CN107991303A - A kind of leaf of beating based on double spectral techniques goes stalk quality detection device and detection method - Google Patents
A kind of leaf of beating based on double spectral techniques goes stalk quality detection device and detection method Download PDFInfo
- Publication number
- CN107991303A CN107991303A CN201711368697.8A CN201711368697A CN107991303A CN 107991303 A CN107991303 A CN 107991303A CN 201711368697 A CN201711368697 A CN 201711368697A CN 107991303 A CN107991303 A CN 107991303A
- Authority
- CN
- China
- Prior art keywords
- leaf
- stalk
- ray
- offal
- rate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000010009 beating Methods 0.000 title claims abstract description 26
- 230000003595 spectral effect Effects 0.000 title claims abstract description 18
- 241000208125 Nicotiana Species 0.000 claims abstract description 57
- 235000002637 Nicotiana tabacum Nutrition 0.000 claims abstract description 57
- 238000010276 construction Methods 0.000 claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 9
- 238000003384 imaging method Methods 0.000 claims abstract description 8
- 239000000463 material Substances 0.000 claims description 33
- 238000005303 weighing Methods 0.000 claims description 26
- 238000012360 testing method Methods 0.000 claims description 12
- 230000001681 protective effect Effects 0.000 claims description 10
- 238000001816 cooling Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 9
- 238000005070 sampling Methods 0.000 claims description 9
- 241000196324 Embryophyta Species 0.000 claims description 6
- 239000011521 glass Substances 0.000 claims description 6
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 235000019504 cigarettes Nutrition 0.000 claims description 5
- 230000001105 regulatory effect Effects 0.000 claims description 5
- 230000005284 excitation Effects 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 239000000700 radioactive tracer Substances 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 239000004575 stone Substances 0.000 claims description 3
- 230000008685 targeting Effects 0.000 claims description 3
- 238000011144 upstream manufacturing Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 7
- 235000013305 food Nutrition 0.000 abstract description 2
- 238000012545 processing Methods 0.000 description 5
- 238000000205 computational method Methods 0.000 description 4
- 238000002594 fluoroscopy Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 230000001066 destructive effect Effects 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000009738 saturating Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
- 210000003462 vein Anatomy 0.000 description 1
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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N23/00—Investigating or analysing materials by the use of wave or particle radiation, e.g. X-rays or neutrons, not covered by groups G01N3/00 – G01N17/00, G01N21/00 or G01N22/00
-
- 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
- G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2223/00—Investigating materials by wave or particle radiation
- G01N2223/10—Different kinds of radiation or particles
- G01N2223/101—Different kinds of radiation or particles electromagnetic radiation
- G01N2223/1016—X-ray
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2223/00—Investigating materials by wave or particle radiation
- G01N2223/40—Imaging
- G01N2223/401—Imaging image processing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2223/00—Investigating materials by wave or particle radiation
- G01N2223/60—Specific applications or type of materials
- G01N2223/621—Specific applications or type of materials tobacco
Abstract
The invention discloses a kind of leaf of beating based on double spectral techniques to go stalk quality detection device and detection method, and the detection device includes laying device (1), positioned at the paver (2) of (1), the X-ray detection machine (3) below paver (2), the visible detection machine (4) positioned at X-ray detection machine (3) outlet lower section, material-receiving device (6), rack (5) and switch board (7) positioned at visible detection machine (4) outlet lower section below laying device.The present invention respectively obtains tobacco leaf area and offal area, offal length using visible ray and x-ray imaging technology and corresponding image algorithm, avoid when splitting leaf, stalk in same piece image there are the problem of, the detection accuracy of identification of image can be lifted.Both blade construction, long stalk rate can have been detected, rate containing leaf in rate containing stalk and stalk can also be detected in leaf, need not know offal density and leaves density during solution index, programming count, which calculates, various beats food value of leaf figureofmerit.
Description
Technical field
Material detection technique field in being processed the present invention relates to tobacco, more particularly to a kind of beating based on double spectral techniques
Leaf goes stalk quality comprehensive detection device and detection method.
Background technology
Tobacco leaf is made of offal and blade two parts, and the thick and stiff vein of tobacco leaf is known as offal, and weight accounting is about tobacco leaf
25%~30%.Leaf of beating in tobacco threshing redrying technique goes the top priority of stalk process exactly to be allowed by special equipment per a piece of
Blade and the offal separation of tobacco leaf, its blade portions are separated into the piece cigarette that size does not wait, and offal is partially separated into length
Different offal section, to meet follow-up classification processing request.
According to tobacco business standard YC/T146-2010《Tobacco threshing and redrying technological specification》, weigh and beat leaf and go to obstruct quality
Refer mainly to indicate rate containing leaf in rate containing stalk in blade construction, leaf, long stalk rate, stalk.The four indices are sampling detection, and physics is anticipated
Justice is weight accounting, as blade construction refers to large stretch of, middle, the weight accounting of small pieces, fragment, powder each in the sample.Its
Blade of the testing requirements of two indexs of rate containing stalk after beating leaf and removing stalk collects in middle blade construction and leaf samples on conveyer belt
(3000 ± 300) g, by different special mechanical equipments and by manually calculating result；And rate containing leaf in long stalk rate and stalk
The detection of two indexs then requires the offal after beating leaf and removing stalk to collect sampling (1000~1500) g on conveyer belt, then passes through four
Sample is reduced to (80~120) g by point-score, then by manual measurement and calculates result.The detection process of each single item index is all
It is time-consuming and laborious, and index is more single, only one i.e. weight accounting.In its middle period the detection of the rate containing stalk in order to make blade and
Offal therein is completely separated, and blade is all smashed, belongs to destructive detection, causes substantial amounts of tobacco leaf to be lost.
In recent years, with the rapid development of machine vision technique, in tobacco business, lossless detection method is begun one's study to take
Traditional destructive detection method is formed, the situation of wastage of material in detection process is reduced, so as to reduce cost.Then it is various to be based on
The detection means of image method continuously emerges, but the equipment developed at present has two deficiencies, first, the blade construction detected, Ye Zhong
The four indices of rate containing leaf in rate containing stalk, long stalk rate, stalk, are respectively necessary for corresponding four kinds of equipment to complete, do not possess one-machine-multi-function
The advantages of, detection device is invested into higher；Second, rate containing stalk and the existing image of the two indices of rate containing leaf in stalk are known in current leaf
Not lossless inspection technology for detection resultant error is larger, it is impossible to adapts to production requirement very well.
Detection for blade construction and long stalk rate is since detection object is single, because the method is relatively easy：Such as use face
Product ratio.Because for single detection object, no matter using weight ratio, area ratio or volume ratio, the ratio of three is equal
, therefore no matter any statistical method is used, all it is equivalent in theory, because the weight per unit area or list of detection object
Position volume weight is unrelated with its size, this point is approved and uniformly at present in tobacco business.
Situation is just different for the index of rate containing leaf in Ye Zhonghan stalks rate and stalk, and computational methods are relative complex, here
It is related to two kinds of different materials of density：Blade and offal, it is therefore necessary to the shape facility ruler such as area for collecting image method
Reliability that is very little to be converted into weight, then asking weight ratio to improve detection data, preferably meets current tobacco business requirement.
The Chinese invention patent of Application No. 201110213062.7 discloses a kind of Ye Zhonghan based on combination x ray fluoroscopy x
Stalk and the visual recognition detection method of rate containing stalk, the saturating of tobacco leaf is obtained by the combined light source and CCD camera for the tobacco leaf both sides that are placed in
Visible image, then identifies the shape ruler of offal and blade, extraction blade and offal according to characteristics of image designed image Processing Algorithm
Very little feature simultaneously calculates rate containing stalk in leaf.The Chinese invention patent of Application No. 201210475963.8 discloses a kind of based on actively
The infrared imaging detection method containing stalk in the leaf of heating；Its step is similar with 201110213062.7, and difference lies in obtain image
Method and image processing algorithm are different, it utilizes the thermal radiation phenomena of tobacco leaf, by the way that to tobacco leaf, actively heating makes blade and offal
The temperature difference is produced, then image is gathered with infrared thermography and identifies blade and offal with image processing algorithm,
Calculate the rate containing stalk of tobacco leaf.
The Chinese invention patent of Application No. 201310069611.7 is disclosed in a kind of leaf discrete based on high-speed flow
Containing stalk and beat leaf parameter detecting elimination method, discrete mainly by high-speed flow, and the mode of its acquisition fluoroscopy images of tobacco leaf
It is consistent with 201110213062.7, by analyzing the tobacco leaf fluoroscopy images obtained, textural characteristics are extracted, using binary tree
Blade and offal are accurately distinguished, the tobacco leaf containing offal is rejected, while calculates tobacco leaf area, and then acquisition Percentage of large and middle size strips,
Rate containing stalk etc. beats leaf parameter in small pieces rate and leaf.These three methods are required to distinguish blade and offal in same piece image, by mistake
Difference is larger.In addition during rate containing stalk in calculating leaf, it is also necessary to knowing the density of offal and blade could solve, and due to
Different cultivars, grade, the place of production, the density of its blade of the tobacco leaf of moisture content and offal are different, therefore there is no this in industry at present
Class data, are used to lack operability when calculating rate containing stalk in leaf in these processes.
The Chinese invention patent of Application No. 201410302230.3 discloses a kind of leaf based on EO-1 hyperion and is detected containing stalk
Device, emphasis are described the structure and composition of device, but EO-1 hyperion are not further described, do not refer to as
What distinguishes the computational methods of the rate containing stalk in blade and offal and leaf.
The Chinese invention patent of Application No. 201410061575.4 discloses a kind of tobacco leaf rate containing stalk assay method, application
Number a kind of tobacco leaf rate containing stalk measurement device is disclosed for 201420078131.7 Chinese utility model patent, filled by X-ray
Put the fluoroscopy images for obtaining offal and then obtain the area or volume of offal, the acquisition of its tobacco stalk quality there are three kinds of methods：When
The offal area density obtained with prior survey calculation is multiplied by be obtained by the offal area of image acquisition；Second, measured with prior
The offal bulk density being calculated is multiplied by be obtained by the offal volume of image acquisition；Third, penetrated according to the thickness of offal with X
There are correlation between line penetrability：I, I in formula0For X-ray intensity before and after decay, A is rubbing for atom
Your quality, σ accumulate for atomic cross section, and N is constant, ρ is offal density, x for offal thickness, as can be seen from the above equation ray decline
The density for subtracting and being tested offal is multiplied by thickness i.e. ρ x and has certain mathematical relationship.And the attenuation change of ray can be embodied in cigarette
On the gray level image of stalk, the change of gray value is shown as, the corresponding gray value of the bigger pixel of ρ x values is smaller, and ρ x values are smaller
The corresponding gray value of pixel is bigger.The area density of gray scale and offal can be subjected to area using the gray scale and ρ x relationships of the above
Between it is corresponding：Such as [0-30]-P1、[30-60]—P2、[60-90]—P3、[90-120]—P4…[210-255]—P8, P1…P8
It is illustrated respectively in the offal area density in corresponding grey scale section；If that the area in corresponding grey scale section is respectively S1、S2…S8,
Then tobacco stalk quality m=P1×S1+P2×S2+…P8×S8；Tobacco stalk quality again divided by by weighting manner obtain quality of tobacco be
Rate containing stalk in leaf can be tried to achieve.This two patent is disadvantageous in that：First, the acquisition of offal area density and bulk density needs to carry
Preceding independent measurement calculates, and with the measurement process of the rate containing stalk in leaf and asynchronous, process is cumbersome and error is larger；Secondly, penetrated based on X
The tobacco stalk quality computational methods of line attenuation are a bit forced, and it is true that the density of the decay of ray and detected offal is multiplied by the i.e. ρ x of thickness
Real storage is in certain mathematical relationship, i.e., offal gradation of image is with ρ x there are correspondence, but ρ x are not the area density of offal, because
This is similar to tobacco stalk quality m=P1×S1+P2×S2+…P8×S8This computational methods are worthless.
The content of the invention
In view of the deficiencies of the prior art, the present invention provides a kind of leaf of beating based on double spectral techniques and removes stalk quality detection device
And detection method, the present invention are detected using NI Vision Builder for Automated Inspection, using image procossing as core, one-machine-multi-function, can examine at the same time
Multiple indexs such as rate containing leaf in rate containing stalk in blade construction, leaf, long stalk rate, stalk are surveyed, solving existing equipment detection, time-consuming, raw material
The shortcomings of loss is big, detects data feedback not in time, and Testing index is single.
First aspect present invention, there is provided a kind of leaf of beating based on double spectral techniques goes stalk quality detection device, the detection
Device includes laying device 1, positioned at 1 paver, the X-ray detection machine 3 positioned at the lower section of paver 2, position below laying device
Visible detection machine 4 below 3 discharge port of X-ray detection machine, the material-receiving device below 4 discharge port of visible detection machine
6th, rack 5 and switch board 7, the rack 5 are used for integrated installation laying device 1, paver 2, X-ray detection machine 3 and can
See light detection machine 4,5 surrounding of rack is both provided with a cover 5B；Switch board 7 is provided with electric-control system and Upper system.
Further, the laying device 1 includes main body belt feeder 1A, Weighing cell module 1B and limit material roller 1C, its
In, decelerating motor driving is respectively adopted in main body belt feeder 1A and limit material roller 1C, and limit material roller 1C is located at the discharging of main body belt feeder 1A
Mouthful；Paver 2 uses plate-spring type jigging conveyer or excitation type jigging conveyer.
Further, the X-ray detection machine 3 includes main body belt feeder 3A, X-ray apparatus 3B, X-ray camera 3C and X
Ray switch board 3D, wherein, X-ray apparatus 3B and X-ray switch board 3D are located at the top of main body belt feeder 3A, X-ray camera
3C is located at the middle part of main body belt feeder 3A；Six, the periphery face of main body belt feeder 3A is respectively provided with X-ray protection cover board, and protective cover
Plate uses double panel structure of the stereotype as lining；
The visible detection machine 4 includes being provided with belt feeder 4A and the video cabinets 4B of its upper part, video cabinets 4B visible
Light camera 4B-1, camera lens 4B-2, multidimensional regulating platform 4B-3, LED light source 4B-4 and the glass vision panel 4B-5 of camera.
Further, the Weighing cell module 1B sets four sets, and four sets of Weighing cell module 1B are installed on main body
Between the left and right sides and rack 5 of belt feeder 1A；
Four sets of Weighing cell module 1B, a terminal box 5A and weighing instrument 7C that weighs form the rail of complete set
Road formula weighing system, the terminal box 5A that weighs are arranged in rack 5, and load-bearing instrument 7c is arranged on switch board 7；
Display 7A, keyboard and mouse drawer 7B, weighing instrument 7C and various control button 7D are installed on the switch board 7
With disconnecting switch 7E；The switch board 7 is used to control laying device 1, paver 2, X-ray detection machine 3 and visible detection
The working status of machine 4.
Further, the main body belt feeder 3A includes cycloconveyor belt 3A-1, supporting plate 3A-2 and stent 3A-3, wherein,
Cycloconveyor belt 3A-1 levels zone face forms the space for being used for installing X-ray camera 3C, and conveyer belt 3A-1 upper stratas zone face relies on
Supporting plate 3A-2 is supported and is kept horizontality, and stent 3A-3 is used to install X-ray camera 3C.
Further, the X-ray apparatus 3B includes X-ray tube 3B-1, ray collimating channel 3B-2, ray pipe protective cover
3B-3 and cabinet 3B-4, wherein, ray collimating channel 3B-2, ray pipe protective cover 3B-3, cabinet 3B-4 peripheries cover board use lead
Double panel structure of the plate as lining, X-ray camera 3C are located at the underface of X-ray tube 3B-1 and ray collimating channel 3B-2, X
Ray switch board 3D is close to X-ray apparatus 3B, for placing X-ray controller 3D-1 and water cooling plant 3D-2.
Second aspect of the present invention, there is provided using the detection beaten leaf and remove stalk quality detection device based on double spectral techniques
Method, double spectrum are respectively visible ray and X-ray, and wherein visible ray is used to gather tobacco leaf image, and X-ray is used to gather cigarette
Obstruct image.
Further, the detection method mainly includes the following steps：
The first step, stone are weighed：When being detected for rate containing stalk in blade construction or leaf, the blade after beating leaf and going to obstruct collects
3000 ± 300g is sampled on conveyer belt；When being detected for rate containing leaf in long stalk rate or stalk, the offal after beating leaf and removing stalk collects defeated
Send and take 1000~1500g of sampling, according to online or offline service condition, make tobacco sample uniform by artificial or upstream equipment
It is paved with laying device (1), then equipment obtains sample quality automatically in a manner of static weighing；
Second step, uniform feeding：Detection device is started by switch board 7, material passed sequentially through laying device 1, paved
Machine 2, X-ray detection machine 3, visible detection machine 4 and material-receiving device 6；
3rd step, gathers image：(1) it is Polaroid：When detecting blade construction or long stalk rate, X-ray tube does not work, and only makes
Material image is gathered with Visible Light Camera；(2) secondary imaging：In detecting rate containing stalk in leaf or obstructing during rate containing leaf, X-ray plumber
Make, gather offal image first by X-ray camera, then gather tobacco leaf image using Visible Light Camera；
4th step, image procossing：The material original image collected after treatment, is obtained by corresponding image algorithm
Area, length, width and the girth of every a piece of tobacco leaf and each offal, are obtained by calculation blade construction, long stalk rate, Ye Zhong
Rate containing leaf in rate containing stalk and stalk.
Further, in detecting rate containing stalk in leaf or obstructing during rate containing leaf, when material is by main body belt feeder 3A, X-ray
Pipe 3B-1 works, and X-ray is under the targeting of ray collimating channel 3B-2, vertically downward through material and cycloconveyor belt
3A-1, clearly offal image is got by the X-ray camera 3C between supporting plate 3A-2 and stent 3A-3；X-ray controls
Cabinet 3D is controlled whether the work of X-ray tube 3B-1 by X-ray controller 3D-1 close to X-ray apparatus 3B and is adjusted X-ray
Intensity, water cooling plant 3D-2 are used for the cooling of X-ray tube 3B-1 and X-ray controller 3D-1；When material continue move ahead and from
Open the moment of belt feeder 4A, Visible Light Camera 4B-1 is in camera lens 4B-2, multidimensional regulating platform 4B-3, LED light source 4B- in video cabinets 4B
4 cooperation lower tracer collects clearly tobacco leaf image through glass vision panel 4B-5.
Further, in the blade construction, long stalk rate, leaf rate containing stalk and stalk in the rate containing leaf calculating process it is as follows：
(1) blade construction：The size of the every a piece of tobacco leaf obtained according to detection, with reference to professional museum, by sample
Product tobacco classification and the gross area S for calculating sample tobacco leaf, while count the gross area S per a kind of tobacco leafi, you can obtain blade knot
Structure
(2) long stalk rate：The length scale of each offal obtained according to detection, with reference to professional museum, counts
The area summation S of offal of the offal length more than 20mm1And the area summation S of all offal samples, you can obtain long stalk rate
(3) in leaf rate containing stalk and stalk in rate containing leaf：
The statistics of the rate containing leaf, which calculates, in Ye Zhonghan stalks rate and stalk comprises the steps of：(a) two parts are obtained automatically using device
Sample the weight M of sample1、M2And blade and offal area S1 leaf、S1 stalk、S2 leaves、S2 stalks, calculate the area density of blade and offal
Ratio K；If the area density of leaf is ρLeaf, the area density of stalk is ρStalk, make ρLeaf=K ρStalk, then have：
S1 leafρLeaf+S1 stalkρStalk=M1 (1)
S2 leavesρLeaf+S2 stalksρStalk=M2 (2)
ρLeaf=K ρStalk (3)
Three formula simultaneous can solve more than：
(b) weight of blade is set as MLeaf, offal weight be MStalk；Ye Zhonghan stalks rate is Y, and rate containing leaf is G in stalk, then by referring to
Calibration justice has：
Wherein SCigaretteObtained by Visible Light Camera, SStalkObtained by X-ray, SLeaf=SCigarette‐SStalk, K is by the acquisition of (4) formula, SCigarette、SStalk、SLeaf
It is the detected value of n-th part of sample (n >=2)；
(c) Automatic Optimal of K values：Often tested twice, being calculated using the basic data of test and above-mentioned (4) formula can be with
Obtain a new K value；So 2n times test can obtain n K value, K1... Kn‐1, Kn；ThenHere KIt is close
Real leaf stalk area density ratio.
Detection device provided by the invention sets two sets of image collecting devices, and two kinds of light of visible ray and X-ray are respectively adopted
Spectrum, wherein visible ray are used to gather tobacco leaf image, and X-ray is used to gather offal image, by corresponding image algorithm respectively
To tobacco leaf area and offal area, offal length, and then obtain rate containing leaf four in rate containing stalk in blade construction, leaf, long stalk rate, stalk
Item index, wherein blade construction and long stalk rate can be obtained only with visual light imaging technology, and be contained in leaf in rate containing stalk and stalk
The detection of leaf rate then needs to use visual light imaging technology and x-ray imaging technology at the same time；The present invention solves nothing during index
It need to know offal density and leaves density, the parameters such as the weight of sample, area, length be obtained automatically by equipment, so that automatically
Calculate and various beat food value of leaf figureofmerit.And often tested twice, basic data and above-mentioned (4) formula meter using test
Calculation can obtain a new K value (ratio of the area density of blade and offal)；So 2n times test can obtain n K value,
K1... Kn-1, Kn；ThenHere KObstruct area density ratio close to real leaf, detected value is more accurate.
Compared with prior art, the invention has the advantages that：The present invention uses visible ray and x-ray imaging technology
And corresponding image algorithm respectively obtains tobacco leaf area and offal area, offal length, avoids and splits in same piece image
When leaf, stalk there are the problem of, the detection accuracy of identification of image can be lifted.And a tractor serves several purposes, can both detect blade construction, length
Stalk rate, rate containing leaf during rate containing stalk in leaf can also be detected and obstructed.Apparatus structure is compact, integrated level is high, and floor space is small, both can be with
It is placed on metering test room and is used for offline inspection, can also installs in the production line and be used to examine online in the form of detecting side line
Survey, since detection limit is minimum, coordinate certain working time, therefore the discrete effect of material is good, the readily identified processing of image, inspection
It is higher to survey precision, high plus automation, the level of informatization, general effect is better than traditional detection method.
Brief description of the drawings
Fig. 1 is the structure chart beating leaf remove stalk quality detection device of the present invention based on double spectral techniques；
Marked in figure：1- laying devices, 2- pavers, 3-X ray detection machines, 4- visible detections machine, 5- racks, 6- connect
Expect device and 7- switch boards.
Embodiment
Technical scheme is described in further details with reference to specific embodiment, but the present invention does not limit to
In following technical scheme.
1 detection device of embodiment
As shown in Figure 1, the detection device includes laying device 1, the paver 2 positioned at laying device lower section 1, positioned at stand
The X-ray detection machine 3 of the lower section of paving machine 2, the visible detection machine 4 positioned at the outlet of X-ray detection machine 3 lower section, examine positioned at visible ray
Material-receiving device 6, rack 5 and the switch board 7 of the outlet of survey machine 4 lower section；
Laying device 1 includes main body belt feeder 1A, Weighing cell module 1B and limit material roller 1C, main body belt feeder 1A and limit
Decelerating motor driving is respectively adopted in material roller 1C.Four sets of Weighing cell module 1B installed in main body belt feeder 1A left and right lateral wall with
Between rack 5.Limit material roller 1C is located at the discharge port of main body belt feeder 1A.
Paver 2 can use plate-spring type jigging conveyer or excitation type jigging conveyer.
X-ray detection machine 3 includes main body belt feeder 3A, X-ray apparatus 3B, X-ray camera 3C, X-ray switch board 3D.X
X-ray apparatus 3B and X-ray switch board 3D is located at the top of main body belt feeder 3A, and X-ray camera 3C is located at main body belt feeder 3A's
Middle part：The space that cycloconveyor belt 3A-1 levels zone face is formed.Main body belt feeder 3A six, periphery face (upper and lower, left and right,
It is forward and backward) X-ray protection cover board is respectively provided with, and protective cover plate is the double panel structure using stereotype as lining.Conveyer belt
3A-1 upper stratas zone face supports by supporting plate 3A-2 and keeps horizontality, and stent 3A-3 is used to install X-ray camera 3C, for protection
X-ray, equally uses double panel structure of the stereotype as lining, is fixed on main body belt feeder 3A and is close to supporting plate 3A-2.X
X-ray apparatus 3B includes X-ray tube 3B-1, ray collimating channel 3B-2, ray pipe protective cover 3B-3, cabinet 3B-4, and ray collimation is logical
Road 3B-2, ray pipe protective cover 3B-3, cabinet 3B-4 peripheries cover board use double panel structure of the stereotype as lining, make cabinet
Actual double-deck X-ray protection measure is formed between X-ray tube 3B-1 and environment in 3B-4.X-ray camera 3C is located at X-ray
The underface of pipe 3B-1 and ray collimating channel 3B-2.X-ray switch board 3D is close to X-ray apparatus 3B, for placing X-ray control
Device 3D-1 and water cooling plant 3D-2 processed.
Visible detection machine 4 includes being provided with visible ray phase in belt feeder 4A and the video cabinets 4B of its upper part, video cabinets 4B
Machine 4B-1, camera lens 4B-2, the multidimensional regulating platform 4B-3 of camera and LED light source 4B-4, glass vision panel 4B-5.
Rack 5 is mainly used for integrated installation laying device 1, paver 2, X-ray detection machine 3, visible detection machine 4 and claims
Reclosing wire box 5A, its surrounding (left, right, front and rear) are both provided with a cover 5B, both play the role of security protection, while also ensure
The aesthetics of equipment entirety.
Material-receiving device 6 is used to collect the material after detection, can be hopper or conveying according to offline or online different operating modes
Equipment.
Switch board 7 is provided with electric-control system and Upper system, and display 7A, keyboard and mouse drawer are provided with its door-plate
7B, weighing instrument 7C and various control button 7D and disconnecting switch 7E.
Four sets of Weighing cell module 1B, the terminal box 5A that weighs, a weighing instrument 7C form the rail of complete set
Road formula weighing system.
2 detection method of embodiment
The first step, stone are weighed：Tobacco business standard sample is pressed first, is detected for rate containing stalk in blade construction or leaf
When, the blade after beating leaf and removing stalk collects sampling (3000 ± 300) g on conveyer belt；Detected for rate containing leaf in long stalk rate or stalk
When, the offal after beating leaf and removing stalk collects sampling (1000~1500) g on conveyer belt., can according to online or offline service condition
By artificial or upstream equipment make sample be uniformly paved with laying device 1 must on, then by rail mounted weighing system with static state
Weighting manner obtains sample quality automatically.
Second step, uniform feeding：By 7 starting device of switch board, material is set to pass sequentially through laying device 1, paver 2, X
Ray detection machine 3, visible detection machine 4, material-receiving device 6, whole process continue 6min~7min.The setting of limit material roller 1C can be with
Ensure the uniformity of whole feeding procedure.
3rd step, gathers image：(1) it is Polaroid：During for detecting blade construction or long stalk rate, X-ray tube 3B-1 is not
Work, material image is gathered using only Visible Light Camera 4B-1；(2) secondary imaging：Contain for detecting in leaf in rate containing stalk or stalk
During leaf rate, when material is by main body belt feeder 3A, X-ray tube 3B-1 work, targeting of the X-ray in ray collimating channel 3B-2
Under effect, vertically downward through material and cycloconveyor belt 3A-1, by the X-ray phase between supporting plate 3A-2 and stent 3A-3
Machine 3C gets clearly offal image.X-ray apparatus 3B has carried out Double-protection measure for X-ray, and first layer protection is arranged
It is cabinet 3B-4 to apply as ray collimating channel 3B-2 and ray pipe protective cover 3B-3, second layer safeguard procedures.X-ray switch board 3D is tight
Adjacent X-ray apparatus 3B, is controlled whether the work of X-ray tube 3B-1 by X-ray controller 3D-1 and adjusts the intensity of X-ray,
Water cooling plant 3D-2 is used for the cooling of X-ray tube 3B-1 and X-ray controller 3D-1.When material continues to move ahead and is leaving belt
The moment of machine 4A, Visible Light Camera 4B-1 matches somebody with somebody in camera lens 4B-2, multidimensional regulating platform 4B-3, LED light source 4B-4 in video cabinets 4B
Close lower tracer and collect clearly tobacco leaf image through glass vision panel 4B-5.
4th step, image procossing：The material original image collected is after Upper system is handled, by Upper system
Corresponding image algorithm obtains the often physical dimension such as the area of a piece of tobacco leaf and each offal, length, width, girth.
5th step, the statistics that hit the target in Upper system calculate, and with diversified forms such as data, chart, curves
Performance：1st, blade construction：The size of the every a piece of tobacco leaf obtained according to detection, with reference to professional museum, by sample cigarette
Leaf classifies and calculates the gross area S of sample tobacco leaf, while counts the gross area S per a kind of tobacco leafi, you can obtain blade construction
2nd, long stalk rate：The length scale of each offal obtained according to detection, with reference to professional museum, counts smoke
Obstruct the area summation S of offal of the length more than 20mm1And the area summation S of all offal samples, you can obtain long stalk rate
3rd, in leaf rate containing stalk and stalk in rate containing leaf：
The statistics of the rate containing leaf, which calculates, in Ye Zhonghan stalks rate and stalk comprises the steps of：
(a) the weight M of two parts of sampling samples is obtained automatically using device1、M2And blade and offal area S1 leaf、S1 stalk、
S2 leaves、S2 stalks, calculate the ratio K of the area density of blade and offal..If the area density of leaf is ρLeaf, the area density of stalk is ρStalk,
Make ρLeaf=K ρStalk.Then have：
S1 leafρLeaf+S1 stalkρStalk=M1 (1)
S2 leavesρLeaf+S2 stalksρStalk=M2 (2)
ρLeaf=K ρStalk (3)
Three formula simultaneous can solve more than：
(b) weight of blade is set as MLeaf, offal weight be MStalk；Ye Zhonghan stalks rate is Y, and rate containing leaf is G in stalk, then by referring to
Calibration justice has：
Wherein SCigaretteObtained by Visible Light Camera, SStalkObtained by X-ray, SLeaf=SCigarette‐SStalk, K is by the acquisition of (4) formula, SCigarette、SStalk、SLeaf
It is the detected value of n-th part of sample (n >=2).
(c) Automatic Optimal of K values：Often tested twice, being calculated using the basic data of test and above-mentioned (4) formula can be with
Obtain a new K value.So 2n times test can obtain n K value, K1... Kn-1, Kn；ThenHere KConnect
The area density ratio of nearly real leaf stalk, rate containing stalk and stalk in the blade construction obtained using above-mentioned calculation formula, long stalk rate, leaf
In the rate containing leaf test value and actual value error within ± 5%.
Switch board 7 is provided with electric-control system and Upper system, and display 7A, keyboard and mouse drawer are provided with its door-plate
7B, weighing instrument 7C and various control button 7D and disconnecting switch 7E.Electric-control system be used for control device operation and with
The communication of position system, Upper system include hardware and the software systems such as industrial personal computer, display, interchanger, image pick-up card, tool
The functions such as standby Image Acquisition, image procossing, data analysis, result calculating.
As described above, it is only the specific embodiment of the present invention, it is impossible to the scope of the present invention is limited with this, i.e., according to of the invention special
The equivalent variations and modification that profit application protection domain is made, all should still belong to the scope that the present invention covers.
Claims (10)
1. a kind of leaf of beating based on double spectral techniques removes stalk quality detection device, it is characterised in that the detection device includes paving
Expect device (1), positioned at the paver (2) of (1), the X-ray detection machine (3) below paver (2), position below laying device
Visible detection machine (4) below X-ray detection machine (3) discharge port, connecing below visible detection machine (4) discharge port
Expect device (6), rack (5) and switch board (7), the rack (5) is used for integrated installation laying device (1), paver (2), X
Ray detection machine (3) and visible detection machine (4), rack (5) surrounding are both provided with a cover (5B)；Switch board (7) is provided with
Electric-control system and Upper system.
2. the leaf of beating according to claim 1 based on double spectral techniques removes stalk quality detection device, it is characterised in that described
Laying device (1) includes main body belt feeder (1A), Weighing cell module (1B) and limit material roller (1C), wherein, main body belt feeder
Decelerating motor driving is respectively adopted in (1A) and limit material roller (1C), and limit material roller (1C) is located at the discharge port of main body belt feeder (1A)；Stand
Paving machine (2) uses plate-spring type jigging conveyer or excitation type jigging conveyer.
3. the leaf of beating according to claim 1 based on double spectral techniques removes stalk quality detection device, it is characterised in that described
X-ray detection machine (3) includes main body belt feeder (3A), X-ray apparatus (3B), X-ray camera (3C) and X-ray switch board
(3D), wherein, X-ray apparatus (3B) and X-ray switch board (3D) are located at the top of main body belt feeder (3A), X-ray camera
(3C) is located at the middle part of main body belt feeder (3A)；Six, the periphery face of main body belt feeder (3A) is respectively provided with X-ray protection cover board, and
Protective cover plate uses double panel structure of the stereotype as lining；
The visible detection machine (4) includes belt feeder (4A) and the video cabinets (4B) of its upper part, is provided with video cabinets (4B)
Visible Light Camera (4B-1), camera lens (4B-2), the multidimensional regulating platform (4B-3) of camera, LED light source (4B-4) and glass vision panel
(4B‐5)。
4. the leaf of beating according to claim 2 based on double spectral techniques removes stalk quality detection device, it is characterised in that described
Weighing cell module (1B) sets four sets, and four sets of Weighing cell modules (1B) are installed on the left and right sides of main body belt feeder (1A)
Between rack (5)；
Four sets of Weighing cell modules (1B), a terminal box of weighing (5A) and a weighing instrument (7C) form complete set
Rail mounted weighing system, the terminal box of weighing (5A) are arranged in rack (5), and load-bearing instrument (7c) is arranged on switch board (7)
On；
Display (7A), keyboard and mouse drawer (7B), weighing instrument (7C) and various controls are installed on the switch board (7) to press
Button (7D) and disconnecting switch (7E)；The switch board (7) is used to control laying device (1), paver (2), X-ray detection machine
(3) and visible detection machine (4) working status.
5. the leaf of beating according to claim 3 based on double spectral techniques removes stalk quality detection device, it is characterised in that described
Main body belt feeder (3A) includes cycloconveyor belt (3A-1), supporting plate (3A-2) and stent (3A-3), wherein, cycloconveyor belt (3A-
1) levels zone face forms the space for being used for installing X-ray camera (3C), and conveyer belt (3A-1) upper strata zone face relies on supporting plate (3A-
2) support and keep horizontality, stent (3A-3) is used to install X-ray camera (3C).
6. the leaf of beating based on double spectral techniques removes stalk quality detection device as claimed in claim 3, it is characterised in that the X
X-ray apparatus (3B) includes X-ray tube (3B-1), ray collimating channel (3B-2), ray pipe protective cover (3B-3) and cabinet (3B-
4), wherein, ray collimating channel (3B-2), ray pipe protective cover (3B-3), cabinet (3B-4) periphery cover board use stereotype conduct
The double panel structure of lining, X-ray camera (3C) are located at the underface of X-ray tube (3B-1) and ray collimating channel (3B-2), X
Ray switch board (3D) is close to X-ray apparatus (3B), for placing X-ray controller (3D-1) and water cooling plant (3D-2).
7. a kind of go obstructing quality detection device using such as the leaf of beating based on double spectral techniques as described in claim 1~6 is any
Detection method, it is characterised in that double spectrum are respectively visible ray and X-ray, and wherein visible ray is used to gather tobacco leaf image,
X-ray is used to gather offal image.
8. the leaf of beating according to claim 7 based on double spectral techniques removes stalk quality determining method, it is characterised in that described
Detection method mainly includes the following steps：
The first step, stone are weighed：When being detected for rate containing stalk in blade construction or leaf, the blade after beating leaf and going to obstruct collects conveying
Take 3000 ± 300g of sampling；When being detected for rate containing leaf in long stalk rate or stalk, the offal after beating leaf and going to obstruct collects conveyer belt
1000~1500g of upper sampling, according to online or offline service condition, makes tobacco sample uniformly be paved with by artificial or upstream equipment
On laying device (1), then equipment obtains sample quality automatically in a manner of static weighing；
Second step, uniform feeding：Detection device is started by switch board (7), material passed sequentially through laying device (1), paved
Machine (2), X-ray detection machine (3), visible detection machine (4) and material-receiving device (6)；
3rd step, gathers image：(1) it is Polaroid：Detect blade construction or during long stalk rate, X-ray tube does not work, using only can
See that light camera gathers material image；(2) secondary imaging：In detecting rate containing stalk in leaf or obstructing during rate containing leaf, X-ray tube work is first
First using X-ray camera collection offal image, then tobacco leaf image is gathered using Visible Light Camera；
4th step, image procossing：The material original image collected after treatment, is obtained each by corresponding image algorithm
The area of piece tobacco leaf and each offal, length, width and girth, are obtained by calculation in blade construction, long stalk rate, leaf containing stalk
Rate containing leaf in rate and stalk.
9. a kind of leaf of beating based on double spectral techniques according to claim 8 removes stalk quality determining method, it is characterised in that
In detecting rate containing stalk in leaf or obstructing during rate containing leaf, when material is by main body belt feeder (3A), X-ray tube (3B-1) work, X is penetrated
Line is under the targeting of ray collimating channel (3B-2), vertically downward through material and cycloconveyor belt (3A-1), by positioned at
X-ray camera (3C) between supporting plate (3A-2) and stent (3A-3) gets clearly offal image；X-ray switch board (3D)
Close to X-ray apparatus (3B), controlled by X-ray controller (3D-1) whether the work of X-ray tube (3B-1) and adjust X-ray
Intensity, water cooling plant (3D-2) is used for the cooling of X-ray tube (3B-1) and X-ray controller (3D-1)；Before material continuation
Row is simultaneously leaving the moment of belt feeder (4A), and video cabinets (4B) interior Visible Light Camera (4B-1) is adjusted in camera lens (4B-2), multidimensional
Platform (4B-3), the cooperation lower tracer of LED light source (4B-4) collect clearly tobacco leaf image through glass vision panel (4B-5).
10. a kind of leaf of beating based on double spectral techniques according to claim 8 removes stalk quality determining method, its feature exists
In, in the blade construction, long stalk rate, leaf rate containing stalk and stalk in the rate containing leaf calculating process it is as follows：
(1) blade construction：The size of the every a piece of tobacco leaf obtained according to detection, with reference to professional museum, by sample cigarette
Leaf classifies and calculates the gross area S of sample tobacco leaf, while counts the gross area S per a kind of tobacco leafi, you can obtain blade construction
<mrow>
<msub>
<mi>P</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<mfrac>
<msub>
<mi>S</mi>
<mi>i</mi>
</msub>
<mi>S</mi>
</mfrac>
<mo>&times;</mo>
<mn>100</mn>
<mi>%</mi>
<mo>;</mo>
</mrow>
(2) long stalk rate：The length scale of each offal obtained according to detection, with reference to professional museum, counts offal
The area summation S of offal of the length more than 20mm1And the area summation S of all offal samples, you can obtain long stalk rate
<mrow>
<mi>X</mi>
<mo>=</mo>
<mfrac>
<msub>
<mi>S</mi>
<mn>1</mn>
</msub>
<mi>S</mi>
</mfrac>
<mo>&times;</mo>
<mn>100</mn>
<mi>%</mi>
<mo>;</mo>
</mrow>
(3) in leaf rate containing stalk and stalk in rate containing leaf：
The statistics of the rate containing leaf, which calculates, in Ye Zhonghan stalks rate and stalk comprises the steps of：(a) two parts of samplings are obtained automatically using device
The weight M of sample1、M2And blade and offal area S1 leaf、S1 stalk、S2 leaves、S2 stalks, calculate the ratio of the area density of blade and offal
K；If the area density of leaf is ρLeaf, the area density of stalk is ρStalk, make ρLeaf=K ρStalk, then have：
S1 leafρLeaf+S1 stalkρStalk=M1 (1)
S2 leavesρLeaf+S2 stalksρStalk=M2 (2)
ρLeaf=K ρStalk (3)
Three formula simultaneous can solve more than：
(b) weight of blade is set as MLeaf, offal weight be MStalk；Ye Zhonghan stalks rate is Y, and rate containing leaf is G in stalk, then determines by index
Justice has：
Wherein SCigaretteObtained by Visible Light Camera, SStalkObtained by X-ray, SLeaf=SCigarette‐SStalk, K is by the acquisition of (4) formula, SCigarette、SStalk、SLeafIt is
The detected value of n-th part of sample (n >=2)；
(c) Automatic Optimal of K values：Often tested twice, calculate and can obtain using the basic data of test and above-mentioned (4) formula
One new K value；So 2n times test can obtain n K value, K1... Kn‐1, Kn；ThenHere KClose to very
Real leaf stalk area density ratio.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711368697.8A CN107991303B (en) | 2017-12-18 | Threshing and stem removing quality detection device and detection method based on double-spectrum technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711368697.8A CN107991303B (en) | 2017-12-18 | Threshing and stem removing quality detection device and detection method based on double-spectrum technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107991303A true CN107991303A (en) | 2018-05-04 |
| CN107991303B CN107991303B (en) | 2024-04-26 |
Family
ID=
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110930381A (en) * | 2019-11-19 | 2020-03-27 | 南京大树智能科技股份有限公司 | Tobacco flake shape determination method for improving production quality of fine cigarettes |
| CN111307805A (en) * | 2020-03-20 | 2020-06-19 | 湖南烟叶复烤有限公司郴州复烤厂 | Threshing quality detection device and method based on visual feature fusion |
| CN111948104A (en) * | 2020-06-29 | 2020-11-17 | 中国烟草总公司郑州烟草研究院 | Stem granularity detection and classification control method |
| CN113390799A (en) * | 2021-06-24 | 2021-09-14 | 中国烟草总公司郑州烟草研究院 | Method for identifying and detecting stems in tobacco leaves |
| CN113624147A (en) * | 2021-09-27 | 2021-11-09 | 中国烟草总公司郑州烟草研究院 | Nondestructive detection system and method for thickness and density of tobacco leaves |
| CN114062366A (en) * | 2021-11-29 | 2022-02-18 | 湖北中烟工业有限责任公司 | Tobacco shred production wind-selection stem-removing quality on-line detection method and system |
| CN114062366B (en) * | 2021-11-29 | 2024-04-19 | 湖北中烟工业有限责任公司 | Online detection method and system for winnowing stem-removing quality in tobacco shred production |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102339385A (en) * | 2011-07-28 | 2012-02-01 | 南京焦耳科技有限责任公司 | Combined light perspective based visual recognition detection method of stems and stem ratios in leaves |
| CN102359963A (en) * | 2011-07-14 | 2012-02-22 | 红塔烟草(集团)有限责任公司 | Method for measuring rate of long tobacco stalks by image analysis process |
| US20150131090A1 (en) * | 2012-04-20 | 2015-05-14 | Office Color Science Co., Ltd. | Multi-angle spectral imaging measurement method and apparatus |
| CN207557127U (en) * | 2017-12-18 | 2018-06-29 | 云南烟叶复烤有限责任公司 | A kind of leaf of beating based on double spectral techniques removes stalk quality detection device |
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102359963A (en) * | 2011-07-14 | 2012-02-22 | 红塔烟草(集团)有限责任公司 | Method for measuring rate of long tobacco stalks by image analysis process |
| CN102339385A (en) * | 2011-07-28 | 2012-02-01 | 南京焦耳科技有限责任公司 | Combined light perspective based visual recognition detection method of stems and stem ratios in leaves |
| US20150131090A1 (en) * | 2012-04-20 | 2015-05-14 | Office Color Science Co., Ltd. | Multi-angle spectral imaging measurement method and apparatus |
| CN207557127U (en) * | 2017-12-18 | 2018-06-29 | 云南烟叶复烤有限责任公司 | A kind of leaf of beating based on double spectral techniques removes stalk quality detection device |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110930381A (en) * | 2019-11-19 | 2020-03-27 | 南京大树智能科技股份有限公司 | Tobacco flake shape determination method for improving production quality of fine cigarettes |
| CN111307805A (en) * | 2020-03-20 | 2020-06-19 | 湖南烟叶复烤有限公司郴州复烤厂 | Threshing quality detection device and method based on visual feature fusion |
| CN111948104A (en) * | 2020-06-29 | 2020-11-17 | 中国烟草总公司郑州烟草研究院 | Stem granularity detection and classification control method |
| CN113390799A (en) * | 2021-06-24 | 2021-09-14 | 中国烟草总公司郑州烟草研究院 | Method for identifying and detecting stems in tobacco leaves |
| CN113390799B (en) * | 2021-06-24 | 2023-06-27 | 中国烟草总公司郑州烟草研究院 | Method for identifying and detecting stems in tobacco leaves |
| CN113624147A (en) * | 2021-09-27 | 2021-11-09 | 中国烟草总公司郑州烟草研究院 | Nondestructive detection system and method for thickness and density of tobacco leaves |
| CN113624147B (en) * | 2021-09-27 | 2023-11-17 | 中国烟草总公司郑州烟草研究院 | Nondestructive testing system and method for thickness and density of tobacco leaves |
| CN114062366A (en) * | 2021-11-29 | 2022-02-18 | 湖北中烟工业有限责任公司 | Tobacco shred production wind-selection stem-removing quality on-line detection method and system |
| CN114062366B (en) * | 2021-11-29 | 2024-04-19 | 湖北中烟工业有限责任公司 | Online detection method and system for winnowing stem-removing quality in tobacco shred production |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Gomes Junior et al. | Automated image analysis of seedlings for vigor evaluation of common bean seeds | |
| CN102359963B (en) | Method for measuring rate of long tobacco stalks by image analysis process | |
| US8935881B2 (en) | Method and device for evaluating germination properties of plant seeds | |
| CN103822935B (en) | The quick analytic instrument of heavy metal cadmium and analytical approach in a kind of non-destructive determination food | |
| CN102914620A (en) | Determination method for ration of reconstituted tobacco finished product | |
| CN105973915A (en) | Grain water content and volume-weight automatic detection method | |
| Marschalek et al. | Image-Rice Grain Scanner: a three-dimensional fully automated assessment of grain size and quality traits | |
| Lohumi et al. | Nondestructive estimation of lean meat yield of South Korean pig carcasses using machine vision technique | |
| CN207557127U (en) | A kind of leaf of beating based on double spectral techniques removes stalk quality detection device | |
| CN107991303A (en) | A kind of leaf of beating based on double spectral techniques goes stalk quality detection device and detection method | |
| WO2021174612A1 (en) | Device and methods for measuring long stem content in tobacco stem | |
| JP2019105451A (en) | Cancer inspection with urine in which urine specimen sampling time is registered | |
| Herrera et al. | Strategies to identify genetic diversity in root traits | |
| CN207396258U (en) | A kind of corn seed cleanliness analytical equipment | |
| CN107316131A (en) | A kind of electric power meter mounting process quality detecting system based on image recognition | |
| CN107655852A (en) | The near infrared spectrum quick determination method of essential nutrient in baby formula milk powder | |
| Dengyu et al. | Phenotype-based robotic screening platform for leafy plant breeding | |
| US20200394580A1 (en) | Yield monitoring systems and methods | |
| CN111504927A (en) | Efficient and stable atomic absorption spectrometer for food detection and control method thereof | |
| CN108240987A (en) | A kind of paddy ranking equipment | |
| CN107991303B (en) | Threshing and stem removing quality detection device and detection method based on double-spectrum technology | |
| CN205538538U (en) | Papermaking method reconstituted tobacco product ration spot test appearance | |
| Erasmus et al. | Optimising the determination of maize endosperm vitreousness by a rapid non‐destructive image analysis technique | |
| CN107389703A (en) | One kind beats the online photoelectric detection system of leaf index and detection method | |
| CN208727939U (en) | The vertical automatic assay system of grain |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |