CN102135503A - Method for detecting color overprinting deviation by using image edge information - Google Patents
Method for detecting color overprinting deviation by using image edge information Download PDFInfo
- Publication number
- CN102135503A CN102135503A CN2011100005459A CN201110000545A CN102135503A CN 102135503 A CN102135503 A CN 102135503A CN 2011100005459 A CN2011100005459 A CN 2011100005459A CN 201110000545 A CN201110000545 A CN 201110000545A CN 102135503 A CN102135503 A CN 102135503A
- Authority
- CN
- China
- Prior art keywords
- edge
- image
- symbiosis
- probability matrix
- conditional probability
- 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
Abstract
The invention belongs to the technical field of automatic detection of surface defects of a machine visual object, in particular a method for automatically detecting color overprinting deviation by using image edge information. The method comprises the following steps of: extracting the edge information of a color overprinting image so as to obtain an edge image; in the edge image, calculating to obtain an edge symbiotic condition probability matrix by an edge symbiotic condition probability matrix (ECM) method provided by the invention; and finally, extracting an extreme value point of the edge symbiotic condition probability matrix, wherein if the extreme value point exists on points of which the coordinates are not (0 and 0), the original image has the overprinting deviation and the extreme value is a deviation parameter; and if the coordinate of the extreme value point is (0 and 0), the original image has no overprinting deviation. In the method, a reference image and a color overprinting mark are not needed; by the method, the experiment shows that the overprinting deviation detection of the color overprinting image is precision and effective; and the detection result reaches a pixel level.
Description
Technical field
The invention belongs to the Automatic Measurement Technique field of machine vision body surface flaw, be specifically related to a kind of chromatography deviation of sense colors cover watermark image and the method for estimation of straggling parameter thereof.
Background technology
Process printing is that original copy is carved into the monochromatic forme of polylith respectively according to the component of different color, and then by the look chromatography, finishes the chromatograp [1] that is similar to original work at last.The process printing deviation is a kind of flaw that often occurs in the process printing, is normally caused by the skew of color forme.The necessity of the detection of process printing deviation in the colored printing process is mainly reflected in: at first, if there is the chromatography deviation, the color of printed images is changed, also can make the fuzzy of printed images change; Secondly, the chromatography deviation has very large influence to the value of finished product, has the value of the printed matter of obvious chromatography deviation can reduce 45%-65%[2]; The 3rd, the chromatography deviation all can produce in whole print production process: before batch process, the registration between the color forme may cause the chromatography deviation; In the print production, because the asynchronous chromatography deviation [3] that also can cause of material deformation or color forme; The 4th, in industrial detection, the detection of chromatography deviation normally is independent of other printing Defect Detection, is very significant so study the detection method of chromatography deviation separately.In sum, the detection of process printing deviation and the estimation of migration parameter thereof are indispensable parts in the printing process.
The automatic testing method of process printing deviation mainly contains: 1. the chromatography deviation that detects the cover watermark image by the colored register mark at analysis of material edge.[4] the colored register mark of traditional double exposure has been adopted in [5] [6], and the colored register mark of double exposure commonly used has cross mark, opal mark, circle mark, bar code label etc.Chromatography deviation at the colored register mark of above-mentioned double exposure detects, [4] provide the color separation classification and the marginal information thereof of four kinds of primary colors by graphical analysis, many edge lines in conjunction with least square method and the colored register mark of Hough converter technique match double exposure calculate the offset distance between four kinds of former color characteristic straight lines in image; [5] at first detected image edge and calculating pixel gradient direction, divide the marginal point set according to gradient direction, the least square line iterative fitting is carried out in different directions marginal point set, obtain the linear edge position, and be the side-play amount that benchmark calculates each color with black; [6] method that a kind of color cluster in the HIS color space is cut apart has been proposed.Because said method is the detection that utilizes color of image information, thus light source and imaging system there are harsh requirement, and all be based on the geometric properties of a certain concrete colored register mark of double exposure, do not have general applicability.[7] [8] have adopted the colored register mark of a kind of non-double exposure, utilize the offset of Euclidean distance sense colors register mark to come the chromatography of estimated image to be offset.It is above-mentioned that to utilize the method for the colored register mark of edge of materials all be indirect detection chromatography image deviations, reserve the position of printing color register mark before this not only needs to print in edge of materials, and when being completed for printing the making finished product, also need to carry out cutting work.Simultaneously, in the printing of textile,, detect so can't utilize colored register mark to carry out the chromatography deviation because the textile structural of textile is unsuitable for carrying out cutter's work after weaving is finished.2. utilize the direct detecting method of matching template image.[9] proposed a kind of chromatography deviation detecting method of netrual colour register mark: the image that utilizes no chromatography deviation is as template image, the method that adopts color to cut apart is extracted the color characteristic of template image and image to be detected, both color characteristic is mated draw straggling parameter.3. in addition, the detection system of commercial use and patent are more paid close attention to the design [10] [11] of whole detection system mostly.
Summary of the invention
The object of the present invention is to provide the automatic testing method of the process printing deviation that a kind of applicability is wide, detection accuracy is high.
The automatic testing method of process printing deviation provided by the invention, it is a kind of template image that need not, need not the automatic testing method that utilizes image edge information of colored register mark---edge symbiosis conditional probability matrix (ECM) method is used for sense colors cover watermark image and whether has the estimation of chromatography deviation and straggling parameter.These method concrete steps are as follows:
1, extracts image edge information to be detected, obtain edge image;
2, in the edge image that step 1 obtains, edge symbiosis conditional probability matrix (ECM) method of utilizing the present invention to propose is calculated its offset information;
3, in the edge symbiosis conditional probability matrix that step 2 calculates, at first thresholding is removed image background information; Then in the image of thresholding, adopt 8 to be communicated with operators and to calculate connected regions and extract maximal value in the connected region, this maximal value is the extreme point of edge symbiosis conditional probability matrix.If have extreme point in the testing result, then the extreme value that exists chromatography deviation and detection to obtain in the process printing image is a straggling parameter.If do not have extreme point in the testing result, then no longer chromatography deviation in the process printing image.
Step 1: edge of image detects
At first, utilize gaussian filtering function [12] to carry out the noise processed of image, the noise in the reduction image background is to the interference of testing result.Then, utilize canny edge detection method [13] to extract image edge information.Why adopting the canny edge detection method, is that this method can better detect real weak marginal information, has guaranteed the integrality of image border because with respect to other edge detection methods.
Step 2: edge calculation symbiosis conditional probability matrix
The process printing deviation is the skew between the different formes and the stack of the pigment that causes and covers phenomenon.Characteristics are arranged: have a fixing constant offset between two color look versions of generation translation in the process printing offset images.Based on these characteristics, this paper has proposed the method for edge symbiosis conditional probability matrix ECM, comes the chromatography deviation in the sense colors cover watermark image.
The chromatography offset images
Can be regarded as color forme by its certain translation
The color forme of translation does not take place with other
Merging obtain.Wherein,
Be by its primitive color forme
Translation
Obtain.Shown in following formula:
For the edge symbiosis conditional probability matrix of computed image, this paper has proposed the scanning vector
Notion: wherein, s represents the component of horizontal direction of vector, and t represents the component of the vertical direction of vector.P(only comprises its marginal information at the process printing image) in, its edge symbiosis conditional probability entry of a matrix element
Be by scanning vector
Retouch entire image P, and statistics scanning vector
Starting point and terminal point be positioned at probability on the image border simultaneously.
For certain scanning vector
, utilize following formula to come the edge symbiosis conditional probability entry of a matrix element of computed image (only comprising image edge information)
:
Wherein,
The starting point of expression scanning vector,
The terminal point of expression scanning vector, # are used for calculating the plain number of element of set,
Total number of presentation video edge pixel.
For one group of scanning vector
, wherein
, s, t is integer, and S, T are its maximal value, 0 ,-T is its minimum value.Then can obtain a size is
Edge symbiosis conditional probability matrix ECM.
Step 3: the extreme point that extracts edge symbiosis conditional probability matrix
Extract the extreme point of edge symbiosis conditional probability matrix ECM, and judge whether process printing image P exists the estimation of chromatography deviation and straggling parameter thereof.
At first, in the edge symbiosis conditional probability matrix ECM that calculates, thresholding is removed image background information.Its threshold value is that the standard deviation by edge calculation symbiosis conditional probability matrix ECM obtains, and its concrete account form is as follows:
Wherein,
The mean value of expression edge symbiosis conditional probability matrix.And utilize following formula compute matrix for all elements in the edge symbiosis conditional probability matrix ECM image
:
The matrix that is calculating
In, be zero if element value, then makes the corresponding element value among the edge symbiosis conditional probability matrix ECM less than threshold value, otherwise the corresponding element value of edge symbiosis conditional probability matrix ECM remain unchanged.
In the image of thresholding, judge whether to exist extreme point and calculate extreme value then.Because the part background information of image is by the threshold value cancellation, extreme point and neighborhood thereof can form connected region so, and the maximal value of connected region is exactly an extreme point.Utilize 8 to be communicated with operators [14] and to come connected region in the statistical threshold image, and calculate the maximal value in each connected region, this maximal value is exactly the extreme point of edge symbiosis conditional probability matrix (ECM).Because the element ECM (0 in the edge symbiosis conditional probability matrix, 0) is element in the edge image and the symbiosis of himself statistics, so any cover watermark image in its edge symbiosis conditional probability matrix (0,0) all can produce an extreme point, the extreme point that need when calculating the chromatography deviation, ignore (0,0) some place.Therefore, if there is the extreme point at non-(0,0) some place in the testing result, then exist chromatography deviation and extreme value to be its straggling parameter in the process printing image.If do not have the extreme point of non-(0,0) point in the testing result, then do not have the chromatography deviation in the process printing image.
The present invention need not with reference to image, need not colored register mark.Experiment shows that the present invention is that accurately, effectively testing result can be as accurate as Pixel-level to the chromatography deviation detection of process printing image.
Description of drawings
Fig. 1 is colored register mark commonly used in the colored printing.Wherein, (a) being the opal mark, (b) is the cross mark, (c) is the non-overlapped colored register mark that separates.
Fig. 2 is illustrated in the process printing of adopting four-color process (CMYK), the formation mechanism of process printing offset images.Wherein, (a) situation of process printing deviation does not take place in expression, after (b) translation has taken place expression cyan forme, with the chromatography offset images that forms after the overlapping chromatography of other formes.
Fig. 3 a represents to scan the computing method that vector scanning on the cover watermark image generates edge symbiosis conditional probability matrix element.Fig. 3 b is the plain distribution mode of edge symbiosis conditional probability entry of a matrix.
Fig. 4 is for detecting each stage result of chromatography image deviations parameter.Wherein, (a) be chromatography offset images to be detected; (b) be the edge image of chromatography offset images; (c) be the edge symbiosis conditional probability matrix ECM of edge image; (d) be three latitude grid histograms of edge symbiosis conditional probability matrix; (e) be three latitude grid histograms of the edge symbiosis conditional probability matrix peak point of extraction.
Fig. 5 is the detection method process flow diagram of process printing offset images.
Fig. 6 is an experimental result.Wherein, (a) and (b) are the colored analog images that have the chromatography deviation, and (e), (f) be its corresponding detection result, its off-set value that calculates equates with the known offset value.(c) be the coloured image that does not have the chromatography deviation, (g) be its testing result: do not have peak point, illustrate that there is not the chromatography deviation in former figure.(d) for there being the true picture of process printing deviation, (h) be its testing result.
Embodiment
The specific algorithm of this invention is as follows:
Edge symbiosis conditional probability matrix algorithms (ECM)
Input:Image P, S, T, weight %S, T represent to scan the maximal value of vector, and its minimum value is 0 accordingly ,-T
The weight of %weight edge symbiosis conditional probability matrix thresholding
% P is the process printing image to be detected of input
1. extraction edge image: imageedge=canny (P);
2. edge calculation symbiosis conditional probability matrix ECM
[a,b]=size(imageedge);
for?s=0:S;?t=?-T:T
for?i=1:a;?j=1:b
if?imageedge(i,j)==1&&imageedge(i+s,j+t)==1
ECM(s,t)=ECM(s,t)+1;
end
end
end
3. remove the background noise of edge symbiosis conditional probability matrix ECM and extract the value of peak point
for?s=0:S;?t=?-T:T
if?devECM(s,t)<threshold
ECM(s,t)=0;
end
end
connectedregion=find_connecedregion?(ECM);
[Δx,?Δy]=max(connectiveregion);
Output:The 3D grid histogram of migration parameter [Δ x, Δ y] and peak point.
The process printing offset images is owing to form with the overlapping chromatography of the color forme that translation does not take place after certain or certain several color forme translation, so in the image that has the chromatography deviation, can have a translation constant on the corresponding edge.The present invention at first extracts the process printing image edge information, obtains edge image; In the edge image that obtains, calculate its edge symbiosis conditional probability matrix ECM then; Extract the extreme point in the edge symbiosis conditional probability matrix at last.If there is extreme value, having chromatography deviation and extreme value among the then former figure is the chromatography straggling parameter; If there is not extreme value, there is not the chromatography deviation among the then former figure.Its embodiment:
1. utilize the canny edge detection method to extract image edge information to be detected, obtain its edge image;
2. in the edge image that obtains, use the method for the edge symbiosis conditional probability matrix (ECM) that proposes among the present invention and calculate migration parameter.Use one group of scanning vector
Scanning colour chromatography offset images can obtain the edge symbiosis conditional probability matrix of a size for (S+1) * (2*T+1); Wherein:
Wherein,
The starting point of expression scanning vector,
The terminal point of expression scanning vector, # are used for the size of set of computations,
Total number of presentation video edge pixel;
3. extract the extreme point of edge symbiosis conditional probability matrix, and judge the estimation that whether has chromatography deviation and straggling parameter thereof among the former figure.At first, in the edge symbiosis conditional probability matrix diagram that calculates, thresholding is removed image background information.Its threshold value is that the standard deviation by edge calculation symbiosis conditional probability matrix obtains, and its concrete account form is as follows:
Wherein,
The mean value of expression edge symbiosis conditional probability matrix.And utilize following formula compute matrix for all elements among the edge symbiosis conditional probability matrix ECM
:
。
The matrix that is calculating
In, be zero if element value, then makes the corresponding element value among the edge symbiosis conditional probability matrix ECM less than threshold value, otherwise the corresponding element value of edge symbiosis conditional probability matrix ECM remain unchanged.
Then, in the image of thresholding, judge whether to exist extreme point and calculate extreme value.Because the background information of image is by the threshold value cancellation, extreme point and neighborhood thereof can form connected region so, and the maximal value of connected region is exactly an extreme point.Utilize 8 to be communicated with operators and to come connected region in the statistical threshold image, and calculate the maximal value in each connected region, this maximal value is exactly the extreme point of edge symbiosis conditional probability matrix (ECM).Because the element ECM (0 in the edge symbiosis conditional probability matrix, 0) is element in the edge image and the symbiosis of himself statistics, so any cover watermark image in its edge symbiosis conditional probability matrix (0,0) all can produce an extreme point, the extreme point that need when calculating the chromatography deviation, ignore (0,0) some place.Therefore, if there is the extreme point at non-(0,0) some place in the testing result, then exist chromatography deviation and extreme value to be its straggling parameter in the process printing image.If do not have the extreme point of non-(0,0) point in the testing result, then do not have the chromatography deviation in the process printing image.
List of references
[1] Qkshun, xhffeng. chromatography [E]. http://baike.baidu.com/view/188922.htm, 2010,12.
[2]?K.?Sriniva?san.?FDAS:?A?knowledge-based?frame?detection?work?for?analysis?of?defects?in?woven?textile?structures.?J.?Text.Inst.,?1992,?vol.83,?no.3:?431-447.
[3] Lv Zhigang, Cao Yuejin, Liu Chongxuan. the realization [J] of novel circular screen printer registration precision detection system. Jiangsu weaving, 2003, (7): 50-52.
[4]?Liu?linghui,?WangYue-zong.Study?on?color?division?model?about?register?calculation.?Computer?Engineering?andApplications,?2009,?45(19):?210-212．
[5]?YuLi_jie,?Li?De-sheng,?WangYue-zong. Application?of?image?processing?in?detection?of?overprint?deviation?in?color?printing.?Computer?Engineering?and?Applications,?2010,?46(11):?190-192．
[6]?ZengXinxin,?Li?Desheng,?Wang?Yuezong.?A?new?color?image?segment?method?for?register?detection.?Micro-computer?Imformation,?2008.24.
[7]?LiuHaoxue,?YangWenjie,?HUANG?Min,?et?al.?Detection?and?Control?Algorithm?of?Multi-?color?Printing?Registration?Based?on?Computer?Vision.?Proceedings?of?the?2nd?International?Congress?on?Image?and?Signal?Processing?(CISP'09),?Washington,?USA:?IEEE?Computer?Society,?2009:?2364-236.
[8]?Gao?Juan,?DuanZhong-xin.?Overprint?error?detection?algorithm?based?on?mathematical?morphology.?Journal?of?Computer?Applications,2010.
[9]?Gao,?J.?and?Lu,?B.?Research?on?an?Overprinting?Accuracy?Analysis?Algorithm?without?Color?Marks?of?Multi-color?Printings.?International?Conference?on?Computational?Intelligence?and?Security?Workshops,2007:?914-917.
[10]?De?Jong,?J.N.M.?and?Castelli,?V.R.?et?al.?Method?and?apparatus?for?correction?of?color?registration?errors.?US?Patent?5,287,162.?1994.
[11]?Iwata,?N.,?Sato,?T.?and?Shinohara,?T.?et?al.?Image?forming?apparatus?eliminating?influence?of?fluctuation?in?speed?of?a?conveying?belt?to?correction?of?offset?in?color?registration.US?Patent?5,875,380.?1999.
[12]?I.?T.?Young?and?L.?J.?Van?Vliet.?Recursive?implementation?of?the?Gaussian?filters.?Signal?Process,1995,?vol.44:?139-151.
[13]?J.?Canny.?A?computational?approach?to?edge?detection.?IEEETrans.?Pattern?Anal.?Machine?Intell.,1986,vol.8:?679-698.
[14]?Rafael?C.Gonzalez,?Richard?E.?Woods.?Digital?Image?Processing?Second?Edition.?Beijing:?Publishing?House?of?Electronics?Industry,?2003:?435-437。
Claims (1)
1. automatic testing method that utilizes the process printing deviation of image edge information is characterized in that may further comprise the steps:
(1) extracts image edge information to be detected, obtain edge image;
(2) in the edge image that step 1 obtains, utilize edge symbiosis conditional probability matrix method (ECM), calculate its offset information, computing formula is as follows:
Wherein,
The starting point of expression scanning vector,
The terminal point of expression scanning vector, # are used for the size of set of computations,
Total number of presentation video edge pixel;
(3) extract the extreme point of edge symbiosis conditional probability matrix (ECM), and judge whether original color cover watermark image exists the estimation of chromatography deviation and straggling parameter thereof:
At first, in the edge symbiosis conditional probability matrix (ECM) that step 2 calculates, thresholding is removed image background information; Its threshold value is the standard deviation acquisition by edge calculation symbiosis conditional probability matrix, and its concrete account form is as follows:
Utilize following formula to calculate the devECM matrix for all elements in the edge symbiosis conditional probability matrix (ECM):
S, t is integer, S, T is its maximal value, 0 ,-T is its minimum value;
The matrix that is calculating
In, be zero if element value, then makes the corresponding element in the edge symbiosis conditional probability matrix (ECM) less than threshold value, otherwise the element value of edge symbiosis conditional probability matrix (ECM) remain unchanged;
Then, in the image behind thresholding, adopt 8 to be communicated with operators and to calculate connected regions and put forward maximal value in the connected region, this maximal value is the extreme point of edge symbiosis conditional probability matrix (ECM); If there is the extreme point of non-(0,0) point in the testing result, then exist chromatography deviation and extreme value to be its straggling parameter in the process printing image; If do not have the extreme point of non-(0,0) point in the testing result, then do not have the chromatography deviation in the process printing image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110000545.9A CN102135503B (en) | 2011-01-04 | 2011-01-04 | Method for detecting color overprinting deviation by using image edge information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110000545.9A CN102135503B (en) | 2011-01-04 | 2011-01-04 | Method for detecting color overprinting deviation by using image edge information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102135503A true CN102135503A (en) | 2011-07-27 |
| CN102135503B CN102135503B (en) | 2014-04-02 |
Family
ID=44295350
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110000545.9A Expired - Fee Related CN102135503B (en) | 2011-01-04 | 2011-01-04 | Method for detecting color overprinting deviation by using image edge information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102135503B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105882129A (en) * | 2016-06-03 | 2016-08-24 | 杭州宏华数码科技股份有限公司 | Printing mechanism achieving synchronous digital printing and rotary screen printing and printing method |
| CN109934836A (en) * | 2017-12-15 | 2019-06-25 | 中国科学院深圳先进技术研究院 | A kind of detection method of image sharpening |
| CN110696481A (en) * | 2019-10-28 | 2020-01-17 | 吴克生 | Automatic plate aligning method of printing machine |
| CN113793354A (en) * | 2021-08-20 | 2021-12-14 | 航天晨光股份有限公司 | Self-adaptive straight line detection method based on Hough transform |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3525872A (en) * | 1967-11-03 | 1970-08-25 | Calmec Extruform Ltd | Radiation sensitive control means for a moving sheet having registration marks |
| US5440650A (en) * | 1991-01-08 | 1995-08-08 | Nippondenso Co., Ltd. | Image processing system for inspection of overprinted matter |
| CN101007458A (en) * | 2007-02-01 | 2007-08-01 | 洛阳圣瑞机电技术有限公司 | Printing registration test method |
-
2011
- 2011-01-04 CN CN201110000545.9A patent/CN102135503B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3525872A (en) * | 1967-11-03 | 1970-08-25 | Calmec Extruform Ltd | Radiation sensitive control means for a moving sheet having registration marks |
| US5440650A (en) * | 1991-01-08 | 1995-08-08 | Nippondenso Co., Ltd. | Image processing system for inspection of overprinted matter |
| CN101007458A (en) * | 2007-02-01 | 2007-08-01 | 洛阳圣瑞机电技术有限公司 | Printing registration test method |
Non-Patent Citations (2)
| Title |
|---|
| 于丽杰等: "彩色套印偏差检测中的图像处理技术研究", 《计算机工程与研究》 * |
| 王雪琳等: "基于ECM 的彩色套印偏差检测算法", 《计算机工程》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105882129A (en) * | 2016-06-03 | 2016-08-24 | 杭州宏华数码科技股份有限公司 | Printing mechanism achieving synchronous digital printing and rotary screen printing and printing method |
| CN105882129B (en) * | 2016-06-03 | 2019-02-19 | 杭州宏华数码科技股份有限公司 | A kind of printing machine frame and printing method that digit printing is synchronous with rotary scream printing |
| CN109934836A (en) * | 2017-12-15 | 2019-06-25 | 中国科学院深圳先进技术研究院 | A kind of detection method of image sharpening |
| CN110696481A (en) * | 2019-10-28 | 2020-01-17 | 吴克生 | Automatic plate aligning method of printing machine |
| CN113793354A (en) * | 2021-08-20 | 2021-12-14 | 航天晨光股份有限公司 | Self-adaptive straight line detection method based on Hough transform |
| CN113793354B (en) * | 2021-08-20 | 2023-08-15 | 航天晨光股份有限公司 | Self-adaptive straight line detection method based on Hough transform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102135503B (en) | 2014-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5903966B2 (en) | Image inspection apparatus, image forming apparatus, and control method for image inspection apparatus | |
| US9310737B2 (en) | Image inspection of printed matter with a master image | |
| CN111080582B (en) | Method for detecting defects of inner and outer surfaces of workpiece | |
| CN108776140A (en) | A kind of printed matter flaw detection method and system based on machine vision | |
| CN107389693B (en) | Automatic detection method for defects of printed matter based on machine vision | |
| CN111242896A (en) | Color printing label defect detection and quality rating method | |
| CN107014819A (en) | A kind of solar panel surface defects detection system and method | |
| JP5172643B2 (en) | Printed matter contamination degree determination apparatus and printed matter contamination degree determination method | |
| CN111062934B (en) | Fabric image defect real-time detection method | |
| CN104462380A (en) | Trademark retrieval method | |
| CN102135503B (en) | Method for detecting color overprinting deviation by using image edge information | |
| CN111126391B (en) | Printed character defect positioning method | |
| CN104778710A (en) | Morphological image edge detecting method based on quantum theory | |
| CN101246593A (en) | Color image edge detection method and apparatus | |
| CN113034488A (en) | Visual detection method of ink-jet printed matter | |
| CN106327464A (en) | Edge detection method | |
| CN111095907B (en) | Adjusting colors in an image | |
| CN102980659A (en) | Digitalized characterization method of monochrome tight fabric surface color | |
| Ma et al. | The defect detection of personalized print based on template matching | |
| JP2020087473A (en) | High-speed image distortion correction for image inspection | |
| Gong et al. | Adaptive visual inspection method for transparent label defect detection of curved glass bottle | |
| CN110501339B (en) | Cloth cover positioning method in complex environment | |
| JP2021158583A (en) | Image processing apparatus, image processing method, and program | |
| Ouji et al. | Chromatic/achromatic separation in noisy document images | |
| US11135833B2 (en) | Method for verifying a printing plate, specifically a gravure cylinder |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20140402 Termination date: 20170104 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |