CN106093055A - Individual film quality determining method a kind of and plural number Zhang Feilin quality determining method - Google Patents

Individual film quality determining method a kind of and plural number Zhang Feilin quality determining method Download PDF

Info

Publication number
CN106093055A
CN106093055A CN201610701260.0A CN201610701260A CN106093055A CN 106093055 A CN106093055 A CN 106093055A CN 201610701260 A CN201610701260 A CN 201610701260A CN 106093055 A CN106093055 A CN 106093055A
Authority
CN
China
Prior art keywords
film
image
determining method
plural number
quality determining
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
Application number
CN201610701260.0A
Other languages
Chinese (zh)
Other versions
CN106093055B (en
Inventor
黄旭东
宁沪鑫
王玮
林宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fuzhou Dragonfly Vision Software Technology Co Ltd
Original Assignee
Fuzhou Dragonfly Vision Software Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Fuzhou Dragonfly Vision Software Technology Co Ltd filed Critical Fuzhou Dragonfly Vision Software Technology Co Ltd
Priority to CN201610701260.0A priority Critical patent/CN106093055B/en
Publication of CN106093055A publication Critical patent/CN106093055A/en
Application granted granted Critical
Publication of CN106093055B publication Critical patent/CN106093055B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/8851Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
    • G01N2021/8887Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Image Processing (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The present invention provides individual film quality determining method a kind of, and by scanner scanning, the film is obtained a film image;This film image is rectified a deviation, and aligns with standard drawing;Standard drawing is converted into gray-scale map;The gray-scale map of this film image with standard drawing is contrasted, obtains quality measurements;The present invention also provides for a kind of plural number Zhang Feilin quality determining method;The defect on the film can be detected accurately, it is ensured that the quality of leaflet, improve production efficiency and reduce cost.

Description

Individual film quality determining method a kind of and plural number Zhang Feilin quality determining method
Technical field
The present invention relates to individual film quality determining method a kind of and plural number Zhang Feilin quality determining method.
Background technology
The film refers to the egative film in plate making, is the template manufacturing printed panel.If there is mistake in the printed patterns of the film, The high-volume print product produced for template with this film then can be caused to scrap;Therefore, on the film, the accuracy of printed patterns is straight Connect and affect printed panel workmanship, and the quality of follow-up sheet material print product.Traditional film detection mode be manually by The amplifying devices such as magnifier subregion each to the film is detected one by one, this not only detection efficiency low, and accuracy of identification is relatively low Easily occur that detection fatigue may result in a lot of missing inspections with artificial.Occurred that one was examined by collected by camera film comparison in recent years Survey mode, but emphasis embodies collected by camera mode, the most specifically embodies detection method, so have cannot to word, The whole structure of symbol, image detail and the synthesis of multiple films carries out the defects such as detection;And this collected by camera mode is deposited Needing multi collect to piece together complete film image at the large format film, the most not only picking rate is slow, and to detected phenanthrene Woods placement location, angle have strict requirements.
Summary of the invention
The technical problem to be solved in the present invention, is to provide individual film quality determining method a kind of and plural number Zhang Feilin matter Quantity measuring method, it is possible to detect the defect on the film accurately, it is ensured that the quality of leaflet, improves production efficiency and reduces into This.
One of present invention is achieved in that individual film quality determining method a kind of, comprises the steps:
Step 1, the film is obtained a film image by scanner scanning;
Step 2, this film image is rectified a deviation, and align with standard drawing;
Step 3, standard drawing is converted into gray-scale map;
Step 4, the gray-scale map of this film image with standard drawing is contrasted, obtain quality measurements.
Further, first described step 4 further particularly as follows: draw choosing to need inspection on the gray-scale map of standard drawing ROI, the ROI according to drawing choosing mate location on film image;The Pictures location that will match to selects with the gray scale picture of standard drawing Region carries out image comparison and obtains quality measurements.
Further, described quality measurements includes defect image, defect image area and defect image position.
Further, also include step 5, quality measurements is shown in interface.
Further, described film image is gray-scale map.
The two of the present invention are achieved in that a kind of plural number Zhang Feilin quality determining method, comprise the steps:
Step 1, by plural number Zhang Feilin respectively by scanner scanning, obtain plural number Zhang Feilin image;
Step 2, described plural number Zhang Feilin image is rectified a deviation, and align with standard drawing;
Step 3, according on standard drawing extract color plural number Zhang Feilin image is mixed colours respectively as film toning figure;
Step 4, plural number Zhang Feilin toning figure is overlapped synthesizing a film synthesis original text;
Step 5, by this film synthesis original text contrast with standard drawing, obtain quality measurements.
Further, first described step 5 further particularly as follows: draw the ROI that choosing needs to check, according to picture on standard drawing The ROI of choosing is coupling location on film synthesis original text;The Pictures location that will match to and standard picture favored area carry out image comparison Obtain quality measurements.
Further, described quality measurements includes defect image, defect image area and defect image position.
Further, also include step 6, quality measurements is shown in interface.
Further, described film image is gray-scale map.
Present invention have the advantage that the present invention individual film quality determining method a kind of and plural number Zhang Feilin quality testing Method, it is possible to achieve all types of films detect, and on support the market, the input of film scanogram the comparison of various scanneies are examined Survey.It is simple that this method has testing process, powerful, the feature that detection efficiency is high, loss is low.
Accompanying drawing explanation
The present invention is further illustrated the most in conjunction with the embodiments.
Fig. 1 is that individual film quality determining method of the present invention performs flow chart.
Fig. 2 is the execution flow chart of the present invention a kind of plural number Zhang Feilin quality determining method.
Fig. 3 is the flow chart of a kind of detailed description of the invention of the present invention.
Detailed description of the invention
As it is shown in figure 1, individual film quality determining method of the present invention, comprise the steps:
Step 1, by scanner scanning, the film being obtained a film image, described film image is gray-scale map;
Step 2, this film image is rectified a deviation, and align with standard drawing;
Step 3, standard drawing is converted into gray-scale map;
Step 4, the ROI that first picture choosing needs check on the gray-scale map of standard drawing, according to drawing the ROI selected at film image Upper coupling location;The gray scale picture favored area of the Pictures location that will match to and standard drawing carries out image comparison and obtains quality testing As a result, described quality measurements includes defect image, defect image area and defect image position.
Step 5, quality measurements is shown in interface.
As in figure 2 it is shown, plural number Zhang Feilin quality determining method of the present invention, comprise the steps:
Step 1, by plural number Zhang Feilin respectively by scanner scanning, obtain plural number Zhang Feilin image;
Step 2, described plural number Zhang Feilin image is rectified a deviation, and align with standard drawing;
Step 3, according on standard drawing extract color plural number Zhang Feilin image is mixed colours respectively as film toning figure;
Step 4, plural number Zhang Feilin toning figure is overlapped synthesizing a film synthesis original text;
Step 5, the ROI that first picture choosing needs check on standard drawing, according to drawing the ROI selected coupling on film synthesis original text Location;The Pictures location that will match to and standard picture favored area carry out image comparison and obtain quality measurements, described quality Testing result includes defect image, defect image area and defect image position.
Step 6, quality measurements is shown in interface.
As in figure 2 it is shown, one detailed description of the invention of the present invention:
The present invention realizes mainly including two parts, and one is film image acquisition, and two is film comparison.
Film image acquisition of the present invention illustrates: by scanner, the film is scanned into image, the most again by image transmitting the most also Carry out detection process.Various scanneies on common market of the present invention, can by scanner once to the film of different breadths Scanning imagery, the film especially for large format can also pass through large scale scanner single pass imaging.This single pass The image acquisition mode of imaging, not only efficiency is high, and film placement location and angle is not had particular requirement, as long as completing The film of complete breadth detects image scanning, and the later stage can realize image is carried out automatic deviation correction.
Film comparison of the present invention illustrates: the present invention includes the synthesis original text comparison of individual film contribution, multiple films and quality inspection Survey.Individual film original text comparison: obtaining film monochrome original text by scanning individual film original text, the scanogram first come in transmission enters Row automatic deviation correction, by drawing selected bit patterns so that detection film original text and standard film original text are automatically positioned alignment, then standard Figure extracts film monochrome original text corresponding pattern, finally extracts pattern and compare with film detection original text.Film synthesis original text comparison: logical The film, by multiple film monochrome original texts synthesis film synthesis original text, is synthesized original text and carries out with standard drawing by overscanning, toning, superposition the most again Comparison, comparison flow process is similar with individual film comparison.
Film comparison of the present invention can realize the film detection original text on word, numeral, the Determination function such as symbol, image, Film detection original text bar code and the detection function of Quick Response Code can also be realized.It is also possible to testing result is generated report Table, it is achieved record and management and control function.
As it is shown on figure 3, the film of the present invention detection invention working mechanism as follows: first pass through scanner and the film be scanned into figure Picture, then by film scanned picture being carried out image alignment, image toning, image overlay, picture detects, defect shows etc. one Image series processes and reaches film defects detection demand.Image alignment: make by searching the registration pattern on the film and standard drawing Detected film scanning figure is reached and standard drawing alignment effect by geometric transformation operation.Allow film place exist angle and The deviation of position, by algorithm automatic aligning, owing to alignment thereof is that view picture graphic operation does not exist picture Bonding Problem, so figure As alignment effect is good, error is little.Image is mixed colours: extract individual film scanning figure corresponding color from standard drawing, according to detected Film scanogram is calculated the operation that completes to mix colours of the color value of corresponding replacement and obtains film toning figure.Image overlay: will be many Zhang Feilin toning figure is overlapped operation.Film picture detects: first drawing choosing on standard drawing needs the ROI, ROI that check permissible Picture selects whole breadth or draws simultaneously and select regional area, draws and selects ROI to provide the detection types such as detection defect, bar code, Quick Response Code.According to Draw ROI coupling location on film synthesis original text of choosing;The Pictures location that will match to carries out image ratio with standard picture favored area To obtaining defect picture, bar code content, Quick Response Code content.Detection algorithm filters picture noise and error, comparison real defect, lacks Falling into figure content is standard drawing and two values expressions of inconsistent part in detection figure, provides enhanced setup feature simultaneously, can be by Complicated image needs the contents extraction detected go out individually to compare, compare the most accurate;Defect picture is carried out image divide Analysis obtains the parameters such as defective locations, area and numbering;Comparison and analysis result are shown in interface, defect label Circle is selected line label of going forward side by side and is generated form simultaneously;Can be simpler by the way of film composite diagram and defect map Overlapping display Singly check the situation of defect.There is provided number of drawbacks display packing: the modes such as simultaneously operating, mouse following, alternately display are entered simultaneously Row defect shows, can highlight defect, thus reduce the lookup of human eye.Display function is by standard drawing, film composite diagram (individual Film scanning figure), testing result figure three figure shows.Simultaneously operating provides three width figures according to checking that needs synchronize scaling, put down Shifting function.Mouse following provides standard drawing, film composite diagram (individual film scanning figure) to follow mouse phase in testing result figure Position is zoomed in and out translation.Alternately display provides and alternately shows three width figures on same interface.Eurypalynous check mode How make defect check the simplest, reduce people eyestrain.
Coupling location can have in the location mode used: template matching, Feature Points Matching, geometric match, Generalized Hough Join;
Graphical analysis can by by the way of have: image split, rim detection, image filtering, particle analysis etc..
The present invention uses following several algorithm:
1. location alignment algorithm
1.1 location: chosen the characteristics of image of registration pattern by analysis, limit in the range of calculate registration pattern feature with The associated similarity of detection image is (unrelated with position, angle, scaling;I.e. similarity algorithm), obtain finally giving similarity and divide Number, arranges score threshold, determines position location;
1.2 alignment: according to the respective coordinates group navigated to, be calculated transformation parameter, according to transformation parameter, image entered Row alignment operation;
2. image alignment algorithm
2.1 levy according to the CF top grade of image and to carry out image comparison and obtain image difference value, set threshold value, determine Image is the most defective in this position;
3. image analysis algorithm
In 3.1 analyzing defect images, the feature such as the shape of defect, position, obtains position and the partial geometry parameter of defect, Obtain defect label and defective labels frame;
4. bar code, Quick Response Code, aberration have canonical algorithm to be identified or calculate and be not described here.
The present invention can be unrelated to tiny error, image acquisition introducing error etc. by controlling detection parameter and display packing Or negligible error ignores, detected emphasis word, symbol, image equal error are highlighted, thus reach to simplify inspection Survey operation, improve accuracy of detection.The defect on the film can be detected accurately, it is ensured that the quality of leaflet, improve and produce effect Rate and reduction cost.
Although the foregoing describing the detailed description of the invention of the present invention, but those familiar with the art should managing Solving, our described specific embodiment is merely exemplary rather than for the restriction to the scope of the present invention, is familiar with this The technical staff in field, in the equivalent modification made according to the spirit of the present invention and change, should be contained the present invention's In scope of the claimed protection.

Claims (10)

1. individual film quality determining method, it is characterised in that: comprise the steps:
Step 1, the film is obtained a film image by scanner scanning;
Step 2, this film image is rectified a deviation, and align with standard drawing;
Step 3, standard drawing is converted into gray-scale map;
Step 4, the gray-scale map of this film image with standard drawing is contrasted, obtain quality measurements.
Individual film quality determining method of one the most according to claim 1, it is characterised in that: described step 4 is further Particularly as follows: first draw the ROI that choosing needs to check on the gray-scale map of standard drawing, the ROI according to drawing choosing mates on film image Location;The gray scale picture favored area of the Pictures location that will match to and standard drawing carries out image comparison and obtains quality measurements.
3. individual film quality determining method a kind of as claimed in claim 1 or 2, it is characterised in that: described quality testing is tied Fruit includes defect image, defect image area and defect image position.
4. individual film quality determining method a kind of as claimed in claim 1, it is characterised in that: also include step 5, by quality Testing result is shown in interface.
5. individual film quality determining method a kind of as claimed in claim 1, it is characterised in that: described film image is gray scale Figure.
6. a plural Zhang Feilin quality determining method, it is characterised in that: comprise the steps:
Step 1, by plural number Zhang Feilin respectively by scanner scanning, obtain plural number Zhang Feilin image;
Step 2, described plural number Zhang Feilin image is rectified a deviation, and align with standard drawing;
Step 3, according on standard drawing extract color plural number Zhang Feilin image is mixed colours respectively as film toning figure;
Step 4, plural number Zhang Feilin toning figure is overlapped synthesizing a film synthesis original text;
Step 5, by this film synthesis original text contrast with standard drawing, obtain quality measurements.
A kind of plural number Zhang Feilin quality determining method the most according to claim 6, it is characterised in that: described step 5 enters one First step particularly as follows: draw the ROI that choosing needs to check on standard drawing, according to the ROI coupling location on film synthesis original text drawing choosing; The Pictures location that will match to and standard picture favored area carry out image comparison and obtain quality measurements.
A kind of plural number Zhang Feilin quality determining method the most as claimed in claims 6 or 7, it is characterised in that: described quality testing Result includes defect image, defect image area and defect image position.
9. a kind of plural number Zhang Feilin quality determining method as claimed in claim 6, it is characterised in that: also include step 6, by matter Amount testing result is shown in interface.
10. a kind of plural number Zhang Feilin quality determining method as claimed in claim 6, it is characterised in that: described film image is Gray-scale map.
CN201610701260.0A 2016-08-22 2016-08-22 Quality detection method for plural films Active CN106093055B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610701260.0A CN106093055B (en) 2016-08-22 2016-08-22 Quality detection method for plural films

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610701260.0A CN106093055B (en) 2016-08-22 2016-08-22 Quality detection method for plural films

Publications (2)

Publication Number Publication Date
CN106093055A true CN106093055A (en) 2016-11-09
CN106093055B CN106093055B (en) 2020-04-24

Family

ID=57224625

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610701260.0A Active CN106093055B (en) 2016-08-22 2016-08-22 Quality detection method for plural films

Country Status (1)

Country Link
CN (1) CN106093055B (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106931893A (en) * 2017-03-10 2017-07-07 黄攸平 The method that grating thin slice pitch is accurately measured based on refraction principle
CN107014818A (en) * 2017-02-28 2017-08-04 深圳市维图视技术有限公司 A kind of laser carving defective vision detecting system and method
CN107515348A (en) * 2017-08-14 2017-12-26 奥士康科技股份有限公司 A kind of method for preventing film data from opening short circuit
CN109840499A (en) * 2019-01-31 2019-06-04 闽江学院 A kind of method of quick detection printed matter printing and bookbinding quality
CN114324405A (en) * 2021-12-29 2022-04-12 安徽中科锟铻量子工业互联网有限公司 Data labeling system based on film detection

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1396446A (en) * 2001-07-12 2003-02-12 虹光精密工业股份有限公司 Method for scanner to detect defect on transmission-type negative film
CN102156136A (en) * 2011-03-14 2011-08-17 浙江展邦电子科技有限公司 Method for detecting PCB negative film
CN102416758A (en) * 2011-08-18 2012-04-18 深圳华智包装制品有限公司 Paper package box quick proofing method
CN103364402A (en) * 2012-04-05 2013-10-23 川宝科技股份有限公司 System and method for judging assembling error of printed circuit board substrate
CN104330419A (en) * 2014-11-20 2015-02-04 北京凌云光技术有限责任公司 Method and device for detecting film
CN105718271A (en) * 2016-02-15 2016-06-29 福州觉感视觉软件科技有限公司 Machine vision intelligent detection system
KR20160095381A (en) * 2015-02-03 2016-08-11 성우테크론 주식회사 method for optical inspection of transparent electrode film

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1396446A (en) * 2001-07-12 2003-02-12 虹光精密工业股份有限公司 Method for scanner to detect defect on transmission-type negative film
CN102156136A (en) * 2011-03-14 2011-08-17 浙江展邦电子科技有限公司 Method for detecting PCB negative film
CN102416758A (en) * 2011-08-18 2012-04-18 深圳华智包装制品有限公司 Paper package box quick proofing method
CN103364402A (en) * 2012-04-05 2013-10-23 川宝科技股份有限公司 System and method for judging assembling error of printed circuit board substrate
CN104330419A (en) * 2014-11-20 2015-02-04 北京凌云光技术有限责任公司 Method and device for detecting film
KR20160095381A (en) * 2015-02-03 2016-08-11 성우테크론 주식회사 method for optical inspection of transparent electrode film
CN105718271A (en) * 2016-02-15 2016-06-29 福州觉感视觉软件科技有限公司 Machine vision intelligent detection system

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107014818A (en) * 2017-02-28 2017-08-04 深圳市维图视技术有限公司 A kind of laser carving defective vision detecting system and method
CN107014818B (en) * 2017-02-28 2020-08-04 深圳市维图视技术有限公司 Laser etching defect visual detection system and method
CN106931893A (en) * 2017-03-10 2017-07-07 黄攸平 The method that grating thin slice pitch is accurately measured based on refraction principle
CN107515348A (en) * 2017-08-14 2017-12-26 奥士康科技股份有限公司 A kind of method for preventing film data from opening short circuit
CN107515348B (en) * 2017-08-14 2020-05-22 奥士康科技股份有限公司 Method for preventing film data from open short circuit
CN109840499A (en) * 2019-01-31 2019-06-04 闽江学院 A kind of method of quick detection printed matter printing and bookbinding quality
CN114324405A (en) * 2021-12-29 2022-04-12 安徽中科锟铻量子工业互联网有限公司 Data labeling system based on film detection
CN114324405B (en) * 2021-12-29 2022-11-08 安徽中科锟铻量子工业互联网有限公司 Data labeling system based on film detection

Also Published As

Publication number Publication date
CN106093055B (en) 2020-04-24

Similar Documents

Publication Publication Date Title
CN106093055A (en) Individual film quality determining method a kind of and plural number Zhang Feilin quality determining method
JP5861462B2 (en) Inspection standard registration method for solder inspection and board inspection apparatus using the method
CN109856156A (en) A kind of display panel tiny flaw determination method and device based on AOI
CN101751672A (en) Image processing system
JP2020106467A (en) Defect inspection device, defect inspection method, and program therefor
JP2006099758A (en) Substrate inspection method and apparatus
CN105913093A (en) Template matching method for character recognizing and processing
CN105976354B (en) Color and gradient based component positioning method and system
CN106033544A (en) Test content area extraction method based on template matching
JP2007293809A (en) Displacement detecting device, displacement detecting method, displacement detecting program, and recording medium
CN113724216A (en) Method and system for detecting wave crest welding spot defects
CN108830267A (en) A kind of method and system goed over examination papers based on image recognition
JP2007184589A (en) Substrate inspection method and substrate inspecting apparatus
CN109484045A (en) The imaging sensor of automation is calibrated
TWI669519B (en) Board defect filtering method and device thereof and computer-readabel recording medium
CN109859164A (en) A method of by Quick-type convolutional neural networks to PCBA appearance test
CN106033535A (en) Electronic paper marking method
CN109886960A (en) The method of glass edge defects detection based on machine vision
WO2014045508A1 (en) Inspection device, inspection method, and inspection program
CN105223208B (en) A kind of circuit board detecting template and preparation method thereof, circuit board detecting method
CN109285140A (en) A kind of printed circuit board image registration appraisal procedure
CN112967221B (en) Shield segment production and assembly information management system
CN106934411A (en) Electronic paper marking method based on template matches
CN102592302A (en) Digital cartoon intelligent dynamic detection system and dynamic detection method
JP2023522360A (en) OCR-based document analysis system and method

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