CN104198325B - Stem ratio measuring method in pipe tobacco based on computer vision - Google Patents

Stem ratio measuring method in pipe tobacco based on computer vision Download PDF

Info

Publication number
CN104198325B
CN104198325B CN201410448180.XA CN201410448180A CN104198325B CN 104198325 B CN104198325 B CN 104198325B CN 201410448180 A CN201410448180 A CN 201410448180A CN 104198325 B CN104198325 B CN 104198325B
Authority
CN
China
Prior art keywords
stem
pipe tobacco
measured
value
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201410448180.XA
Other languages
Chinese (zh)
Other versions
CN104198325A (en
Inventor
董浩
刘锋
王澍
周明珠
张龙
刘勇
周德成
李晓辉
荆熠
王锦平
邢军
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.)
Hefei Institutes of Physical Science of CAS
National Tobacco Quality Supervision and Inspection Center
Original Assignee
Hefei Institutes of Physical Science of CAS
National Tobacco Quality Supervision and Inspection Center
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 Hefei Institutes of Physical Science of CAS, National Tobacco Quality Supervision and Inspection Center filed Critical Hefei Institutes of Physical Science of CAS
Priority to CN201410448180.XA priority Critical patent/CN104198325B/en
Publication of CN104198325A publication Critical patent/CN104198325A/en
Application granted granted Critical
Publication of CN104198325B publication Critical patent/CN104198325B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Abstract

The invention discloses a kind of stem ratio measuring method in pipe tobacco based on computer vision, A: utilize image capturing system to gather each stem image respectively;B: multiple the stem images obtained are pre-processed;C: the characteristics of image obtaining stem respectively the characteristic amount calculating stem;D: set up property data base;E: gather pipe tobacco to be measured each constitutional diagram picture;F: constitutional diagram picture each to pipe tobacco to be measured pre-processes;G: calculate in pipe tobacco to be measured each constitutional diagram picture pipe tobacco characteristic amount to be measured and carry out relatedness computation, is analyzed identifying to stem component according to relatedness computation result;H: sorted out the stem in pipe tobacco to be measured by sorting system;I: weigh by and calculate stem component ratio in pipe tobacco to be measured respectively.The present invention is capable of quick, accurate, the automatic assay of stem component in pipe tobacco, improves determination efficiency and accuracy, reduces intensity of workers.

Description

Stem ratio measuring method in pipe tobacco based on computer vision
Technical field
The present invention relates to a kind of stem ratio measuring method in pipe tobacco, particularly relate to one and regard based on computer Stem ratio measuring method in the pipe tobacco felt.
Background technology
Cigarette composition design is basis and the core of cigarette enterprise product design, cut tobacco, expansion leaf in cigarette The components such as silk, stem, reconstituted tobacco accurately mix pairing cigarette physical index, flue gas characteristic and sense organ matter There is impact in various degree in amount.Therefore, determine rapidly and accurately cut tobacco in cigarette, expansive cut tobacco, The component such as stem, reconstituted tobacco ratio in pipe tobacco, to examination formula design object accuracy, stablizes Pipe tobacco hybrid technique quality and homogeneity produce significant.
Owing to the feature of detection object is complicated and relates to correlation technique bottleneck, therefore pipe tobacco constituent Mensuration still relies on hand-sorting and artificial interpretation.At present, normally used stem ratiometric method is Stem in cigarette is separated by water with other components, weighs after drying, calculate the ratio of stem. Existing detection method operating procedure is complicated, and detection efficiency is low, along with the increase of workload will produce relatively Big error, is not suitable for detecting in a large number, and measurement efficiency and precision have been difficult to adapt to the detection of modernization to be needed Bigger error is there is also between the requirement of summation high-quality production of cigarettes, and the testing result of different personnel.
Due to processing method and the difference of raw material self character, between the different component of pipe tobacco, there is texture, face Look, form, the difference of edge-smoothing degree, these differences to exist for computer vision means identification each Component provides characteristic parameter.Comparing other components, the texture of stem and edge feature clearly, can To be made a distinction with other components by computer vision technique.
Summary of the invention
It is an object of the invention to provide a kind of stem ratio measuring method in pipe tobacco based on computer vision, Can be acquired processing to the image of one-component stem by computer, obtain the characteristic of stem Measure and set up property data base, by the stem in property data base analysis identification multicomponent pipe tobacco, finally Realize quick, accurate, the automatic assay of stem component in pipe tobacco, improve determination efficiency and accuracy, Reduce intensity of workers.
The present invention uses following technical proposals:
A kind of stem ratio measuring method in pipe tobacco based on computer vision, comprises the following steps:
A: non-overlapping put smooth for many stems, then utilize image capturing system to gather each respectively Stem image;
B: utilize image processing and analyzing system that multiple the stem images obtained are pre-processed, remove every Interference in stem image and noise;
C: utilize image processing and analyzing system to obtain the characteristics of image of stem in multiple stem images respectively, so Afterwards according to the characteristic amount of the box counting algorithm stem of stem;
D: utilize image processing and analyzing system to set up according to the characteristic amount of the stem in multiple stem images Property data base;
E: piece-rate system is smooth non-overlapping puts by sprawling by pipe tobacco to be measured, utilizes image capturing system Gather pipe tobacco to be measured each constitutional diagram picture;
F: utilize image processing and analyzing system that the pipe tobacco to be measured each constitutional diagram picture obtained is pre-processed, go Except the interference in pipe tobacco to be measured each constitutional diagram picture and noise;
G: pipe tobacco characteristic amount to be measured in image processing and analyzing system-computed pipe tobacco to be measured each constitutional diagram picture, And carry out relatedness computation with the characteristic amount of the stem in the property data base set up in step D, It is analyzed identifying to the stem component being blended in pipe tobacco according to relatedness computation result;
H: image processing and analyzing system will be analyzed recognition result and send to sorting system, sorting system sort Go out the stem in pipe tobacco to be measured;
I: weigh the stem quality and remaining ingredient quality sorted out by sorting system respectively, and calculate to be measured The ratio of stem component in pipe tobacco.
In described step B, image processing and analyzing system uses the scanning window of 5 × 5 pixels to acquisition Stem image is scanned according to order from top to bottom, from left to right, calculates stem in scanning window Image average and variance Var, if variance Var is more than setting threshold value TD, then this point is used Quick Median Filtering method is smoothed, and removes the interference in stem image and noise.
In described step C, the stem image of acquisition is transformed into hsv color by image processing and analyzing system Space;In conjunction with Canny and Log edge detection operator respectively to R, G, B, H, S, V these six The image of component carries out rim detection, records pipe tobacco in R, G, B, H, S, V component image respectively The pixel variance yields V in regionR、VG、VB、VH、VS、VV;Then gray level co-occurrence matrixes is used to calculate stalk The contrast in pipe tobacco region, entropy, angle second moment and four textural characteristics values of correlation in silk image;Wherein, Wherein, R component graphical representation is at RGB color, and the R value of each pixel is constant, G value and B Value is zero;G component image represents at RGB color, and the G value of each pixel is constant, R Value and B value are zero;B component graphical representation is at RGB color, and the B value of each pixel is not Becoming, R value and G value are zero;H component image represents in hsv color space, the H of each pixel Being worth constant, S value and V value are zero;S component image represents in hsv color space, each pixel S value constant, H value and V value are zero;V component graphical representation in hsv color space, each The V value of pixel is constant, and H value and S value are zero;Characteristic amount described in step C includes ten The V in pipe tobacco region in individual characteristic value, respectively stem imageR、VG、VB、VH、VS、VVSix components On pixel variance yields, and the contrast in pipe tobacco region in stem image, entropy, angle second moment and relevant Four textural characteristics values of property.
In described step D, image processing and analyzing system calculates the spy of stem in every stem image respectively Levy data volume, and add up distribution C of each characteristic valuei(i=1,2 ..., 10), then by each model The value enclosed is multiplied by the proportionality coefficient e of correspondencei(i=1,2 ..., 10), finally set up property data base Ti=Ciei(i=1,2 ..., 10), wherein,Inverse for dispersion degree.
In described step F, image processing and analyzing system uses the scanning window of 5 × 5 pixels to acquisition Pipe tobacco to be measured each constitutional diagram picture is scanned according to order from top to bottom, from left to right, calculates and sweep Average and variance Var in pipe tobacco to be measured each constitutional diagram picture in retouching window, if variance Var is more than setting threshold value TD, then use Fast Median Filtering method to be smoothed this point, remove each constitutional diagram of pipe tobacco to be measured Interference in Xiang and noise.
In described step G, image processing and analyzing system calculates in pipe tobacco characteristic amount to be measured respectively Ten characteristic values, and these ten characteristic values are directed respectively in property data base, then image processing and analyzing The degree of correlation with stem of system-computed pipe tobacco to be measured, the calculating of degree of correlation R with stem of pipe tobacco to be measured Formula is R = n &CenterDot; &Pi; i = 1 n S i 10 , Wherein S i = x i V &OverBar; i x i < V &OverBar; i V &OverBar; i x i x i &GreaterEqual; V &OverBar; i , n &Element; [ 1,10 ] , For pipe tobacco to be measured ten Individual characteristic value is in the quantity in property data base critical field;xiFor character pair value,It is characterized The average of this feature value in database;If degree of correlation R is more than or equal to relevance threshold T, then judge current Pipe tobacco to be measured is stem;If degree of correlation R is less than relevance threshold T, then judge that current pipe tobacco to be measured is not Stem, wherein, relevance threshold T is the dispersion degree of character pair databaseT ∈ [0.25,0.75],
The present invention, based on computer vision technique, by the stem image acquisition and processing to one-component, obtains Take the characteristic amount of stem and set up property data base, then by property data base analysis identification multicomponent Stem in pipe tobacco also sorts, it is possible to avoid the manual measurement impact on test result in existing method, Eliminate human error;The present invention by gathering stem feature input database, one by one by pipe tobacco to be measured finally Compare calculating with the stem feature in database, finally sort out the stem component in pipe tobacco, test Speed is fast, and can provide other test data such as area ratio, geomery parameter;Measurement process is complete Full-automatic process, it is possible to increase the efficiency of measurement, accuracy and certainty of measurement, significantly reduces the amount of labour.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of the present invention.
Detailed description of the invention
As it is shown in figure 1, stem ratio measuring method in pipe tobacco based on computer vision of the present invention, It is characterized in that, comprise the following steps:
A: non-overlapping put smooth for many stems, then utilize image capturing system to gather each respectively Stem image;
B: utilize image processing and analyzing system that multiple the stem images obtained are pre-processed, remove every Interference in stem image and noise;
When carrying out pre-processing and removing interference and noise, image processing and analyzing system uses 5 × 5 pixels The stem image obtained is scanned, then by scanning window according to order from top to bottom, from left to right Calculate stem image average and variance Var in scanning window, if variance Var is more than setting threshold value TD, Then show that at this, pixel value has large change, use Fast Median Filtering method to be smoothed this point, Remove the interference in stem image and noise.Calculating to image average and variance Var belongs to this area Prior art, is smoothed removing interference by Fast Median Filtering method and noise falls within ability The prior art in territory, does not repeats them here.
C: utilize image processing and analyzing system to obtain the characteristics of image of stem in multiple stem images respectively, so Afterwards according to the characteristic amount of the box counting algorithm stem of stem;
When carrying out step C, first the stem image of acquisition is transformed into HSV by image processing and analyzing system Color space;In conjunction with Canny and Log edge detection operator respectively to R, G, B, H, S, V this The image of six components carries out rim detection, records the pixel variance in pipe tobacco region in each component image respectively Value VR、VG、VB、VH、VS、VV;Then gray level co-occurrence matrixes is used to calculate pipe tobacco district in stem image The contrast in territory, entropy, angle second moment and four textural characteristics values of correlation;Wherein, R component image table Showing at RGB color, the R value of each pixel is constant, and G value and B value are zero;H component Graphical representation is in hsv color space, and the H value of each pixel is constant, and S value and V value are zero; Other component image is by that analogy.
Characteristic amount described in step C includes ten characteristic values, respectively R, G, B, H, S, The pixel variance yields V in stem region in V component imageR、VG、VB、VH、VS、VV, and stem figure The contrast in pipe tobacco region, entropy, angle second moment and four textural characteristics values of correlation in Xiang.In step C Image is transformed into hsv color space, utilizes Canny and Log edge detection operator that image is carried out Rim detection, use gray level co-occurrence matrixes calculate contrast, entropy, angle second moment and correlation and are ability The prior art in territory, does not repeats them here.
D: utilize image processing and analyzing system to set up according to the characteristic amount of the stem in multiple stem images Property data base;
Image processing and analyzing system calculates the characteristic amount of stem in every stem image respectively, and adds up Distribution C of each characteristic valuei(i=1,2 ..., 10), then the value of each scope is multiplied by correspondence Proportionality coefficient ei(i=1,2 ..., 10), finally set up property data base Ti=Ciei(i=1,2 ..., 10). Wherein,Inverse for dispersion degree.
E: piece-rate system is smooth non-overlapping puts by sprawling by pipe tobacco to be measured, utilizes image capturing system Gather pipe tobacco to be measured each constitutional diagram picture;
F: utilize method described in B to pre-process the image collected, removes each component of pipe tobacco to be measured Interference in image and noise, detailed process repeats no more;
G: pipe tobacco characteristic amount to be measured in image processing and analyzing system-computed pipe tobacco to be measured each constitutional diagram picture, And carry out relatedness computation with the characteristic amount of the stem in the property data base set up in step D, It is analyzed identifying to the stem component being blended in pipe tobacco according to relatedness computation result.
In step G, image processing and analyzing system calculates ten characteristic values of pipe tobacco to be measured respectively, i.e. R, The pixel variance yields V in pipe tobacco region in G, B, H, S, V component imageR、VG、VB、VH、VS、VV, And the contrast in pipe tobacco region, entropy, angle second moment and correlation in pipe tobacco image.And by above-mentioned ten spies Value indicative is directed respectively in property data base, then by image processing and analyzing system-computed pipe tobacco to be measured and stalk The degree of correlation of silk, pipe tobacco to be measured with the computing formula of degree of correlation R of stem is:
Wherein S i = x i V &OverBar; i x i < V &OverBar; i V &OverBar; i x i x i &GreaterEqual; V &OverBar; i . Wherein, n ∈ [1,10], represent the 10 of pipe tobacco to be measured The quantity that is in individual characteristic value in property data base critical field (in property data base VR、VG、VB、 VH、VS、VV, contrast, entropy, this each self-corresponding distribution of ten values of angle second moment be this value Critical field);xiRepresent characteristic of correspondence value,It is characterized the average of this feature value in database;
If degree of correlation R is more than or equal to relevance threshold T, then judge that current pipe tobacco to be measured is as stem;If phase Pass degree R < T, then judge that current pipe tobacco to be measured is not stem.Wherein, during actually detected identification, The dispersion degree of relevance threshold T character pair databaseT ∈ [0.25,0.75], eiComputational methods Be given in step D.Dispersion degree is the biggest, and the critical field of this feature database is the biggest, corresponding T is the least;Otherwise, T is the biggest.
H: image processing and analyzing system will be analyzed recognition result and send to sorting system, sorting system sort Go out the stem in pipe tobacco to be measured;
I: weigh the stem quality and remaining ingredient quality sorted out by sorting system respectively, and calculate to be measured The ratio of stem component in pipe tobacco.
In the present invention, image capturing system includes lighting device, imaging device and image capture software, shines The effect of bright device is to provide suitably illumination for stem and pipe tobacco to be measured, in order to obtain clear real Image;Lighting device can use can provide the planar light source of uniform floodlighting, annular light source, luminescence The light-source system such as LED array, backlight;Imaging device mainly includes camera lens and camera two parts, imaging The effect of device is to cooperate with image capture software and obtains stem and the image of pipe tobacco to be measured;Image capture software The most existing various software can be used, such as Motic2.0 image capture software;Image analysis processing system System can use host computer, coordinates the software according to the establishment of conventional images Treatment Analysis technology to realize correlation function, Such as MATLAB image processing and analyzing software;Sprawl piece-rate system to comprise feed belt, vibratory sieve, shake The mechanical device of smooth for pipe tobacco to be measured non-overlapping separation drawout or device can be combined by moving platforms etc., Sorting system comprises the stem that mechanical sorting machine, manipulator, malleation or negative pressure straw etc. can will identify that The device sorted out with other pipe tobacco components or device combination.Each equipment above-mentioned and corresponding software belong to Existing product, does not repeats them here.
Below in conjunction with embodiment, the present invention will be further elaborated:
Embodiment 1
1) non-overlapping it is placed in smooth for 2 stems under high light LED illumination array, passes through CCD Camera and the Motic2.0 image capture software of autofocus lens coupled computer end, collect 2 Stem image;
2) utilize MATLAB image processing and analyzing software that 2 the stem images obtained are pre-processed, Remove the interference in every stem image and noise;
3) characteristics of image of stem during computer obtains 2 stem images respectively, then according to the figure of stem Characteristic amount as feature calculation stem;
4) computer sets up property data base according to the characteristic amount of the stem in 2 stem images;
5) by pipe tobacco to be measured, by sprawling, piece-rate system is smooth non-overlapping is placed in high light LED illumination battle array Under row, the Motic2.0 IMAQ by CCD camera and autofocus lens coupled computer end is soft Part gathers pipe tobacco to be measured each constitutional diagram picture;
6) utilize MATLAB image processing and analyzing software that the pipe tobacco to be measured each constitutional diagram picture obtained is carried out Pretreatment, removes the interference in pipe tobacco to be measured each constitutional diagram picture and noise;
7) computer calculates pipe tobacco characteristic amount to be measured in pipe tobacco to be measured each constitutional diagram picture, and with step D The characteristic amount of the stem in middle set up property data base carries out relatedness computation, according to the degree of correlation The stem component being blended in pipe tobacco is analyzed identifying by result of calculation;
8) analysis recognition result is sent to sorting system by computer, sorting system sort out pipe tobacco to be measured In stem;
9) the stem quality sorted out that weighs with scale is 0.6g, and remaining ingredient quality 1.4g, then in pipe tobacco The ratio of stem component is 30%.
Embodiment 2
1) non-overlapping it is placed in smooth for 20 stems under planar light source, by CCD camera and micro- Away from the Motic2.0 image capture software of tight shot coupled computer end, collect 20 stem figures Picture;
2) utilize MATLAB image processing and analyzing software that 20 the stem images obtained are carried out pre-place Reason, removes the interference in every stem image and noise;
3) characteristics of image of stem during computer obtains 20 stem images respectively, then according to stem The characteristic amount of box counting algorithm stem;
4) computer sets up property data base according to the characteristic amount of the stem in 20 stem images;
5) by pipe tobacco to be measured, by sprawling, piece-rate system is smooth non-overlapping to be placed under planar light source, passes through The Motic2.0 image capture software of CCD camera and microspur tight shot coupled computer end gathers to be measured Pipe tobacco each constitutional diagram picture;
6) utilize MATLAB image processing and analyzing software that the pipe tobacco to be measured each constitutional diagram picture obtained is carried out Pretreatment, removes the interference in pipe tobacco to be measured each constitutional diagram picture and noise;
7) computer calculates pipe tobacco characteristic amount to be measured in pipe tobacco to be measured each constitutional diagram picture, and with step D The characteristic amount of the stem in middle set up property data base carries out relatedness computation, according to the degree of correlation The stem component being blended in pipe tobacco is analyzed identifying by result of calculation;
8) analysis recognition result is sent to sorting system by computer, sorting system sort out pipe tobacco to be measured In stem;
9) weigh with scale stem quality 1.0g sorted out and remaining ingredient quality 4.5g, then in pipe tobacco The ratio of stem component is 18%.

Claims (4)

1. stem ratio measuring method in a pipe tobacco based on computer vision, it is characterised in that comprise the following steps:
A: non-overlapping put smooth for many stems, then utilize image capturing system to gather each stem image respectively;
B: utilize image processing and analyzing system that multiple the stem images obtained are pre-processed, remove the interference in every stem image and noise;
In step B, image processing and analyzing system uses the scanning window of 5 × 5 pixels to be scanned the stem image obtained according to order from top to bottom, from left to right, calculates stem image average and variance Var in scanning window, if variance Var is more than setting threshold value TD, then use Fast Median Filtering method to be smoothed stem image in scanning window, remove the interference in stem image and noise;
C: utilize image processing and analyzing system to obtain the characteristics of image of stem in multiple stem images respectively, then according to the characteristic amount of the box counting algorithm stem of stem;
In step C, the stem image of acquisition is transformed into hsv color space by image processing and analyzing system;In conjunction with Canny and Log edge detection operator, image to these six components of R, G, B, H, S, V carries out rim detection respectively, records the pixel variance yields V in pipe tobacco region in R, G, B, H, S, V component image respectivelyR、VG、VB、VH、VS、VV;Then gray level co-occurrence matrixes is used to calculate the contrast in pipe tobacco region, entropy, angle second moment and four textural characteristics values of correlation in stem image;Wherein, R component graphical representation is at RGB color, and the R value of each pixel is constant, and G value and B value are zero;G component image represents at RGB color, and the G value of each pixel is constant, and R value and B value are zero;B component graphical representation is at RGB color, and the B value of each pixel is constant, and R value and G value are zero;H component image represents that, in hsv color space, the H value of each pixel is constant, and S value and V value are zero;S component image represents that, in hsv color space, the S value of each pixel is constant, and H value and V value are zero;V component graphical representation is in hsv color space, and the V value of each pixel is constant, and H value and S value are zero;Characteristic amount described in step C includes the V in pipe tobacco region in ten characteristic values, respectively stem imageR、VG、VB、VH、VS、VVPixel variance yields on six components, and the contrast in pipe tobacco region, entropy, angle second moment and four textural characteristics values of correlation in stem image;
D: utilize image processing and analyzing system to set up property data base according to the characteristic amount of the stem in multiple stem images;
E: piece-rate system is smooth non-overlapping puts by sprawling by pipe tobacco to be measured, utilizes image capturing system to gather pipe tobacco to be measured each constitutional diagram picture;
F: utilize image processing and analyzing system that the pipe tobacco to be measured each constitutional diagram picture obtained is pre-processed, remove the interference in pipe tobacco to be measured each constitutional diagram picture and noise;
G: pipe tobacco characteristic amount to be measured in image processing and analyzing system-computed pipe tobacco to be measured each constitutional diagram picture, and carry out relatedness computation with the characteristic amount of the stem in the property data base set up in step D, it is analyzed identifying to the stem component being blended in pipe tobacco according to relatedness computation result;
H: image processing and analyzing system will be analyzed recognition result and send to sorting system, sorting system sort out the stem in pipe tobacco to be measured;
I: weigh the stem quality and remaining ingredient quality sorted out by sorting system respectively, and calculate the ratio of stem component in pipe tobacco to be measured.
Stem ratio measuring method in pipe tobacco based on computer vision the most according to claim 1, it is characterized in that: in described step D, image processing and analyzing system calculates the characteristic amount of stem in every stem image respectively, and adds up distribution C of each characteristic valuei(i=1,2 ..., 10), then the value of each scope is multiplied by the proportionality coefficient e of correspondencei(i=1,2 ..., 10), finally set up property data base Ti=Ciei(i=1,2 ..., 10), wherein,Inverse for dispersion degree.
Stem ratio measuring method in pipe tobacco based on computer vision the most according to claim 2, it is characterized in that: in described step F, image processing and analyzing system uses in the scanning window of 5 × 5 pixels pipe tobacco to be measured each constitutional diagram picture to obtaining and is scanned according to order from top to bottom, from left to right, average and variance Var in pipe tobacco to be measured each constitutional diagram picture in calculating scanning window, if variance Var is more than setting threshold value TD, then use Fast Median Filtering method to be smoothed on pipe tobacco to be measured in scanning window each constitutional diagram picture, remove the interference in pipe tobacco to be measured each constitutional diagram picture and noise.
Stem ratio measuring method in pipe tobacco based on computer vision the most according to claim 3, it is characterized in that: in described step G, image processing and analyzing system calculates ten characteristic values in pipe tobacco characteristic amount to be measured respectively, and these ten characteristic values are directed respectively in property data base, then image processing and analyzing system-computed pipe tobacco to be measured and the degree of correlation of stem, pipe tobacco to be measured with the computing formula of degree of correlation R of stem isWhereinN ∈ [1,10], for being in the quantity in property data base critical field in ten characteristic values of pipe tobacco to be measured;xiFor character pair value,It is characterized the average of this feature value in database;If degree of correlation R is more than or equal to relevance threshold T, then judge that current pipe tobacco to be measured is as stem;If degree of correlation R is less than relevance threshold T, then judging that current pipe tobacco to be measured is not stem, wherein, relevance threshold T is the dispersion degree of character pair databaseT ∈ [0.25,0.75],
CN201410448180.XA 2014-09-04 2014-09-04 Stem ratio measuring method in pipe tobacco based on computer vision Active CN104198325B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410448180.XA CN104198325B (en) 2014-09-04 2014-09-04 Stem ratio measuring method in pipe tobacco based on computer vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410448180.XA CN104198325B (en) 2014-09-04 2014-09-04 Stem ratio measuring method in pipe tobacco based on computer vision

Publications (2)

Publication Number Publication Date
CN104198325A CN104198325A (en) 2014-12-10
CN104198325B true CN104198325B (en) 2016-09-07

Family

ID=52083650

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410448180.XA Active CN104198325B (en) 2014-09-04 2014-09-04 Stem ratio measuring method in pipe tobacco based on computer vision

Country Status (1)

Country Link
CN (1) CN104198325B (en)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107271312B (en) * 2017-07-15 2019-06-21 中国烟草总公司郑州烟草研究院 A method of based on stem content in thermoanalysis technology measurement pipe tobacco
CN109307739B (en) * 2018-09-20 2020-12-08 云南中烟工业有限责任公司 Method for rapidly estimating reconstituted tobacco shred blending proportion of tobacco shreds in cigarettes
CN109297854B (en) * 2018-09-20 2020-12-08 云南中烟工业有限责任公司 Method for rapidly measuring real mixing ratio of cut stems in strip running silks
CN109307740B (en) * 2018-09-20 2021-01-29 云南中烟工业有限责任公司 Method for rapidly estimating cut stem real-doped proportion of cut tobacco in cigarette

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102590211B (en) * 2011-01-11 2014-10-22 郑州大学 Method for utilizing spectral and image characteristics to grade tobacco leaves
CN102679883B (en) * 2012-05-09 2014-06-18 中国科学院光电技术研究所 Tobacco shred width measurement method based on image processing
CN103175835B (en) * 2013-02-26 2015-04-08 上海烟草集团有限责任公司 Method for determining area quality of tobacco leaves based on intelligent image processing and model estimation
CN103592304A (en) * 2013-10-23 2014-02-19 上海烟草集团有限责任公司 Stem object analysis system and stem object analysis method
CN103752531B (en) * 2014-01-14 2016-08-17 河南科技大学 A kind of Nicotiana tabacum L. sorter based on machine vision

Also Published As

Publication number Publication date
CN104198325A (en) 2014-12-10

Similar Documents

Publication Publication Date Title
CN104256882B (en) Based on reconstituted tobacco ratio measuring method in the pipe tobacco of computer vision
CN100561186C (en) The method of testing and the device that are used for the textile color stability and color aberration grading
CN104198325B (en) Stem ratio measuring method in pipe tobacco based on computer vision
CN101424514B (en) Band tape graduation on-line automatic detection system and method based on image processing
CN101059424A (en) Multiple spectrum meat freshness artificial intelligence measurement method and system
CN104198457B (en) Cut tobacco component recognition method based on spectral imaging technology
CN104198324B (en) Computer vision-based method for measuring proportion of cut leaves in cut tobacco
CN106780537B (en) A kind of paper cocooning frame silk cocoon screening plant and method based on image procossing
CN105466921A (en) Simultaneous detection method of many samples
CN106340000A (en) Bone age assessment method
CN110403232A (en) A kind of cigarette quality detection method based on second level algorithm
CN106248680A (en) A kind of engine commutator quality detecting system based on machine vision and detection method
CN105067532A (en) Method for identifying early-stage disease spots of sclerotinia sclerotiorum and botrytis of rape
CN111242123A (en) Power equipment fault diagnosis method based on infrared image
CN106548480A (en) A kind of agricultural product volume rapid measurement device and measuring method based on machine vision
CN105160346A (en) Tongue coating greasyness identification method based on texture and distribution characteristics
CN110044485B (en) Image type fabric color measuring method
Patki et al. Cotton leaf disease detection & classification using multi SVM
CN109827957B (en) Rice leaf SPAD value estimation method and system based on computer vision
He et al. A binocular stereovision system for transplant growth variables analysis
JP5644655B2 (en) Edible fruit inspection method, inspection apparatus and program
CN104198491B (en) Based on expansive cut tobacco ratio measuring method in the tobacco shred of computer vision
Storlie et al. Growth analysis of whole plants using video imagery
CN110705655A (en) Tobacco leaf classification method based on coupling of spectrum and machine vision
CN110503623A (en) A method of Bird&#39;s Nest defect on the identification transmission line of electricity based on convolutional neural networks

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