CN101799434A - Printing image defect detection method - Google Patents
Printing image defect detection method Download PDFInfo
- Publication number
- CN101799434A CN101799434A CN201010125146A CN201010125146A CN101799434A CN 101799434 A CN101799434 A CN 101799434A CN 201010125146 A CN201010125146 A CN 201010125146A CN 201010125146 A CN201010125146 A CN 201010125146A CN 101799434 A CN101799434 A CN 101799434A
- Authority
- CN
- China
- Prior art keywords
- image
- big
- model
- detection
- detected
- 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.)
- Granted
Links
Images
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a printing image defect detection method, which comprises the following steps: carrying out real-time image model learning in a gray scale region and a gradient region by aiming at specific images on a large image; comparing the large image to be detected to the a gray scale region model and a gradient region model established during learning; realizing small-dimension strong-contrast defect detection through Blob cluster analysis; when no small-dimension strong-contrast defect is detected, dividing the large image into sub regions, and respectively calculating image integrated features; adopting a variable threshold method for carrying out threshold division on each sub region; carrying out Blob cluster analysis on divided images; and realizing the large-area weak-contrast defect detection. Compared with the prior art, the invention does not rely on a reference template, is not sensitive on the real-time imaging brightness change, can overcome the defects of missing detection, error detection and poor self adaptation of the template by using a reference template comparison detection method, and can simultaneously solve the problems of eliminating tiny wrinkles and blackspots in printing and papermaking industries.
Description
Technical field
The present invention relates to a kind of printing image defect detection method, particularly relate to a kind of under high speed image disposition condition, to the detection method of defectives such as strong contrast defective of printed images small-medium size and large tracts of land weak contrast's fold, spot.
Background technology
At present, in the printing and the machine vision applications of paper industry, mainly be that iconic model contrasts for the core methed of printing and paper defects detection.Set up iconic model by the specific training set of choosing in advance in different characteristics of image territories, allow current image to be detected and these iconic models pursue pixel comparison and judge its contrast difference's value, the size according to the statistical discrepancy value obtains testing result at last.Objective factors such as the flat field correction coefficient was inconsistent when but flat field correction was with detection during owing to light source decay, camera lens pollution, modeling, exposure parameter is inconsistent, often produce the iconic model average drifting, the result can't detect weak contrast's fold, spot, has defectives such as omission, flase drop and template self-adaptation difference.
Actual industrial production also requires to judge at a high speed when guaranteeing product quality rejects waste product, therefore finds and does not a kind ofly rely on the high speed of benchmark template, printing image defect detection method is very important accurately.
Summary of the invention
Purpose of the present invention is exactly at the deficiencies in the prior art, provide a kind of and do not rely on the benchmark template, brightness changes insensitive printing image defect detection method to real time imagery, not only solve the shortcoming of utilizing omission, flase drop and template self-adaptation difference that benchmark template comparison and detection method exists, and can solve printing and paper industry is rejected the difficult problem of trickle fold, spot.
For achieving the above object, technical scheme of the present invention is as follows:
The present invention proposes a kind of printing image defect detection method, principle---the residual error detection method of whole difference and the combination of fritter interpolation out-phase of imitation human eye detection.Described printing image defect detection method step is as follows:
(1) gathers current big image to be detected, current big image to be detected carried out two-stage image search location, search big specific image block of opening on the image, set up the Mask image and (promptly mask other zones outside the specific image block that searches, also be Mask shielding area image), for subsequent calculations provides shielding area image comparison template.
(2) carry out the realtime graphic model learning at the specific image block (promptly not shielding area) that searches in (1) step in gray scale territory and gradient field, set up not the gray scale area image model and the gradient field iconic model of shielding area, gray scale area image model and gradient field iconic model that current big image to be detected and study are set up compare, according to the Blob cluster analysis, realize the detection of opening the strong contrast defective of small size on the image to big.
(3) there is not the strong contrast defective of small size if do not detect big opening on the image, then, will opens image division greatly and become subregion, each subregion difference computed image comprehensive characteristics according to the branch block size of preset value; Adopt the variable thresholding method, above-mentioned each subregion that is divided into is carried out Threshold Segmentation; The split image that obtains is carried out the Blob cluster analysis, extract the characteristics of image and the graphic feature (as the ratio of abnormal area border and area) of feature abnormalities point,, realize large tracts of land weak contrast defects detection according to detecting specification requirement.It is according to the concrete goal task that detects that the size of described piecemeal preset value sets one, the 2nd, and on behalf of this provincial characteristics, whether the image synthesis feature that the zygote zone is extracted can react decide.When testing goal was inside character about subregion, described image synthesis feature can comprise characteristic quantities such as color, texture, entropy; As detect one big when opening printed matter whether relatively large local colour cast problem being arranged, the image synthesis feature can indicate the subregion feature with characteristic quantities such as HIS, YUV, and (whether the zone that for example needs to judge 9 * 9 elemental area sizes has the colour cast problem, then the piecemeal preset value can be made as 9 * 9, and calculates this regional HIS, YUV eigenwert); As detect one big when opening printed matter whether long shallow impression problem being arranged, the gradient mean value in the image synthesis feature available sub-regions, the statistical moment of grey level histogram.Described variable thresholding method is that according to the probability distribution of the problem of detection, selected threshold can reflect the detection target through after the image synthesis feature of calculating subregion.
There is the strong contrast defective of small size if detect big opening on the image, then detects termination.
Exist the big image of opening of defective to reject processing to detecting.
The present invention does not set up a template by learning a series of object in advance, do in that event, when imaging changes to some extent, certainly will rebulid a new template, therefore the present invention adopts and sets up a template in real time according to current big image to be detected: some need not detect or characteristics of image has the zone of bigger variation with two-stage image search location shielding earlier, to shielding area (specific image block that searches) not, set up a template with the whole statistic (as gray scale, gradient) of present image.Above-mentioned (2) and (3) step comprise twice Blob cluster analysis, but the two pretreatment mode, detected parameters setting, testing goal are all different.Blob cluster analysis in (2) step is at the strong contrast defective of small size; Blob cluster analysis in (3) step is at large tracts of land weak contrast defective, mainly prevent (2) step omission weak contrast defective, because the realtime graphic model all can have a up and down deviation range with the benchmark template is the same, but large tracts of land weak contrast defective we can feel it is wrong object by human eye at once.This detection method can meet the principle of human eye detection preferably.
Because there is deviation in the mechanical driving part of defeated paper, make the paper image have the locus skew, simultaneously owing to can there be technological fluctuation in specific objective object (as watermark) on the printed images, therefore before carrying out image detection, must open the two-stage image search location of image and specific region greatly.Described two-stage image search location, concrete steps are as follows: choose specific image block (by the Flame Image Process slip-stick artist according to the pending characteristics of image of reality, selection has the image-region of distinct characteristic, as security patterns such as watermarks, this image-region generally occurs big opening in the image according to certain rules repeatedly) as search locating template figure T, this template figure T is overlayed on current big the image S to be detected then, and realize the search location by translation, search big opening on the image and the consistent specific image block of this template figure T; Search graph (specific image block) under template figure T covers is called subgraph S
I, j, wherein i, j are the coordinate of this subgraph top left corner pixel point in the big image S of opening, and are called reference point.The core of search location is the definition of similarity measurement criterion, and the similarity measurement criterion has multiple, according to different similarity measurement criterions different search localization methods is arranged, and specifically can adopt the related function method or based on the statistics with histogram method of nuclear.
The gray scale area image model that described study is set up be the gray scale territory by the high and low iconic model of pixel, comprise high gray-value image model and low gray-value image model.Described current big image to be detected compares with the gray scale area image model that study is set up, according to the Blob cluster analysis, realization is to big detection of opening the strong contrast defective of small size on the image, concrete steps are as follows: current big image to be detected and high gray-value image model are pursued pixel comparison, obtain comparing result figure C
hCurrent big image to be detected and low gray-value image model are pursued pixel comparison, obtain comparing result figure C
lRespectively to comparing result figure C
hAnd C
lCarry out binary conversion treatment (can adopt multiple image binaryzation method), form the Blob cluster; According to different surveyed areas and different accuracy of detection, set high gray-scale value comparison and detection threshold value T
hWith low gray-scale value comparison and detection threshold value T
lAccording to the size of each Blob cluster of detection threshold comparison, judge on the big image whether have the strong contrast defective of small size.
Described current big image to be detected compares with the gradient field iconic model that study is set up, according to the Blob cluster analysis, realization is to big detection of opening the strong contrast defective of small size on the image, concrete steps are as follows: select gradient operator, current big image to be detected carried out gradient calculation, and further eliminate noise gradient and the interference of pseudo-gradient, form gradient map G; Gradient field iconic model G with gradient map G and study foundation
mCompare, obtain comparing result figure C
gTo comparing result figure C
gCarry out binary conversion treatment, form the Blob cluster; According to different surveyed areas and different accuracy of detection, set gradient comparison and detection threshold value T
gAccording to the size of each Blob cluster of detection threshold comparison, judge on the big image whether have the strong contrast defective of small size.
Described Blob cluster analysis can be divided into image characteristic analysis and graphic feature analysis.Image characteristic analysis mainly refers to intensity and the energy of Blob, mainly calculates by the gray scale or the gray scale residual error of Blob image-region; The graphic feature analysis refers to by binary conversion treatment image information is converted into the shape information of pattern, such as figure barycenter, graphics area, figure girth, the external minimum rectangle of figure and other graphical informations, thereby can real defect and false defect be distinguished according to the graphic feature difference, typical B lob graphic feature has: the ratio of Blob area and boundary rectangle area, Blob extensibility, minimum external long axis of ellipse angle etc.
Compared with prior art, the invention has the beneficial effects as follows: do not rely on the benchmark template, change insensitive real time imagery brightness, testing result at a high speed, accurately, can solve the shortcoming of omission, flase drop and the template self-adaptation difference of utilizing the existence of benchmark template comparison and detection method, can solve printing and paper industry simultaneously and reject the difficult problem of trickle fold, spot.
Description of drawings
Fig. 1 is the printing image defect detection method schematic flow sheet.
Embodiment
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are further described.
On the printing production line of a wrapping paper, need whether exist defective to detect to printed images.Adopt printing image defect detection method of the present invention, as shown in Figure 1, concrete steps are as follows:
At first, gather current big image to be detected, current big image to be detected carried out two-stage image search location, choose the watermark security pattern as search locating template figure, this template figure is overlayed on current big the image to be detected then, and realize the search location, search big opening on the image and the consistent specific image block of this template figure by translation, mask other zones outside the specific image block, set up the Mask image.
Second step, carry out the realtime graphic model learning at the specific image block that searches in the first step in gray scale territory and gradient field, set up gray scale area image model and gradient field iconic model, gray scale area image model and gradient field iconic model that current big image to be detected and study are set up compare, according to the Blob cluster analysis, realize the detection of opening the strong contrast defective of small size on the image to big.
The gray scale area image model that described study is set up comprises high gray-value image model and low gray-value image model; Current big image to be detected and high gray-value image model are pursued pixel comparison, obtain comparing result figure C
hCurrent big image to be detected and low gray-value image model are pursued pixel comparison, obtain comparing result figure C
lAdopt the OTSU method respectively to comparing result figure C
hAnd C
lCarry out binary conversion treatment, form the Blob cluster.According to different surveyed areas and different accuracy of detection, set different detection thresholds: near the specific region precision prescribed height of 1 centimetre of watermark, calculate corresponding defective minimum area pixel value according to actual imaging resolution, the high gray-scale value comparison and detection threshold value of setting this zone is T
hIndividual pixel, low gray-scale value comparison and detection threshold value are T
lIndividual pixel; And other regional precision prescribeies are low, and setting other regional high gray-scale value comparison and detection threshold values is T
h' individual pixel, low gray-scale value comparison and detection threshold value be T
l' individual pixel.As comparing result figure C
hAnd C
lThe arbitrary Blob cluster area that forms after the binary conversion treatment is just thought to have defective during greater than the corresponding detection threshold set.
Select the Sobel gradient operator, current big image to be detected carried out gradient calculation, and further eliminate noise gradient and the interference of pseudo-gradient, form gradient map G; Gradient field iconic model G with gradient map G and study foundation
mCompare, obtain comparing result figure C
gAdopt the OTSU method to comparing result figure C
gCarry out binary conversion treatment, form the Blob cluster.According to different surveyed areas and different accuracy of detection, set the gradient comparison and detection threshold value of zones of different: near the specific region precision prescribed height of 1 centimetre of watermark, calculate corresponding defective minimum area pixel value according to actual imaging resolution, setting this regional gradient comparison and detection threshold value is T
gIndividual pixel; And other regional precision prescribeies are low, and setting this regional gradient comparison and detection threshold value is T
g' individual pixel.As comparing result figure C
gThe Blob cluster area that forms after the binary conversion treatment is just thought to have defective during greater than the corresponding detection threshold set.
Above-mentioned 3 width of cloth comparing result figure C
h, C
lAnd C
gAt the difference of dealing with problems: and the standard specification product are compared C
hWhat reflect is the regional distribution chart of bright partially residual point, C
lWhat reflect is the regional distribution chart of dark partially residual point, C
gWhat reflect is bright dark variation abnormality regional distribution chart; After this 3 width of cloth comparing result figure carries out binary conversion treatment, as long as wherein there is the strong contrast defective of small size greater than the corresponding detection threshold of setting in the arbitrary Blob cluster area that forms with regard to current big the image to be detected of decidable.
There was not the strong contrast defective of small size in the 3rd step if second step detected big opening on the image, next needed to detect the shallow impression problem that whether has 9 length in pixels.According to concrete detection goal task, the zone of adopting 32 * 32 elemental area sizes is as a minute block size (getting the area size of gray variance value when being peak value is piecemeal preset value size), to open image division greatly and become subregion, each subregion will be calculated the gray variance value respectively as the image synthesis feature.Adopt normal distribution from the gray variance value of all subregions, obtain segmentation threshold above-mentioned each subregion that is divided into is carried out Threshold Segmentation; When the gray variance value of subregion then belongs to unusual subregion greater than this threshold value, then this subregion is made as 255, and the gray variance value is made as 0 smaller or equal to the subregion of this threshold value.The split image that obtains is carried out the Blob cluster analysis, extract the characteristics of image and the graphic feature that are made as the Blob that 255 subregion forms; Because need to detect the shallow impression problem that whether has 9 length in pixels, therefore the length of working as Blob then is judged to be the shallow impression defective that has 9 length in pixels greater than 9 pixels.
Have the strong contrast defective of small size if second step detected big opening on the image, then detection stops, and no longer needs to carry out large tracts of land weak contrast defects detection.
Claims (4)
1. printing image defect detection method, it is characterized in that: described printing image defect detection method step is as follows:
(1) gathers current big image to be detected, current big image to be detected carried out two-stage image search location, search big specific image block of opening on the image, set up the Mask image;
(2) carry out the realtime graphic model learning at the specific image block that searches in (1) step in gray scale territory and gradient field, set up gray scale area image model and gradient field iconic model, gray scale area image model and gradient field iconic model that current big image to be detected and study are set up compare, according to the Blob cluster analysis, realize the detection of opening the strong contrast defective of small size on the image to big;
(3) there is not the strong contrast defective of small size if do not detect big opening on the image, then, will opens image division greatly and become subregion, each subregion difference computed image comprehensive characteristics according to the branch block size of preset value; Adopt the variable thresholding method, above-mentioned each subregion that is divided into is carried out Threshold Segmentation; The split image that obtains is carried out the Blob cluster analysis, extract the characteristics of image and the graphic feature of feature abnormalities point,, realize large tracts of land weak contrast defects detection according to detecting specification requirement;
There is the strong contrast defective of small size if detect big opening on the image, then detects termination.
2. printing image defect detection method according to claim 1, it is characterized in that: described two-stage image search location, concrete steps are as follows: choose specific image block as search locating template figure, then this template figure is overlayed on current big the image to be detected, and realize the search location by translation, search big opening on the image and the consistent specific image block of this template figure.
3. printing image defect detection method according to claim 1 and 2 is characterized in that: the gray scale area image model that described study is set up comprises high gray-value image model and low gray-value image model; Described current big image to be detected compares with the gray scale area image model that study is set up, according to the Blob cluster analysis, realization is to big detection of opening the strong contrast defective of small size on the image, concrete steps are as follows: current big image to be detected and high gray-value image model are pursued pixel comparison, obtain comparing result figure C
hCurrent big image to be detected and low gray-value image model are pursued pixel comparison, obtain comparing result figure C
lRespectively to comparing result figure C
hAnd C
lCarry out binary conversion treatment, form the Blob cluster; According to different surveyed areas and different accuracy of detection, set high gray-scale value comparison and detection threshold value Th and low gray-scale value comparison and detection threshold value T
lAccording to the size of detection threshold comparison Blob cluster, judge on the big image whether have the strong contrast defective of small size.
4. printing image defect detection method according to claim 1 and 2, it is characterized in that: described current big image to be detected compares with the gradient field iconic model that study is set up, according to the Blob cluster analysis, realization is to big detection of opening the strong contrast defective of small size on the image, concrete steps are as follows: select gradient operator, current big image to be detected carried out gradient calculation, and further eliminate noise gradient and the interference of pseudo-gradient, form gradient map G; Gradient field iconic model G with gradient map G and study foundation
mCompare, obtain comparing result figure C
gTo comparing result figure C
gCarry out binary conversion treatment, form the Blob cluster; According to different surveyed areas and different accuracy of detection, set gradient comparison and detection threshold value T
gAccording to the size of detection threshold comparison Blob cluster, judge on the big image whether have the strong contrast defective of small size.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101251460A CN101799434B (en) | 2010-03-15 | 2010-03-15 | Printing image defect detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101251460A CN101799434B (en) | 2010-03-15 | 2010-03-15 | Printing image defect detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101799434A true CN101799434A (en) | 2010-08-11 |
| CN101799434B CN101799434B (en) | 2011-06-29 |
Family
ID=42595199
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010101251460A Active CN101799434B (en) | 2010-03-15 | 2010-03-15 | Printing image defect detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101799434B (en) |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102042812A (en) * | 2010-09-15 | 2011-05-04 | 苏州凌创电子系统有限公司 | Visual machine detection method |
| CN102841102A (en) * | 2012-09-05 | 2012-12-26 | 同济大学 | Recognition method and device for micro-scale damage point in damage threshold measurement |
| CN102928434A (en) * | 2012-08-23 | 2013-02-13 | 深圳市纳研科技有限公司 | Method and apparatus for array graphic detection |
| CN103163156A (en) * | 2013-03-21 | 2013-06-19 | 万新光学集团有限公司 | Automatic grading method of lens defects based on machine vision technology |
| CN103439338A (en) * | 2013-08-30 | 2013-12-11 | 无锡金视界科技有限公司 | Classification method for film defects |
| CN103454282A (en) * | 2013-08-30 | 2013-12-18 | 陕西科技大学 | Gray-gradient-based measurement method of mottle of printed product |
| CN105066892A (en) * | 2015-08-05 | 2015-11-18 | 哈尔滨工业大学 | BGA element detecting and positioning method based on linear clustering analysis |
| CN106097371A (en) * | 2016-06-23 | 2016-11-09 | 凌云光技术集团有限责任公司 | A kind of flaw detection method and system |
| CN106442562A (en) * | 2016-08-31 | 2017-02-22 | 上海华力微电子有限公司 | Method for breaking through detection limit of apparent defect drilling crew |
| CN106855520A (en) * | 2017-02-10 | 2017-06-16 | 南京航空航天大学 | A kind of workpiece, defect detection method based on machine vision |
| CN106898082A (en) * | 2017-03-15 | 2017-06-27 | 深圳怡化电脑股份有限公司 | A kind of image is stained the method and device of judgement |
| US9704236B2 (en) | 2011-09-27 | 2017-07-11 | Hewlett-Packard Development Company, L.P. | Detecting printing effects |
| CN106940885A (en) * | 2017-01-16 | 2017-07-11 | 北京印钞有限公司 | A kind of online test method of fluorescent ink printing defects |
| CN107862679A (en) * | 2017-10-20 | 2018-03-30 | 歌尔股份有限公司 | The determination method and device of image detection region |
| CN108254385A (en) * | 2016-12-29 | 2018-07-06 | 东莞东聚电子电讯制品有限公司 | Nanoscale automatic optical detecting system |
| CN108939524A (en) * | 2017-07-03 | 2018-12-07 | 孙维军 | A kind of place monitoring management method for ice and snow sports |
| CN109376770A (en) * | 2018-09-26 | 2019-02-22 | 凌云光技术集团有限责任公司 | A kind of net region recognition methods and device applied to egative film check machine |
| CN109507209A (en) * | 2019-01-22 | 2019-03-22 | 中科院金华信息技术有限公司 | A kind of film printing defect detecting system and method |
| CN110632094A (en) * | 2019-07-24 | 2019-12-31 | 北京中科慧眼科技有限公司 | Pattern quality detection method, device and system based on point-by-point comparison analysis |
| CN110648330A (en) * | 2019-11-28 | 2020-01-03 | 征图新视(江苏)科技股份有限公司 | Defect detection method for camera glass |
| CN110717889A (en) * | 2019-09-06 | 2020-01-21 | 深圳新视智科技术有限公司 | Defect detection method and device based on digital printing, terminal and readable medium |
| CN111062919A (en) * | 2019-12-12 | 2020-04-24 | 韦士肯(厦门)智能科技有限公司 | Bearing ring appearance defect detection method |
| CN111161222A (en) * | 2019-12-13 | 2020-05-15 | 北京印刷学院 | Printing roller defect detection method based on visual saliency |
| CN111242896A (en) * | 2019-12-31 | 2020-06-05 | 电子科技大学 | Color printing label defect detection and quality rating method |
| CN111426693A (en) * | 2020-04-26 | 2020-07-17 | 湖南恒岳重钢钢结构工程有限公司 | Quality defect detection system and detection method thereof |
| CN111768348A (en) * | 2020-05-29 | 2020-10-13 | 合肥联宝信息技术有限公司 | Defect detection method, device and computer readable storage medium |
| CN112561849A (en) * | 2019-09-26 | 2021-03-26 | 长鑫存储技术有限公司 | Wafer defect detection method |
| CN112789499A (en) * | 2018-10-01 | 2021-05-11 | 世高株式会社 | Teacher data generation device and teacher data generation program |
| CN113030093A (en) * | 2020-12-30 | 2021-06-25 | 凌云光技术股份有限公司 | Battery diaphragm surface defect detection method and system |
| CN113256872A (en) * | 2020-12-31 | 2021-08-13 | 深圳怡化电脑股份有限公司 | Image sensor parameter configuration method and device, computer equipment and storage medium |
| CN113406110A (en) * | 2021-05-20 | 2021-09-17 | 广州市花都联华包装材料有限公司 | Printing quality detection method, device, equipment and computer medium |
| CN113533372A (en) * | 2021-07-12 | 2021-10-22 | 浙江理工大学 | Paper defect detection method, system, device and computer storage medium |
| CN114627080A (en) * | 2022-03-16 | 2022-06-14 | 江苏巨杰机电有限公司 | Vehicle stamping accessory defect detection method based on computer vision |
| CN115018828A (en) * | 2022-08-03 | 2022-09-06 | 深圳市尹泰明电子有限公司 | Defect detection method for electronic component |
| US20220318976A1 (en) * | 2021-03-31 | 2022-10-06 | Canon Kabushiki Kaisha | Apparatus for inspecting defect of printed material, method, and storage medium |
| CN115861722A (en) * | 2023-03-02 | 2023-03-28 | 江西服装学院 | Fabric sand washing process abnormity detection method and system |
| CN116758071A (en) * | 2023-08-17 | 2023-09-15 | 青岛冠宝林活性炭有限公司 | Intelligent detection method for carbon electrode dirt under visual assistance |
| CN117541588A (en) * | 2024-01-10 | 2024-02-09 | 大连建峰印业有限公司 | Printing defect detection method for paper product |
| CN117830315A (en) * | 2024-03-05 | 2024-04-05 | 渭南大东印刷包装机械有限公司 | Real-time monitoring method and system for printing machine based on image processing |
| CN118229688A (en) * | 2024-05-27 | 2024-06-21 | 山东幻彩包装有限公司 | Corrugated paper fold defect detection method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030190075A1 (en) * | 2001-10-31 | 2003-10-09 | Infowrap, Inc. | Method for illumination independent change detection in a pair of registered gray images |
| CN1532541A (en) * | 2003-03-21 | 2004-09-29 | 中国印钞造币总公司 | Detecting method for color printing quality |
| CN101256157A (en) * | 2008-03-26 | 2008-09-03 | 广州中国科学院工业技术研究院 | Method and apparatus for testing surface defect |
| CN101561932A (en) * | 2009-05-12 | 2009-10-21 | 北京交通大学 | Method and device for detecting real-time movement target under dynamic and complicated background |
-
2010
- 2010-03-15 CN CN2010101251460A patent/CN101799434B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030190075A1 (en) * | 2001-10-31 | 2003-10-09 | Infowrap, Inc. | Method for illumination independent change detection in a pair of registered gray images |
| CN1532541A (en) * | 2003-03-21 | 2004-09-29 | 中国印钞造币总公司 | Detecting method for color printing quality |
| CN101256157A (en) * | 2008-03-26 | 2008-09-03 | 广州中国科学院工业技术研究院 | Method and apparatus for testing surface defect |
| CN101561932A (en) * | 2009-05-12 | 2009-10-21 | 北京交通大学 | Method and device for detecting real-time movement target under dynamic and complicated background |
Non-Patent Citations (2)
| Title |
|---|
| 《广东印刷》 20071231 牛一帆 等 图像技术在印刷检测中的应用 54-55 1-4 , 第1期 2 * |
| 《计算机应用》 20071231 王竟爽 等 模糊边缘检测算法在水印模糊检测中的应用 3078-3080 1-4 第27卷, 第12期 2 * |
Cited By (59)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102042812A (en) * | 2010-09-15 | 2011-05-04 | 苏州凌创电子系统有限公司 | Visual machine detection method |
| US9704236B2 (en) | 2011-09-27 | 2017-07-11 | Hewlett-Packard Development Company, L.P. | Detecting printing effects |
| CN102928434A (en) * | 2012-08-23 | 2013-02-13 | 深圳市纳研科技有限公司 | Method and apparatus for array graphic detection |
| CN102841102A (en) * | 2012-09-05 | 2012-12-26 | 同济大学 | Recognition method and device for micro-scale damage point in damage threshold measurement |
| CN103163156A (en) * | 2013-03-21 | 2013-06-19 | 万新光学集团有限公司 | Automatic grading method of lens defects based on machine vision technology |
| CN103439338A (en) * | 2013-08-30 | 2013-12-11 | 无锡金视界科技有限公司 | Classification method for film defects |
| CN103454282A (en) * | 2013-08-30 | 2013-12-18 | 陕西科技大学 | Gray-gradient-based measurement method of mottle of printed product |
| CN103439338B (en) * | 2013-08-30 | 2015-08-12 | 无锡金视界科技有限公司 | Film defects sorting technique |
| CN105066892A (en) * | 2015-08-05 | 2015-11-18 | 哈尔滨工业大学 | BGA element detecting and positioning method based on linear clustering analysis |
| CN105066892B (en) * | 2015-08-05 | 2017-07-28 | 哈尔滨工业大学 | A kind of BGA element testings and localization method based on straight line clustering |
| CN106097371A (en) * | 2016-06-23 | 2016-11-09 | 凌云光技术集团有限责任公司 | A kind of flaw detection method and system |
| CN106442562A (en) * | 2016-08-31 | 2017-02-22 | 上海华力微电子有限公司 | Method for breaking through detection limit of apparent defect drilling crew |
| CN108254385A (en) * | 2016-12-29 | 2018-07-06 | 东莞东聚电子电讯制品有限公司 | Nanoscale automatic optical detecting system |
| CN108254385B (en) * | 2016-12-29 | 2021-04-30 | 东莞东聚电子电讯制品有限公司 | Nanoscale automatic optical detection system |
| CN106940885B (en) * | 2017-01-16 | 2019-10-18 | 北京印钞有限公司 | A kind of online test method of fluorescent ink printing defects |
| CN106940885A (en) * | 2017-01-16 | 2017-07-11 | 北京印钞有限公司 | A kind of online test method of fluorescent ink printing defects |
| CN106855520A (en) * | 2017-02-10 | 2017-06-16 | 南京航空航天大学 | A kind of workpiece, defect detection method based on machine vision |
| CN106898082A (en) * | 2017-03-15 | 2017-06-27 | 深圳怡化电脑股份有限公司 | A kind of image is stained the method and device of judgement |
| CN108939524A (en) * | 2017-07-03 | 2018-12-07 | 孙维军 | A kind of place monitoring management method for ice and snow sports |
| CN107862679A (en) * | 2017-10-20 | 2018-03-30 | 歌尔股份有限公司 | The determination method and device of image detection region |
| CN107862679B (en) * | 2017-10-20 | 2020-12-18 | 歌尔光学科技有限公司 | Method and device for determining image detection area |
| 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 |
| CN109376770A (en) * | 2018-09-26 | 2019-02-22 | 凌云光技术集团有限责任公司 | A kind of net region recognition methods and device applied to egative film check machine |
| CN112789499A (en) * | 2018-10-01 | 2021-05-11 | 世高株式会社 | Teacher data generation device and teacher data generation program |
| CN109507209A (en) * | 2019-01-22 | 2019-03-22 | 中科院金华信息技术有限公司 | A kind of film printing defect detecting system and method |
| CN110632094A (en) * | 2019-07-24 | 2019-12-31 | 北京中科慧眼科技有限公司 | Pattern quality detection method, device and system based on point-by-point comparison analysis |
| CN110632094B (en) * | 2019-07-24 | 2022-04-19 | 北京中科慧眼科技有限公司 | Pattern quality detection method, device and system based on point-by-point comparison analysis |
| CN110717889A (en) * | 2019-09-06 | 2020-01-21 | 深圳新视智科技术有限公司 | Defect detection method and device based on digital printing, terminal and readable medium |
| CN112561849A (en) * | 2019-09-26 | 2021-03-26 | 长鑫存储技术有限公司 | Wafer defect detection method |
| CN110648330A (en) * | 2019-11-28 | 2020-01-03 | 征图新视(江苏)科技股份有限公司 | Defect detection method for camera glass |
| CN111062919B (en) * | 2019-12-12 | 2023-11-03 | 苏州韦士肯检测科技有限公司 | Bearing ring appearance defect detection method |
| CN111062919A (en) * | 2019-12-12 | 2020-04-24 | 韦士肯(厦门)智能科技有限公司 | Bearing ring appearance defect detection method |
| CN111161222A (en) * | 2019-12-13 | 2020-05-15 | 北京印刷学院 | Printing roller defect detection method based on visual saliency |
| CN111161222B (en) * | 2019-12-13 | 2023-08-25 | 北京印刷学院 | Printing roller defect detection method based on visual saliency |
| CN111242896A (en) * | 2019-12-31 | 2020-06-05 | 电子科技大学 | Color printing label defect detection and quality rating method |
| CN111426693A (en) * | 2020-04-26 | 2020-07-17 | 湖南恒岳重钢钢结构工程有限公司 | Quality defect detection system and detection method thereof |
| CN111768348A (en) * | 2020-05-29 | 2020-10-13 | 合肥联宝信息技术有限公司 | Defect detection method, device and computer readable storage medium |
| CN111768348B (en) * | 2020-05-29 | 2022-02-08 | 合肥联宝信息技术有限公司 | Defect detection method, device and computer readable storage medium |
| CN113030093B (en) * | 2020-12-30 | 2022-07-22 | 凌云光技术股份有限公司 | Battery diaphragm surface defect detection method and system |
| CN113030093A (en) * | 2020-12-30 | 2021-06-25 | 凌云光技术股份有限公司 | Battery diaphragm surface defect detection method and system |
| CN113256872B (en) * | 2020-12-31 | 2024-02-02 | 深圳怡化电脑股份有限公司 | Image sensor parameter configuration method, device, computer equipment and storage medium |
| CN113256872A (en) * | 2020-12-31 | 2021-08-13 | 深圳怡化电脑股份有限公司 | Image sensor parameter configuration method and device, computer equipment and storage medium |
| US20220318976A1 (en) * | 2021-03-31 | 2022-10-06 | Canon Kabushiki Kaisha | Apparatus for inspecting defect of printed material, method, and storage medium |
| CN113406110A (en) * | 2021-05-20 | 2021-09-17 | 广州市花都联华包装材料有限公司 | Printing quality detection method, device, equipment and computer medium |
| CN113533372B (en) * | 2021-07-12 | 2024-02-23 | 浙江理工大学 | Paper defect detection method, system, device and computer storage medium |
| CN113533372A (en) * | 2021-07-12 | 2021-10-22 | 浙江理工大学 | Paper defect detection method, system, device and computer storage medium |
| CN114627080B (en) * | 2022-03-16 | 2023-08-25 | 江苏巨杰机电有限公司 | Vehicle stamping accessory defect detection method based on computer vision |
| CN114627080A (en) * | 2022-03-16 | 2022-06-14 | 江苏巨杰机电有限公司 | Vehicle stamping accessory defect detection method based on computer vision |
| CN115018828A (en) * | 2022-08-03 | 2022-09-06 | 深圳市尹泰明电子有限公司 | Defect detection method for electronic component |
| CN115861722A (en) * | 2023-03-02 | 2023-03-28 | 江西服装学院 | Fabric sand washing process abnormity detection method and system |
| CN115861722B (en) * | 2023-03-02 | 2023-07-25 | 江西服装学院 | Fabric sand washing process abnormality detection method and system |
| CN116758071A (en) * | 2023-08-17 | 2023-09-15 | 青岛冠宝林活性炭有限公司 | Intelligent detection method for carbon electrode dirt under visual assistance |
| CN116758071B (en) * | 2023-08-17 | 2023-11-03 | 青岛冠宝林活性炭有限公司 | Intelligent detection method for carbon electrode dirt under visual assistance |
| CN117541588A (en) * | 2024-01-10 | 2024-02-09 | 大连建峰印业有限公司 | Printing defect detection method for paper product |
| CN117541588B (en) * | 2024-01-10 | 2024-03-12 | 大连建峰印业有限公司 | Printing defect detection method for paper product |
| CN117830315A (en) * | 2024-03-05 | 2024-04-05 | 渭南大东印刷包装机械有限公司 | Real-time monitoring method and system for printing machine based on image processing |
| CN117830315B (en) * | 2024-03-05 | 2024-05-10 | 渭南大东印刷包装机械有限公司 | Real-time monitoring method and system for printing machine based on image processing |
| CN118229688A (en) * | 2024-05-27 | 2024-06-21 | 山东幻彩包装有限公司 | Corrugated paper fold defect detection method and system |
| CN118229688B (en) * | 2024-05-27 | 2024-08-06 | 山东幻彩包装有限公司 | Corrugated paper fold defect detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101799434B (en) | 2011-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101799434B (en) | Printing image defect detection method | |
| CN105334219B (en) | A kind of bottle mouth defect detection method of residual analysis dynamic threshold segmentation | |
| CN108776140B (en) | Machine vision-based printed matter flaw detection method and system | |
| CN105913415B (en) | A kind of image sub-pixel edge extracting method with extensive adaptability | |
| CN104680519B (en) | Seven-piece puzzle recognition methods based on profile and color | |
| CN104851085B (en) | The automatic method and system for obtaining detection zone in image | |
| CN102496161B (en) | Method for extracting contour of image of printed circuit board (PCB) | |
| CN103604809B (en) | A kind of online visible detection method of pattern cloth flaw | |
| CN108765402B (en) | Non-woven fabric defect detection and classification method | |
| CN114881915B (en) | Symmetry-based mobile phone glass cover plate window area defect detection method | |
| CN106546263B (en) | A kind of laser leveler shoot laser line detecting method based on machine vision | |
| CN104732536A (en) | Sub-pixel edge detection method based on improved morphology | |
| CN103051872B (en) | Based on the belt deflection detection method of Edge extraction | |
| CN118196068B (en) | Textile printing and dyeing quality monitoring system based on artificial intelligence | |
| CN104992449A (en) | Information identification and surface defect on-line detection method based on machine visual sense | |
| CN104050446A (en) | Meter pointer image identification method based on pointer width character | |
| CN113034488B (en) | Visual inspection method for ink-jet printed matter | |
| CN109886960A (en) | The method of glass edge defects detection based on machine vision | |
| CN117541588A (en) | Printing defect detection method for paper product | |
| CN111539927B (en) | Detection method of automobile plastic assembly fastening buckle missing detection device | |
| CN104331693A (en) | Symmetry detecting method and system of printing matter | |
| CN113221881B (en) | Multi-level smart phone screen defect detection method | |
| CN112132821B (en) | Cotter pin loss detection method based on image processing | |
| CN116030019A (en) | Laser film flaw detection method, device, system and medium | |
| CN103258218A (en) | Matte detection frame generation method and device and defect detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 610041 branch office of No. four section 9 South Renmin Road, Chengdu, Sichuan Patentee after: Shenzhen Zhongchao Kexin Financial Technology Co., Ltd. Patentee after: Chengdu Information Technology of Chinese Academy of Sciences Co., Ltd. Address before: 610041 branch office of No. four section 9 South Renmin Road, Chengdu, Sichuan Patentee before: Shenzhen Zhongchao Kexin Financial Technology Co., Ltd. Patentee before: Chengdu Information Technology Co., Ltd., CAS |
|
| ASS | Succession or assignment of patent right |
Owner name: ZHONGCHAO GREATWALL FINANCIAL EQUIPMENT HOLDING CO Free format text: FORMER OWNER: SHENZHEN ZHONGCHAO KEXIN FINANCIAL TECHNOLOGY CO., LTD. Effective date: 20150430 Owner name: SHENZHEN ZHONGCHAO KEXIN FINANCIAL TECHNOLOGY CO., Free format text: FORMER OWNER: CHENGDU INFORMATION TECHNOLOGY OF CHINESE ACADEMY OF SCIENCES CO., LTD. Effective date: 20150430 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 610041 CHENGDU, SICHUAN PROVINCE TO: 100044 XICHENG, BEIJING |
|
| TR01 | Transfer of patent right |
Effective date of registration: 20150430 Address after: 100044, Beijing, Xicheng District, Desheng street, No. 81, Desheng International Center, block C, 16 Patentee after: Zhongchao Greatwall Financial Equipment Holding Co., Ltd. Patentee after: Shenzhen Zhongchao Kexin Financial Technology Co., Ltd. Address before: 610041 branch office of No. four section 9 South Renmin Road, Chengdu, Sichuan Patentee before: Shenzhen Zhongchao Kexin Financial Technology Co., Ltd. Patentee before: Chengdu Information Technology of Chinese Academy of Sciences Co., Ltd. |