan image and corresponding to connected domain standard picture, then the defects of being further advanced by poor shadow and analyze the difference found out between two image connectivity domains, and then being finally completed PCB identifies.The present invention causes the number of variations of connected domain to judge defect type according to the defects of printed circuit board, inventive algorithm is relatively easy, and the PCB typical defects such as short-circuit, breaking, residual copper, thread cast-off are can detect that by the analysis of images match, connected domain search and poor shadow.
Description
Technical field
The invention belongs to printed circuit board (PCB) detecting and identification field, more particularly to a kind of large format PCB based on connected domain
Board defect method for quickly identifying and system.
Background technology
At present, the detection and recognition methods of PCB (Printed Circuit Board, printed circuit board) base board defect are returned
Receiving has three classes:With reference to comparison method, nonreferential method and mixing method.
(1) comparison method is referred to：This method is to be contrasted the standard picture of reference and detected image, i.e. XOR
Computing, this algorithm is simple, fastest, also easily realizes, but not can determine that defect classification.
(2) nonreferential method：Without reference picture, it judges to treat this method according to pre-defined design rule
Whether detection PCB image has flaw, if not meeting design rule, has been considered as, therefore also referred to as design rule check addition, should
Method memory requirements is small, but algorithm comparison is complicated, and full figure need to be searched for, and operand is very big, therefore realizes that detection is relatively more tired in real time
Difficulty, and the big defects such as wire, pad loss can not be detected.
(3) mixing method：It is the synthesis of foregoing two methods, the shortcomings that overcoming preceding two classes method to a certain extent,
But current this method is not also very ripe, and its algorithm is complicated, it is impossible to meet the requirement detected in real time, and adaptivity is inadequate,
System extended capability is poor.
The content of the invention
The technical problems to be solved by the invention are that providing a kind of large format pcb board defect based on connected domain quickly knows
Other method and system, it is intended to it is complicated to solve current PCB substrate detection algorithm, it is impossible to the problem of determining defect classification.
The present invention is achieved in that a kind of large format pcb board defect method for quickly identifying based on connected domain, including with
Lower step：
Step A, the pcb board scan image collected is consistent for size with standard picture processing；
Step B, the connected domain of the scan image and the standard picture is found out respectively and is identified, is swept to described
Same connected domain in tracing picture and the standard picture carries out characteristic quantity and compares calculating, is screened and is deleted according to result of calculation
Remove, obtain defect connected domain scan image and connected domain standard picture the defects of correspondence；
Step C, by the defect connected domain scan image and the defect connected domain standard picture step-by-step XOR, obtain difference
Shadow figure；
Step D, by the poor shadow figure and the defect connected domain scan image step-by-step with obtaining the first false defect figure；
Step E, each defect connected domain in the first false defect figure is taken, is pressed with the defect connected domain standard picture
Position or, judge pcb board defect；
Step F, by the poor shadow figure and the defect connected domain standard picture step-by-step with obtaining the second false defect figure；
Step G, each defect connected domain in the second false defect figure is taken, is pressed with the defect connected domain scan image
Position or, judge pcb board defect.
Further, the step B comprises the following steps：
Step B1：Connected domain area ratio of the same connected domain in scan image and standard picture is calculated, connection is represented with A
Domain area ratio, set the connected domain area than lower limit AminWith higher limit Amax, as A ＜ AminOr A ＞ AmaxWhen, judge institute
It is defect connected domain to state connected domain；
Step B2：Work as Amin＜ A ＜ AmaxWhen, connected domain similarity ratio is calculated, the connected domain similarity ratio is represented with S,
Set the connected domain similarity than lower limit Smin, as S ＞ SminWhen, it is non-defective connected domain to judge the connected domain；
As S ＜ SminWhen, judge the connected domain for defect connected domain；
Step B3：By the pixel point deletion of the non-defective connected domain and the connected domain of the corresponding standard picture, obtain
To the defect connected domain scan image and the defects of corresponding to connected domain standard picture.
Further, the step E is specially：
Take each defect connected domain in the first false defect figure, with the defect connected domain standard picture step-by-step or：
If the defect connected domain standard picture connected domain number is reduced, judge the defect for circuit defect；
If the defect connected domain standard picture connected domain number increase, judges the defect for residual copper defect.
Further, the step G is specially：
Take each defect connected domain in the second false defect figure, with the defect connected domain scan image step-by-step or：
If the defect connected domain scan image connected domain number is reduced, judge the defect for open defect；
If the defect connected domain scan image connected domain number increase, judges the defect for thread cast-off defect.
Present invention also offers a kind of large format pcb board defect system for rapidly identifying based on connected domain, including：
Image matching unit, pcb board scan image and standard picture processing for that will collect are size phase one
Cause；
Image computing unit, the connected domain for finding out the scan image and the standard picture respectively are gone forward side by side rower
Know, carrying out characteristic quantity to the same connected domain in the scan image and the standard picture compares calculating, according to result of calculation
Screened and deleted, obtain defect connected domain scan image and connected domain standard picture the defects of correspondence；
Image XOR unit, for by the defect connected domain scan image and the defect connected domain standard picture step-by-step
XOR, obtain poor shadow figure；
Image and unit, for by the poor shadow figure and the defect connected domain scan image step-by-step with it is pseudo- to obtain first
Defect map；It is additionally operable to the poor shadow figure and the defect connected domain standard picture step-by-step with obtaining the second false defect figure；
Judging unit, for taking each defect connected domain in the first false defect figure, with the defect connected domain mark
Quasi- image step-by-step or, judge pcb board defect；It is additionally operable to take each defect connected domain in the second false defect figure, it is and described
Defect connected domain scan image step-by-step or, judge pcb board defect.
Further, described image computing unit includes：
Area is than computing module, for calculating connected domain area of the same connected domain in scan image and standard picture
Than, with A represent the connected domain area than set the connected domain area than lower limit AminWith higher limit Amax, as A ＜ Amin
Or A ＞ AmaxWhen, judge the connected domain for defect connected domain；
Similarity is than computing module, for working as Amin＜ A ＜ AmaxWhen, connected domain similarity ratio is calculated, the company is represented with S
Logical domain similarity ratio, set the connected domain similarity than lower limit Smin, as S ＞ SminWhen, it is non-to judge the connected domain
Defect connected domain；
As S ＜ SminWhen, judge the connected domain for defect connected domain；
Removing module, for the pixel of the non-defective connected domain and the connected domain of the corresponding standard picture to be deleted
Remove, obtain the defect connected domain scan image and the defects of corresponding to connected domain standard picture.
Further, the judging unit includes：
First judge module, for taking each defect connected domain in the first false defect figure, connected with the defect
Domain standard picture step-by-step or：
If the defect connected domain standard picture connected domain number is reduced, judge the defect for circuit defect；
If the defect connected domain standard picture connected domain number increase, judges the defect for residual copper defect；
Second judge module, for taking each defect connected domain in the second false defect figure, connected with the defect
Domain scan image step-by-step or：
If the defect connected domain scan image connected domain number is reduced, judge the defect for open defect；
If the defect connected domain scan image connected domain number increase, judges the defect for thread cast-off defect.
Compared with prior art, beneficial effect is the present invention：The present invention is improved on the basis of with reference to comparison method,
The number of variations of connected domain is caused to judge defect type according to the defects of printed circuit board, inventive algorithm is relatively easy,
The PCB typical defects such as short-circuit, breaking, residual copper, thread cast-off can detect that by the analysis of images match, connected domain search and poor shadow.
Brief description of the drawings
Fig. 1 is the consistent scan image of size provided in an embodiment of the present invention, standard drawing and its poor shadow figure of the two.
Fig. 2 is a kind of large format pcb board defect method for quickly identifying based on connected domain provided in an embodiment of the present invention
Flow chart.
Fig. 3 is a kind of large format pcb board defect system for rapidly identifying based on connected domain provided in an embodiment of the present invention
Structural representation.
Fig. 4 is the structural representation of image computing unit provided in an embodiment of the present invention.
Fig. 5 is the structural representation of judging unit provided in an embodiment of the present invention.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
The pcb board scanning figure collected is subjected to binary conversion treatment, and the Gerber files for extracting pcb board are converted into standard
Image, the two is handled to obtain two consistent width figures of size, as Fig. 1 (a) is respectively one detected with 1 (b)
Scan image and corresponding standard picture.Fig. 1 (c) is scanning figure and the result of standard drawing difference movie queen.
Notice that the poor shadow figure of scanning figure and the directly poor movie queen of standard drawing is not more for 0 pixel, illustrate scanning figure and
Standard drawing is not quite identical, and this is due to that tested altimetric image has distortion to cause without position either input picture is directed at completely
, this dislocation or distortion are the basic problems run into by control methods detection image, therefore, to two width of n pixel
Figure pixel-by-pixel carry out defect recognition when not only error it is big, computation complexity is very high, is n2。
Analyze short-circuit, breaking, residual copper, thread cast-off defect influences on scan image connected domain, scanning where circuit defect causes
The area increase of image connectivity domain, entire image connected domain number are reduced；Scan image connected domain area where open defect causes
Reduce, the increase of entire image connected domain number；Scan image connected domain area increase where residual copper defect causes, entire image connect
Logical domain number increase；Scan image connected domain area is reduced where thread cast-off defect causes, and entire image connected domain number is reduced.Profit
With the characteristic, analyzed by images match, the search of connected domain number and poor shadow and accurately detect four kinds of defects.
From above-mentioned principle, Fig. 2 shows a kind of large format pcb board based on connected domain provided in an embodiment of the present invention
The flow of defect method for quickly identifying, is comprised the following steps that：
S1, by the pcb board scanning figure bianry image collected with making the standard drawing after the Gerber files of pcb board are changed
As carrying out coordinate matching, size consistent scan image and standard picture are obtained；
S2, the characteristic quantity calculates of same connected domain are carried out to the scan image and the standard picture, are tied according to calculating
Fruit is screened and deleted, and obtains defect connected domain scan image and connected domain standard picture the defects of correspondence；
S3, by the defect connected domain scan image and the defect connected domain standard picture step-by-step XOR, obtain poor shadow
Figure；
S4, by the poor shadow figure and the defect connected domain scan image step-by-step with obtaining the first false defect figure；
S5, each defect connected domain in the first false defect figure is taken, with the defect connected domain standard picture step-by-step
Or；
S6, judge connected domain number, if the defect connected domain standard picture connected domain number is reduced, judge the defect
For circuit defect；If the defect connected domain standard picture connected domain number increase, judges the defect for residual copper defect；
S7, by the poor shadow figure and the defect connected domain standard picture step-by-step with obtaining the second false defect figure；
S8, each defect connected domain in the second false defect figure is taken, with the defect connected domain scan image step-by-step
Or；
S9, judge connected domain number, if the defect connected domain scan image connected domain number is reduced, judge the defect
For open defect；If the defect connected domain scan image connected domain number increase, judges the defect for thread cast-off defect.
In above-mentioned steps, step S2 is specially：
Step S21；The connected domain of the scan image and the standard picture is found out respectively and is identified,
Step S22：Connected domain area ratio of the same connected domain in scan image and standard picture is calculated, represents to connect with A
Logical domain area ratio, set the connected domain area than lower limit AminWith higher limit Amax, as A ＜ AminOr A ＞ AmaxWhen, judge
The connected domain is defect connected domain；
Step S23：Work as Amin＜ A ＜ AmaxWhen, connected domain similarity ratio is calculated, the connected domain similarity ratio is represented with S,
Set the connected domain similarity than lower limit Smin, as S ＞ SminWhen, it is non-defective connected domain to judge the connected domain；
As S ＜ SminWhen, judge the connected domain for defect connected domain；
Step S24：By the pixel point deletion of the non-defective connected domain and the connected domain of the corresponding standard picture, obtain
To the defect connected domain scan image and the defects of corresponding to connected domain standard picture.
Such as Fig. 3, a kind of large format pcb board defect system for rapidly identifying based on connected domain provided in an embodiment of the present invention
Structural representation, wherein：
Image matching unit 1, for the Gerber texts of the pcb board scanning figure bianry image and making pcb board that will collect
Standard picture after part conversion carries out coordinate matching, obtains size consistent scan image and standard picture；
Image computing unit 2, for finding out the connected domain of the scan image and the standard picture respectively, to same company
Logical domain carries out characteristic quantity calculates, is screened and is deleted according to result of calculation, obtains defect connected domain scan image and corresponding
Defect connected domain standard picture；
Image XOR unit 3, for the defect connected domain scan image and the defect connected domain standard picture to be pressed
Position XOR, obtains poor shadow figure；
Image and unit 4, for by the poor shadow figure and the defect connected domain scan image step-by-step with it is pseudo- to obtain first
Defect map；It is additionally operable to the poor shadow figure and the defect connected domain standard picture step-by-step with obtaining the second false defect figure；
Judging unit 5, for taking each defect connected domain in the first false defect figure, with the defect connected domain mark
Quasi- image step-by-step or, judge pcb board defect；It is additionally operable to take each defect connected domain in the second false defect figure, it is and described
Defect connected domain scan image step-by-step or, judge pcb board defect.
Fig. 4 is the structural representation of image computing unit provided in an embodiment of the present invention, wherein；
Area is than computing module 21, for calculating connected domain area of the same connected domain in scan image and standard picture
Than, the connected domain area ratio is represented with A, set the connected domain area than lower limit AminWith higher limit Amax, as A ＜
AminOr A ＞ AmaxWhen, judge the connected domain for defect connected domain；
Similarity is than computing module 22, for working as Amin＜ A ＜ AmaxWhen, calculate connected domain phase knowledge and magnanimity ratio, represented with S described in
Connected domain similarity ratio, set the connected domain similarity than lower limit Smin, as S ＞ SminWhen, judge that the connected domain is
Non-defective connected domain；
As S ＜ SminWhen, judge the connected domain for defect connected domain；
Removing module 23, for by the pixel of the non-defective connected domain and the connected domain of the corresponding standard picture
Delete, obtain the defect connected domain scan image and the defects of corresponding to connected domain standard picture.
Fig. 5 is the structural representation of judging unit provided in an embodiment of the present invention, wherein：
First judge module 51, for taking each defect connected domain in the first false defect figure, connect with the defect
Logical domain standard picture step-by-step or：
If the defect connected domain standard picture connected domain number is reduced, judge the defect for circuit defect；
If the defect connected domain standard picture connected domain number increase, judges the defect for residual copper defect；
Second judge module 52, for taking each defect connected domain in the second false defect figure, connect with the defect
Logical domain scan image step-by-step or：
If the defect connected domain scan image connected domain number is reduced, judge the defect for open defect；
If the defect connected domain scan image connected domain number increase, judges the defect for thread cast-off defect.
Using the present invention, scan image and standard picture for carrying out defects detection after piecemeal, extract respectively respective
All target area (region that the white pixel point that target area is 1 forms, the black pixel point that background is 0 form) connections
Domain, and Digital ID is carried out, according to the connected domain size of target area, the centre of form, girth, aspect ratio and minimum external square
Shape etc. carries out judging to contrast one by one to each connected domain, deletes some essentially identical connected domains in the range of allowable error, so
After determine whether to differ in connected domain have which kind of defect, find out the difference between respective standard image and scan image connected domain
It is different, and difference section is considered as latent defect point, false defect removal is carried out afterwards, so as to detect to be truly present in PCB image
The defects of, changed according to defect to caused by scanning figure or standard drawing connected domain, it is classified, find out the position letter of defect
The defects of ceasing, being finally completed PCB identifies.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should be included in the scope of the protection.
Claims (7)
1. a kind of large format pcb board defect method for quickly identifying based on connected domain, it is characterised in that comprise the following steps：
Step A, the pcb board scan image collected is consistent for size with standard picture processing；
Step B, the connected domain of the scan image and the standard picture is found out respectively and is identified, to the scanning figure
Same connected domain in picture and the standard picture carries out characteristic quantity and compares calculating, is screened and is deleted according to result of calculation,
The defects of obtaining defect connected domain scan image and corresponding to connected domain standard picture；
Step C, by the defect connected domain scan image and the defect connected domain standard picture step-by-step XOR, obtain poor shadow
Figure；
Step D, by the poor shadow figure and the defect connected domain scan image step-by-step with obtaining the first false defect figure；
Step E, each defect connected domain in the first false defect figure is taken, with the defect connected domain standard picture step-by-step
Or, judge pcb board defect；
Step F, by the poor shadow figure and the defect connected domain standard picture step-by-step with obtaining the second false defect figure；
Step G, each defect connected domain in the second false defect figure is taken, with the defect connected domain scan image step-by-step
Or, judge pcb board defect.
2. large format pcb board defect method for quickly identifying as claimed in claim 1, it is characterised in that the step B include with
Lower step：
Step B1：Connected domain area ratio of the same connected domain in scan image and standard picture is calculated, connected domain face is represented with A
Product ratio, set the connected domain area than lower limit AminWith higher limit Amax, as A ＜ AminOr A ＞ AmaxWhen, judge the company
Logical domain is defect connected domain；
Step B2：Work as Amin＜ A ＜ AmaxWhen, connected domain similarity ratio is calculated, the connected domain similarity ratio is represented with S, is set
The connected domain similarity than lower limit Smin, as S ＞ SminWhen, it is non-defective connected domain to judge the connected domain；
As S ＜ SminWhen, judge the connected domain for defect connected domain；
Step B3：By the pixel point deletion of the non-defective connected domain and the connected domain of the corresponding standard picture, institute is obtained
State defect connected domain scan image and the defects of corresponding to connected domain standard picture.
3. large format pcb board defect method for quickly identifying as claimed in claim 1, it is characterised in that the step E is specific
For：
Take each defect connected domain in the first false defect figure, with the defect connected domain standard picture step-by-step or：
If the defect connected domain standard picture connected domain number is reduced, judge the defect for circuit defect；
If the defect connected domain standard picture connected domain number increase, judges the defect for residual copper defect.
4. large format pcb board defect method for quickly identifying as claimed in claim 1, it is characterised in that the step G is specific
For：
Take each defect connected domain in the second false defect figure, with the defect connected domain scan image step-by-step or：
If the defect connected domain scan image connected domain number is reduced, judge the defect for open defect；
If the defect connected domain scan image connected domain number increase, judges the defect for thread cast-off defect.
A kind of 5. large format pcb board defect system for rapidly identifying based on connected domain, it is characterised in that including：
Image matching unit, the pcb board scan image for that will collect are consistent for size with standard picture processing；
Image computing unit, for finding out the connected domain of the scan image and the standard picture respectively and being identified,
Characteristic quantity is carried out to the same connected domain in the scan image and the standard picture and compares calculating, is carried out according to result of calculation
Screening and deletion, obtain defect connected domain scan image and connected domain standard picture the defects of correspondence；
Image XOR unit, for the defect connected domain scan image and the defect connected domain standard picture step-by-step is different
Or, obtain poor shadow figure；
Image and unit, for by the poor shadow figure and the defect connected domain scan image step-by-step with obtaining the first false defect
Figure；It is additionally operable to the poor shadow figure and the defect connected domain standard picture step-by-step with obtaining the second false defect figure；
Judging unit, for taking each defect connected domain in the first false defect figure, with the defect connected domain standard drawing
As step-by-step or, judge pcb board defect；It is additionally operable to take each defect connected domain in the second false defect figure, with the defect
The step-by-step of connected domain scan image or, judge pcb board defect.
6. large format pcb board defect system for rapidly identifying as claimed in claim 5, it is characterised in that described image calculates single
Member includes：
Area is than computing module, for calculating connected domain area ratio of the same connected domain in scan image and standard picture, with A
Represent the connected domain area ratio, set the connected domain area than lower limit Amin and higher limit Amax, as A ＜ Amin or
During A ＞ Amax, judge the connected domain for defect connected domain；
Similarity is than computing module, for working as Amin＜ A ＜ AmaxWhen, connected domain similarity ratio is calculated, the connected domain is represented with S
Similarity ratio, set the connected domain similarity than lower limit Smin, as S ＞ SminWhen, it is non-defective to judge the connected domain
Connected domain；
As S ＜ SminWhen, judge the connected domain for defect connected domain；
Removing module, for by the pixel point deletion of the non-defective connected domain and the connected domain of the corresponding standard picture,
Obtain the defect connected domain scan image and the defects of corresponding to connected domain standard picture.
7. large format pcb board defect system for rapidly identifying as claimed in claim 5, it is characterised in that the judging unit bag
Include：
First judge module, for taking each defect connected domain in the first false defect figure, with the defect connected domain mark
Quasi- image step-by-step or：
If the defect connected domain standard picture connected domain number is reduced, judge the defect for circuit defect；
If the defect connected domain standard picture connected domain number increase, judges the defect for residual copper defect；
Second judge module, for taking each defect connected domain in the second false defect figure, swept with the defect connected domain
Tracing as step-by-step or：
If the defect connected domain scan image connected domain number is reduced, judge the defect for open defect；
If the defect connected domain scan image connected domain number increase, judges the defect for thread cast-off defect.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510629501.0A CN105092598B (en) | 2015-09-28 | 2015-09-28 | A kind of large format pcb board defect method for quickly identifying and system based on connected domain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510629501.0A CN105092598B (en) | 2015-09-28 | 2015-09-28 | A kind of large format pcb board defect method for quickly identifying and system based on connected domain |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105092598A CN105092598A (en) | 2015-11-25 |
| CN105092598B true CN105092598B (en) | 2018-02-06 |
Family
ID=54573513
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510629501.0A Active CN105092598B (en) | 2015-09-28 | 2015-09-28 | A kind of large format pcb board defect method for quickly identifying and system based on connected domain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105092598B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109785324A (en) * | 2019-02-01 | 2019-05-21 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of large format pcb board localization method |
Families Citing this family (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228546B (en) * | 2016-07-13 | 2019-01-29 | 广州视源电子科技股份有限公司 | A kind of detection method and device of board |
| CN109300102B (en) * | 2017-07-21 | 2021-05-04 | 凌云光技术股份有限公司 | Defect detection method for PCB |
| CN108344738B (en) * | 2018-01-22 | 2021-07-27 | 翰飞骏德（北京）医疗科技有限公司 | Imaging method for hydroxyapatite and device thereof |
| 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 |
| CN108230324B (en) * | 2018-01-31 | 2023-10-20 | 浙江理工大学 | Visual detection method for microdefect on surface of magnetic shoe |
| CN108537772B (en) * | 2018-02-08 | 2020-06-23 | 杭州蓝雪科技有限公司 | Visual detection method for printing defects of chip resistor positive conductor |
| CN108510476B (en) * | 2018-03-14 | 2022-03-15 | 五邑大学 | Mobile phone screen circuit detection method based on machine vision |
| CN108956616B (en) * | 2018-05-31 | 2021-02-02 | 南京航空航天大学 | Image-based workpiece defect detection method |
| CN109100370A (en) * | 2018-06-26 | 2018-12-28 | 武汉科技大学 | A kind of pcb board defect inspection method based on sciagraphy and connected domain analysis |
| CN109376770B (en) * | 2018-09-26 | 2020-10-20 | 凌云光技术集团有限责任公司 | Grid area identification method and device applied to negative film inspection machine |
| CN109815556B (en) * | 2018-12-30 | 2023-04-18 | 广州兴森快捷电路科技有限公司 | Method, device, equipment and storage medium for identifying isolated region of line layer |
| CN110009618B (en) * | 2019-04-02 | 2021-04-20 | 浙江大学 | Shaft part surface quality detection method and device |
| CN110533660B (en) * | 2019-09-03 | 2023-05-30 | 博科视(苏州)技术有限公司 | Method for detecting silk-screen defect of electronic product shell |
| CN112330597A (en) * | 2020-10-14 | 2021-02-05 | 浙江大华技术股份有限公司 | Image difference detection method and device and computer equipment |
| CN115014427A (en) * | 2021-03-05 | 2022-09-06 | 奥特斯(中国)有限公司 | Measuring physical properties of component carriers based on design data |
| CN113554626A (en) * | 2021-07-26 | 2021-10-26 | 朗华全能自控设备（上海）股份有限公司 | Method and device for detecting defects of flexible circuit board |
| CN113688807B (en) * | 2021-10-26 | 2022-02-08 | 中科慧远视觉技术(北京)有限公司 | Self-adaptive defect detection method, device, recognition system and storage medium |
| CN113781486B (en) * | 2021-11-15 | 2022-03-15 | 新恒汇电子股份有限公司 | IC card image defect detection method |
| CN114216915B (en) * | 2021-12-15 | 2024-03-29 | 江门市浩远科技有限公司 | Method for detecting and classifying class levels based on stains and defect types of circuit board |
| CN114202543B (en) * | 2022-02-18 | 2022-04-26 | 成都数之联科技股份有限公司 | Method, device, equipment and medium for detecting dirt defects of PCB (printed circuit board) |
| CN114627113B (en) * | 2022-05-12 | 2022-07-29 | 成都数之联科技股份有限公司 | Method, system, device and medium for detecting defects of printed circuit board |
| CN115018828B (en) * | 2022-08-03 | 2022-10-25 | 深圳市尹泰明电子有限公司 | Defect detection method for electronic component |
| CN116818797A (en) * | 2023-05-04 | 2023-09-29 | 四川德中智能科技有限公司 | Automatic detection method and system for PCB bare board based on machine vision |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104297254A (en) * | 2014-10-08 | 2015-01-21 | 华南理工大学 | Mixing-method-based method and system applied to defect detection of printed circuit board |
-
2015
- 2015-09-28 CN CN201510629501.0A patent/CN105092598B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104297254A (en) * | 2014-10-08 | 2015-01-21 | 华南理工大学 | Mixing-method-based method and system applied to defect detection of printed circuit board |
Non-Patent Citations (3)
| Title |
|---|
| "PCB缺陷自动检测***的研究与设计";张玙;《中国优秀硕士学位论文全文数据库 信息科技辑》;20080815(第08期);论文全文 * |
| "基于图像处理的PCB缺陷检测***的设计与研究";马彩青;《中国优秀硕士学位论文全文数据库 信息科技辑》;20100215(第02期);论文全文 * |
| 印刷电路板缺陷检测技术及***实现研究;姚文伟;《中国优秀硕士学位论文全文数据库 信息科技辑》;20121215(第12期);论文全文 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109785324A (en) * | 2019-02-01 | 2019-05-21 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of large format pcb board localization method |
| CN109785324B (en) * | 2019-02-01 | 2020-11-27 | 佛山市南海区广工大数控装备协同创新研究院 | Large-format PCB positioning method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105092598A (en) | 2015-11-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105092598B (en) | A kind of large format pcb board defect method for quickly identifying and system based on connected domain | |
| US11797886B2 (en) | Image processing device, image processing method, and image processing program | |
| US10872406B2 (en) | Hot spot defect detecting method and hot spot defect detecting system | |
| TWI557650B (en) | System and method for identifying defects in a material | |
| CN104867144B (en) | IC element welding point defect detection methods based on mixed Gauss model | |
| CN103500459A (en) | Printed circuit board defect detecting method based on regularization parameters | |
| CN105894037B (en) | A kind of full supervised classification method of remote sensing images extracted based on SIFT training sample | |
| Dave et al. | PCB defect detection using image processing and embedded system | |
| Azad et al. | A novel and robust method for automatic license plate recognition system based on pattern recognition | |
| WO2020110560A1 (en) | Inspection assistance device, inspection assistance method, and inspection assistance program for concrete structure | |
| CN104867145A (en) | IC element solder joint defect detection method based on VIBE model | |
| CN111242899A (en) | Image-based flaw detection method and computer-readable storage medium | |
| Chavan et al. | Quality control of PCB using image processing | |
| Peng et al. | Void defect detection in ball grid array X-ray images using a new blob filter | |
| CN111178445A (en) | Image processing method and device | |
| Caliskan et al. | Design and realization of an automatic optical inspection system for PCB solder joints | |
| CN103295238A (en) | ROI (region of interest) motion detection based real-time video positioning method for Android platform | |
| KR20160034196A (en) | An apparatus for evaluating form of a conductive particle and a method for evaluating form of a conductive particle | |
| CN105354833A (en) | Shadow detection method and apparatus | |
| CN112232390B (en) | High-pixel large image identification method and system | |
| CN108982544A (en) | A kind of printed circuit board flaw component detection method | |
| Niskanen et al. | Experiments with SOM based inspection of wood | |
| CN110738638B (en) | Visual saliency detection algorithm applicability prediction and performance blind evaluation method | |
| Bawa et al. | A binarization technique for extraction of devanagari text from camera based images | |
| TWI277911B (en) | An image processing method for selected fruit by the X-ray scanner to automatically identify the region of injury within the scanned fruit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20151125 Assignee: SHENZHEN SINGSUN ELECTRONIC SCIENCE & TECHNOLOGY CO.,LTD. Assignor: SHENZHEN University Contract record no.: X2023980032335 Denomination of invention: A method and system for rapid defect identification of large-format PCB based on connected domain Granted publication date: 20180206 License type: Common License Record date: 20230217 |