CN106404792A - Machine vision recognition technology-based color difference detection method of high gloss cigarette carton packaging paper - Google Patents

Machine vision recognition technology-based color difference detection method of high gloss cigarette carton packaging paper Download PDF

Info

Publication number
CN106404792A
CN106404792A CN201610797431.4A CN201610797431A CN106404792A CN 106404792 A CN106404792 A CN 106404792A CN 201610797431 A CN201610797431 A CN 201610797431A CN 106404792 A CN106404792 A CN 106404792A
Authority
CN
China
Prior art keywords
rgb
wrapping paper
value
packaging paper
color difference
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
CN201610797431.4A
Other languages
Chinese (zh)
Other versions
CN106404792B (en
Inventor
郭丽娟
李超
范多青
赵敏
缪燕霞
段海波
刘秀明
刘欣
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.)
China Tobacco Yunnan Industrial Co Ltd
Original Assignee
China Tobacco Yunnan Industrial 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 China Tobacco Yunnan Industrial Co Ltd filed Critical China Tobacco Yunnan Industrial Co Ltd
Priority to CN201610797431.4A priority Critical patent/CN106404792B/en
Publication of CN106404792A publication Critical patent/CN106404792A/en
Application granted granted Critical
Publication of CN106404792B publication Critical patent/CN106404792B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84—Systems specially adapted for particular applications
    • G01N21/88—Investigating the presence of flaws or contamination
    • G01N21/8851—Scan 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

Landscapes

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

Abstract

The invention relates to a machine vision recognition technology-based color difference detection method of high gloss cigarette carton packaging paper. The machine vision recognition technology-based color difference detection method comprises following steps: 1, a piece of packaging paper to be tested is unfolded on a testing platform; 2, a uniform constant D65 standard light source is turned on; 3, a single set of CCD camera is selected, a panorama standard picture is taken from a fixed position, and the signals of the whole picture is obtained; 4, the panorama standard picture is divided into 32 different parts, the signal of each part is converted into digital signal via A/D conversion so as to obtain a RGB value; 5, the RGB values X<1> to X<32> are introduced into a regression equation to calculate the value of packaging paper whole RGB index Y<RGB index>, and the value is recorded as Y2; and 6, the same method is used for measuring and calculating of a piece of standard cigarette carton packaging paper, and an obtained value is recorded as Y1, wherein the absolute value of the difference value of Y2 and Y1 is divided by Y1, and it is determined that no color difference is detected between the two high gloss cigarette carton packaging paper samples to be tested if an obtained value is equal to or smaller than 5%.

Description

A kind of aberration inspection of the high photosensitiveness tobacco shred wrapping paper based on Machine Vision Recognition Technology Survey method
Technical field
The invention belongs to tobacco shred wrapping paper appearance quality trait field is and in particular to a kind of pass through Machine Vision Recognition skill The color difference analysis method to high photosensitiveness tobacco shred wrapping paper for the art.
Background technology
Tobacco shred wrapping paper presentation quality directly carries external image and the antiforge function of cigarette product, determines Medicated cigarette The primary impression to cigarette product for the final consumer, and affect the selection to cigarette product for the consumer to a certain extent.Volume Cigarette consumer requires Medicated cigarette interior quality and packaging quality to be all consistent the favor of cigarette product, and aberration is tobacco shred packaging The important indicator of paper printing quality inspection, directly influences packaging quality and the corporate image of cigarette product, is also current Medicated cigarette One of difficult point of bar wrapping paper quality control.Evaluating cigarette bar, the concordance of box packaging quality at present, generally adopts subjective visual inspection Print product is contrasted by method or color difference meter method with standard sample, to judge whether aberration.Tobacco shred packaging aberration be Refer in leaflet output procedure due to the aspects such as personnel, equipment, raw material, Technology, measurement difference so that leaflet with The heterochromia being formed in coloristic areas between original copy.
Traditional evaluation methodology of tobacco shred wrapping paper aberration mainly has visual subjective methods and integrating sphere type spectrophotometer method. Visual subjective methods are different to the impression degree of aberration due to crowd, there is larger uncertainty；Integrating sphere type light splitting light Degree instrument method, because it detects that aperture and area of detection are less, uses the mode comparing reflection optical attenuation differentiating bar simultaneously The aberration of packaging.So the detection of full width sample cannot be realized, for the detection of the tobacco shred wrapping paper aberration containing high photosensitiveness Also due to there is larger difficulty with reflecting in a jumble in the light intensity of background.Wherein said high photosensitiveness tobacco shred wrapping paper refers to minute surface The paper that reflectance is more than 30%.High photosensitiveness tobacco shred wrapping paper visual effect of magnificent mansion because of light, should with industry in cigarette With increasingly extensive, but the interference because of reflected light, the difficulty of its Difference Control is also continuously increased, traditional acetes chinensis and analysis side Method can not meet Industry Control demand.Detection method for high photosensitiveness tobacco shred wrapping paper aberration had become industry concern already One of emphasis.
Content of the invention
Present invention aims to the deficiencies in the prior art, provide a kind of Machine Vision Recognition Technology that is based on to bloom The color difference analysis method of property tobacco shred wrapping paper, fast and accurately to complete the prison of high photosensitiveness tobacco shred wrapping paper presentation quality Control work, the quality of lifting cigarette product.
The purpose of the present invention is achieved by the following technical programs.
A kind of color difference analysis method of the high photosensitiveness tobacco shred wrapping paper based on Machine Vision Recognition Technology, walks including following Suddenly：
(1) tobacco shred wrapping paper to be detected is launched into plane, and makes the one side with ink be positioned over testboard upwards On；
(2) arrange and open the D65 standard light source of a homogeneous constant on testboard；
(3) select separate unit CCD camera, shoot the full width standard drawing of Medicated cigarette high photosensitiveness bar wrapping paper in fixed position Picture, is always on light source in whole shooting process, and obtains entire image signal；
(4) acquired entire image signal is divided into 32 pieces of different regions, and by each for measured target piece of region Picture signal by A/D conversion be turned into digital signal, i.e. rgb value；
(5) by the rgb value X in 32 pieces of regions of the bar being detected wrapping paper1To X32It is substituting in following regression equation, calculate Bar wrapping paper entirety RGB index YRGB indexNumerical value：
YRGB index=10.766X1+10.789X2+9.554X3+9.522X4+8.724X5+8.717X6+8.821X7+8.639X8 +8.527X9+8.525X10+8.544X11+8.593X12+8.621X13+8.668X14+8.575X15+8.506X16+7.114X17+ 7.038X18+7.226X19+7.025X20+7.129X21+7.018X22+7.029X23+7.086X24+5.038X25+5.035X26+ 5.053X27+5.036X28+5.071X29+5.235X30+5.097X31+5.138X32；
(6) in kind measure and calculate standard cigarettes bar wrapping paper respectively, and tobacco shred wrapping paper to be compared Overall RGB index YRGB indexNumerical value Y1And Y2, as │ Y2-Y1│/Y1It is believed that two high photosensitiveness tobacco shreds to be compared are packed when≤5% Paper no color differnece.
Wherein said CCD camera preferably has fine definition and high speed camera, and wherein " fine definition " refers to differentiate Rate is at least 5,000,000 pixels, preferably at least 8,000,000 pixels, more preferably at least 10,000,000 pixels.Wherein " at a high speed " refer at least every Second beats takes the photograph 10 photos.
List in table 1 below for the rgb value in above-mentioned 32 pieces of regions, it is to tobacco shred wrapping paper entirety RGB index Regression equation coefficient.
Table 1 regression equation coefficient
With respect to prior art, the present invention has advantages below：
1st, the method for the present invention is simple and easy to do, and analysis process is quick, and accurately, adjustment is simple to operate, achievable for result of calculation Non-Destructive Testing.
2nd, adopt Uniform Illumination technology, the reflected light interference of complicated and high photosensitiveness tobacco shred wrapping paper can be successfully managed, subtract Little personal error improves efficiency, repeatability height.
3rd, Machine Vision Recognition Technology, is a kind of technology of standardization view mode.Replace human eye in a standardized way To detect the whole plane of product, rather than certain point on product, this greatly expands sample representation, improves detection Reliability.
4th, what analysis process gathered is the entire image signal of tobacco shred wrapping paper, and the RGB subregion of entire image is assigned Different weights are given to calculate overall RGB index YAs referring toNumerical value and compare.To bar wrapping paper color difference analysis more fully, it is Ensure Medicated cigarette presentation quality, and the stability of technique productions provides favourable technical support.
Brief description
Fig. 1 is tobacco shred wrapping paper picture signal zoning schematic diagram.
Fig. 2 is the in-profile figure of Machine Vision Recognition equipment, in figure label：1 is CCD camera；2 is testboard；3 are D65 standard light source；4 is image-signal processor；5 is detected sample.
Specific embodiment
The present invention is described in further detail by the following examples, but specific embodiment is not to skill of the present invention The restriction of art scheme.
Embodiment 1
A, same for cloud and mist (Yunlong) two high photosensitiveness bar wrapping papers of batch quantity-produced are launched into plane, and make band oil The one side of ink is positioned on testboard vertically upward.
B, the D65 standard light source vertical irradiation arranging on testboard and using a homogeneous constant are on testing sample.
C, selection carry fine definition, the separate unit CCD camera of high-speed camera camera lens.The visual field according to testing sample will Ask, open the uniform standard light source of D65 in (2), shoot the full width standard picture of Medicated cigarette high photosensitiveness bar wrapping paper, entirely shot It is always on light source in journey, and obtain entire image signal.
D, acquired entire image signal is divided into 32 pieces of different regions, and by each for measured target piece of region Picture signal is turned into digital signal by A/D conversion, i.e. rgb value.
E, the rgb value in 32 pieces of regions of the bar being detected wrapping paper is brought into respectively to following regression equation, and calculate Bar wrapping paper entirety RGB index YRGB indexNumerical value：
YAs referring to=10.766X1+10.789X2+9.554X3+9.522X4+8.724X5+8.717X6+8.821X7+8.639X8+ 8.527X9+8.525X10+8.544X11+8.593X12+8.621X13+8.668X14+8.575X15+8.506X16+7.114X17+ 7.038X18+7.226X19+7.025X20+7.129X21+7.018X22+7.029X23+7.086X24+5.038X25+5.035X26+ 5.053X27+5.036X28+5.071X29+5.235X30+5.097X31+5.138X32；
F, calculating standard cigarettes bar wrapping paper, and the overall RGB index Y of tobacco shred wrapping paper to be compared respectivelyRGB index's Numerical value Y1And Y2, as │ Y2-Y1│/Y1It is believed that two high photosensitiveness tobacco shred wrapping paper no color differneces to be compared when≤5%.Concrete data Referring to table 2.As shown in Table 2, sample A and B measures overall RGB index Y for tri- times2With Y1Difference ratio average be 3.093%, say Bright two samples are similar, and outward appearance does not have aberration, and this is consistent with range estimation result of determination, the also result of determination one with color difference meter simultaneously Cause, this color difference analysis method is described, and when judging the same brand trade mark aberration of same process condition, same materials, accuracy is relatively Height, has good practicality.
Table 2 adopts the colour difference assessment result to sample A and B for the distinct methods
Embodiment 2
Repeat embodiment 1, have following difference：
A laboratory sample selects cloud and mist (soft as one wishes) label paper of different technology conditions, different material, by embodiment 1 Mode is placed and detection sample.
B chooses sample C as standard, and calculates another kind of sample D and its overall RGB index YAs referring toDifference value, as The judgment basis of different sample aberration.Concrete data is referring to table 3.As shown in Table 3, the overall RGB of tri- mensure of sample C and D refers to Number Y2With Y1Difference ratio average be 21.130%, illustrate that two sample colors have notable difference, appearance chromatic difference is obvious, with Range estimation result of determination is consistent, and the result of determination of color difference meter is to there is nuance, and this color difference analysis method high resolution is described In color difference meter analysis method, when judging the identic trade mark aberration of different technology conditions, different material, there is better reliability Property.
Table 3 adopts the colour difference assessment result to sample C and D for the distinct methods

Claims (1)

1. a kind of acetes chinensis method of the high photosensitiveness tobacco shred wrapping paper based on Machine Vision Recognition Technology, walks including following Suddenly：
(1) tobacco shred wrapping paper to be detected is launched into plane, and so that the one side with ink is positioned over upwards on testboard；
(2) arrange and open the D65 standard light source of a homogeneous constant on testboard；
(3) select separate unit CCD camera, shoot the full width standard picture of Medicated cigarette high photosensitiveness bar wrapping paper in fixed position, whole It is always on light source in individual shooting process, and obtain entire image signal；
(4) acquired entire image signal is divided into 32 pieces of different regions, and the figure by each for measured target piece of region As signal is turned into digital signal by A/D conversion, i.e. rgb value；
(5) by the rgb value X in 32 pieces of regions of the bar being detected wrapping paper1To X32It is substituting in following regression equation, calculate bar bag Dress paper entirety RGB index YRGB indexNumerical value：
YRGB index=10.766X1+10.789X2+9.554X3+9.522X4+8.724X5+8.717X6+8.821X7+8.639X8+ 8.527X9+8.525X10+8.544X11+8.593X12+8.621X13+8.668X14+8.575X15+8.506X16+7.114X17+ 7.038X18+7.226X19+7.025X20+7.129X21+7.018X22+7.029X23+7.086X24+5.038X25+5.035X26+ 5.053X27+5.036X28+5.071X29+5.235X30+5.097X31+5.138X32
(6) in kind measure respectively and calculate standard cigarettes bar wrapping paper, and the entirety of tobacco shred wrapping paper to be compared RGB index YRGB indexNumerical value Y1And Y2, as │ Y2-Y1│/Y1When≤5% it is believed that two high photosensitiveness tobacco shred wrapping papers to be compared no Aberration.
CN201610797431.4A 2016-08-31 2016-08-31 A kind of acetes chinensis method of the high photosensitiveness tobacco shred wrapping paper based on Machine Vision Recognition Technology Active CN106404792B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610797431.4A CN106404792B (en) 2016-08-31 2016-08-31 A kind of acetes chinensis method of the high photosensitiveness tobacco shred wrapping paper based on Machine Vision Recognition Technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610797431.4A CN106404792B (en) 2016-08-31 2016-08-31 A kind of acetes chinensis method of the high photosensitiveness tobacco shred wrapping paper based on Machine Vision Recognition Technology

Publications (2)

Publication Number Publication Date
CN106404792A true CN106404792A (en) 2017-02-15
CN106404792B CN106404792B (en) 2019-09-17

Family

ID=58001952

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610797431.4A Active CN106404792B (en) 2016-08-31 2016-08-31 A kind of acetes chinensis method of the high photosensitiveness tobacco shred wrapping paper based on Machine Vision Recognition Technology

Country Status (1)

Country Link
CN (1) CN106404792B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110243475A (en) * 2019-05-05 2019-09-17 浙江乌镇街科技有限公司 A kind of fabric acetes chinensis method based on Machine Vision Recognition Technology
CN111579505A (en) * 2020-04-23 2020-08-25 河南中烟工业有限责任公司 Cigarette packaging material color difference detection method based on digital image processing
CN111739018A (en) * 2020-07-27 2020-10-02 中建科技集团有限公司 Chromatic aberration detection method, device, terminal and medium based on point cloud technology

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102494773A (en) * 2011-11-14 2012-06-13 无锡众望四维科技有限公司 Automatic detection method of machine vision system on snap-fastener chromatic aberration
CN104197838A (en) * 2014-09-19 2014-12-10 安徽中烟工业有限责任公司 Computer vision based cigarette carton and box packing paper dimension measurement method
CN104574389A (en) * 2014-12-26 2015-04-29 康奋威科技（杭州）有限公司 Battery piece chromatism selection control method based on color machine vision
CN104764718A (en) * 2015-04-14 2015-07-08 云南中烟工业有限责任公司 Method for performing color-difference evaluation on cigarette outside wrapping paper

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102494773A (en) * 2011-11-14 2012-06-13 无锡众望四维科技有限公司 Automatic detection method of machine vision system on snap-fastener chromatic aberration
CN104197838A (en) * 2014-09-19 2014-12-10 安徽中烟工业有限责任公司 Computer vision based cigarette carton and box packing paper dimension measurement method
CN104574389A (en) * 2014-12-26 2015-04-29 康奋威科技（杭州）有限公司 Battery piece chromatism selection control method based on color machine vision
CN104764718A (en) * 2015-04-14 2015-07-08 云南中烟工业有限责任公司 Method for performing color-difference evaluation on cigarette outside wrapping paper

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
范鹏飞等: "金属印刷品在线色差检测系统", 《江南大学学报》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110243475A (en) * 2019-05-05 2019-09-17 浙江乌镇街科技有限公司 A kind of fabric acetes chinensis method based on Machine Vision Recognition Technology
CN110243475B (en) * 2019-05-05 2021-09-24 浙江乌镇街科技有限公司 Fabric color difference detection method based on machine vision recognition technology
CN111579505A (en) * 2020-04-23 2020-08-25 河南中烟工业有限责任公司 Cigarette packaging material color difference detection method based on digital image processing
CN111739018A (en) * 2020-07-27 2020-10-02 中建科技集团有限公司 Chromatic aberration detection method, device, terminal and medium based on point cloud technology
CN111739018B (en) * 2020-07-27 2020-12-11 中建科技集团有限公司 Chromatic aberration detection method, device, terminal and medium based on point cloud technology

Also Published As

Publication number Publication date
CN106404792B (en) 2019-09-17

Similar Documents

Publication Publication Date Title
KR0169892B1 (en) Method and apparatus for measuring nonuniformity of glossiness and thickness of printed image
CN107144353B (en) A kind of textile chromatism measurement method based on digital camera
CN101518980B (en) Printing color quality detecting method of integrating visual measurement, density measurement and color measurement
Leon et al. Color measurement in L∗ a∗ b∗ units from RGB digital images
CN101100807B (en) Textile color stability and color aberration grading method
CN107505046B (en) Multispectral color measurement method
CN106585090B (en) A kind of detection and bearing calibration of Dot Area increment value
US5917541A (en) Color sense measuring device
CN107192456A (en) A kind of color measuring multi-optical spectrum imaging system based on LED illumination
CN106404792A (en) Machine vision recognition technology-based color difference detection method of high gloss cigarette carton packaging paper
US20220358682A1 (en) Device and method for detecting cigarette fly ash by gray-scale difference based on machine vision (mv)
CN108801938A (en) A kind of aberration On-line Measuring Method and system
CN111579505A (en) Cigarette packaging material color difference detection method based on digital image processing
CN102445275A (en) Spectrum light splitting color image color acquisition box and spectrum light splitting color image color detection method
CN113156047A (en) Image method based cigarette combustion ash column gray testing method
CN109459136A (en) A kind of method and apparatus of colour measurement
JP2016206760A (en) Color discrimination method and color discrimination device, as well as printer color tone control method
CN102279160A (en) Method for evaluating quality of famous green tea
CN217465848U (en) Synchronous quantitative measurement device for pearl multi-grade index parameters based on multi-azimuth observation
CN110243475B (en) Fabric color difference detection method based on machine vision recognition technology
JP2008533435A (en) Method and apparatus for metrologically detecting a visually perceived color impression difference between a reference multicolor patterned surface and a test item multicolor patterned surface
CN101788460B (en) Method for detecting color change of note ink
CN206832360U (en) The closed lamp box of color measuring multi-optical spectrum imaging system based on LED illumination
Gabrova et al. Explore the possibilities for objective assessment of some beer quality indicators
CN103852430B (en) A kind of measurement of aluminium paper POP ink printing look and characterizing 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