CN104198457B - Cut tobacco component recognition method based on spectral imaging technology - Google Patents
Cut tobacco component recognition method based on spectral imaging technology Download PDFInfo
- Publication number
- CN104198457B CN104198457B CN201410491816.9A CN201410491816A CN104198457B CN 104198457 B CN104198457 B CN 104198457B CN 201410491816 A CN201410491816 A CN 201410491816A CN 104198457 B CN104198457 B CN 104198457B
- Authority
- CN
- China
- Prior art keywords
- tobacco shred
- tobacco
- image
- measured
- shred
- 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
Links
Landscapes
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
- Manufacture Of Tobacco Products (AREA)
Abstract
The invention discloses a cut tobacco component recognition method based on a spectral imaging technology. Differences among different components of cut tobacco are used, the spectral imaging technology is based, under the irradiation of a specified excitation light source, a spectral imaging system is used for acquiring an image formed by fluorescence irradiated by the cut tobacco, and the cut tobacco with different components is recognized according to characteristic differences presented by the cut tobacco with the different components on the fluorescence image, so that automatic cut tobacco determination and recognition can be finished rapidly and accurately, the determination efficiency and the determination accuracy are greatly improved, and the labor intensity of workers is reduced. Meanwhile, no chemical reagent is involved, and harm to the physical health of operators cannot be caused.
Description
Technical field
The present invention relates to a kind of tobacco shred component recognition methodss, more particularly, to a kind of tobacco shred component based on spectral imaging technology
Recognition methodss.
Background technology
Cigarette composition design is basis and the core of cigarette enterprise product design.Tobacco shred blending link in production of cigarettes
In, the component such as cut tobacco, stem, expansive cut tobacco, reconstituted tobacco silk mix dosage to Medicated cigarette physical index, flue gas characteristic and sense organ matter
There is different degrees of impact in amount.Therefore, rapidly and accurately determine ratio in tobacco shred for each component, to examination formula design
Target, stablize tobacco shred hybrid technique quality and homogeneity produce significant.
Because the feature of detection object is complicated and is related to correlation technique bottleneck, the mensure of tobacco shred constituent still relies on
Hand-sorting and artificial interpretation, the tobacco shred component recognition methodss step being usually used at present is as follows：Artificial cognition goes out tobacco shred first
In each component, then pass through hand-sorting and specific solvent and each component screened one by one, calculating of finally each weighing
Go out cut tobacco, stem, reconstituted tobacco silk, the ratio of each composition of expansive cut tobacco.Existing tobacco shred component recognition methodss poor operability,
Time-consuming, workload is huge it is difficult to be applied to batch detection, and hardly possible has adapted to the detection modernizing for its measurement efficiency and precision
Demand and the requirement of high-quality production of cigarettes.Additionally, the use of organic solvent also increases the protection difficulty in experimentation, no
Healthy beneficial to reviewer.
Content of the invention
It is an object of the invention to provide a kind of tobacco shred component recognition methodss based on spectral imaging technology, can be according to difference
The feature difference that the tobacco shred of component shows on fluoroscopic image carries out the identification of different component tobacco shred, finally realizes tobacco shred each group
Divide and carry out quick, accurate, automatic assay, improve determination efficiency and accuracy, reduce intensity of workers.
The present invention adopts following technical proposals：
A kind of tobacco shred component recognition methodss based on spectral imaging technology, comprise the following steps：
A：Respectively by a number of cut tobacco, stem, expansive cut tobacco with reconstituted tobacco silk sample is smooth non-overlapping puts
On Image-capturing platform；
B：Open excitation source to be irradiated, different cigarettes are gathered successively with reference to image capture software by spectrum imaging system
The fluoroscopic image of silk component；
C：Using image processing and analyzing system, the fluoroscopic image of tobacco shred is carried out with pretreatment, remove the interference in image and make an uproar
Sound；
D：Obtain the spectrum picture feature of all types of tobacco shred components using image processing and analyzing system respectively, then according to light
The characteristic amount of spectrum box counting algorithm dissimilar tobacco shred component；
E：Using image processing and analyzing system, property data base is set up according to the characteristic amount of all types of tobacco shred components；
F：By tobacco shred to be measured pass through spread out separation system smooth non-overlapping be placed on Image-capturing platform, using spectrum
Imaging system combines the fluoroscopic image that image capture software gathers tobacco shred to be measured；
G：Using image processing and analyzing system, the fluoroscopic image of tobacco shred to be measured is carried out with pretreatment, remove tobacco shred image to be measured
In interference and noise；
H：Calculate the characteristic number of every tobacco shred to be measured in tobacco shred fluoroscopic image to be measured by image processing and analyzing system respectively
According to amount, and carry out relatedness computation with the characteristic amount of all types of tobacco shred components in the property data base set up in step E,
Then tobacco shred to be measured is analyzed identify according to relatedness computation result；
I：Image processing and analyzing system will be analyzed recognition result and send to sorting system, by sorting system tobacco shred is carried out by
Class sorts；
J：Weigh the quality of each component tobacco shred being sorted out by sorting system respectively, and calculate the ratio of all types of tobacco shreds.
In described step B and step F, the fluoroscopic image being collected is sharp by being specified by spectrum imaging system collection
Tobacco shred under luminous source irradiation obtains, and in the range of excitation wavelength, each wave band all gathers a width fluoroscopic image.
In described step C and step G, image processing and analyzing system adopts the scanning window of 5 × 5 pixels that acquisition is treated
Survey tobacco shred each group partial image to be scanned according to order from top to bottom, from left to right, calculate tobacco shred to be measured in scanning window
Each group partial image average and variance Var, if variance Var is more than given threshold TD, then Fast Median Filtering method is adopted to this point
It is smoothed, remove the interference in tobacco shred image to be measured and noise.
In described step E, the property data base of each type tobacco shred component is by tobacco shred in the fluoroscopic image of this kind of tobacco shred
The pixel value average in regionComposition, i is tobacco shred species, and including cut tobacco, stem, reconstituted tobacco silk and expansive cut tobacco, j is
The wavelength of corresponding exciting light, each wavelength j corresponds to a width fluoroscopic image.
In described step H, the pixel that image processing and analyzing system calculates every tobacco shred to be measured in fluoroscopic image respectively is equal
ValueAnd carry out mating judgement with the characteristic amount of tobacco shreds all types of in property data base, x is tobacco shred species to be determined；It is under the excitation light irradiation for j for the wavelength, the characteristic of tobacco shred pixel value average to be measured and i type tobacco shred
Measure the side-play amount mated；The variance of the total drift amount that tobacco shred to be measured is mated with the characteristic amount of i type tobacco shred isWherein n is the start wavelength of exciting light, and m is to terminate wavelength,For to be measured
The side-play amount average that tobacco shred is compared with i type tobacco shred；By tobacco shred to be measured and cut tobacco, stem, reconstituted tobacco silk, expansive cut tobacco
Total drift amount variance VRiIt is ranked up, work as VRiWhen value is minimum, makes x=i, complete the judgement to current tobacco shred species.
In described step B and step F, described spectrum imaging system using spectrum camera or is provided with bandpass filter
CCD camera with tight shot.
The present invention utilizes the difference between the different component of tobacco shred, based on spectral imaging technology, in specified excitation source
Under irradiation, gather, using spectrum imaging system, the image formed by fluorescence that tobacco shred gives off, the tobacco shred according to different component is glimmering
The feature difference showing in light image carries out the identification of different component tobacco shred, can rapidly and accurately complete tobacco shred component automatic
Change and measure identification, drastically increase determination efficiency and accuracy, reduce intensity of workers.Meanwhile, the present invention does not relate to
And any chemical reagent, will not healthy to operator work the mischief.
Brief description
Fig. 1 is the testing process schematic diagram of the present invention.
Specific embodiment
Due to the difference of processing method and raw material self character, between the different component of tobacco shred, there is texture, color, shape
State, the difference of edge-smoothing degree, the existing for of these differences identifies that each component provides characteristic parameter.Therefore, it can utilize
Difference between the different component of tobacco shred, based on spectral imaging technology, under specified excitation source irradiates, using light spectrum image-forming
Image formed by the fluorescence that system acquisition tobacco shred gives off, the feature being shown on fluoroscopic image according to the tobacco shred of different component
Difference carries out the identification of different component tobacco shred.
As shown in figure 1, the tobacco shred component recognition methodss based on spectral imaging technology of the present invention, walk including following
Suddenly：
A：Respectively by a number of cut tobacco, stem, expansive cut tobacco with reconstituted tobacco silk sample is smooth non-overlapping puts
On Image-capturing platform.
B：Open excitation source to be irradiated, different cigarettes are gathered successively with reference to image capture software by spectrum imaging system
The fluoroscopic image of silk component.The fluoroscopic image being collected is by being specified under excitation source irradiation by spectrum imaging system collection
Tobacco shred obtain, in the range of excitation wavelength, each wave band all gathers a width fluoroscopic image.Spectrum imaging system can adopt
Spectrum camera or the CCD camera being provided with bandpass filter and tight shot.
C：Using image processing and analyzing system, the fluoroscopic image of tobacco shred is carried out with pretreatment, remove the interference in image and make an uproar
Sound.Image processing and analyzing system adopt 5 × 5 pixels scanning window to obtain tobacco shred each group partial image to be measured according to
Under, order from left to right be scanned, calculate tobacco shred each group partial image average to be measured and variance Var in scanning window, if
Variance Var is more than given threshold TD, then this point is smoothed using Fast Median Filtering method, removes tobacco shred figure to be measured
Interference in picture and noise.
D：Obtain the spectrum picture feature of all types of tobacco shred components using image processing and analyzing system respectively, then according to light
The characteristic amount of spectrum box counting algorithm dissimilar tobacco shred component；
E：Using image processing and analyzing system, property data base is set up according to the characteristic amount of all types of tobacco shred components.Often
The property data base of type tobacco shred component is by the pixel value average in tobacco shred region in the fluoroscopic image of this kind of tobacco shredGroup
Become, i is tobacco shred species, including cut tobacco, stem, reconstituted tobacco silk and expansive cut tobacco, j is the wavelength of corresponding exciting light, each
Wavelength j corresponds to a width fluoroscopic image.
F：By tobacco shred to be measured pass through spread out separation system smooth non-overlapping be placed on Image-capturing platform, using spectrum
Imaging system combines the fluoroscopic image that image capture software gathers tobacco shred to be measured；The acquisition of fluoroscopic image and step B in this step
In consistent, will not be described here.
G：Using image processing and analyzing system, the fluoroscopic image of tobacco shred to be measured is carried out with pretreatment, remove tobacco shred image to be measured
In interference and noise；The interference removing in tobacco shred image to be measured is consistent with step C with the method for noise, and here is no longer superfluous
State.
H：Calculate the characteristic number of every tobacco shred to be measured in tobacco shred fluoroscopic image to be measured by image processing and analyzing system respectively
According to amount, and carry out relatedness computation with the characteristic amount of all types of tobacco shred components in the property data base set up in step E,
Then tobacco shred to be measured is analyzed identify according to relatedness computation result.Specific analysis recognition method is as follows：
Calculate the pixel average of every tobacco shred to be measured in fluoroscopic image first by image processing and analyzing system respectivelyAnd
Carry out mating judgement with the characteristic amount of tobacco shreds all types of in property data base, x is tobacco shred species to be determined；It is under the excitation light irradiation for j for the wavelength, the characteristic of tobacco shred pixel value average to be measured and i type tobacco shred
Measure the side-play amount mated；The variance of the total drift amount that tobacco shred to be measured is mated with the characteristic amount of i type tobacco shred isWherein n is the start wavelength of exciting light, and m is to terminate wavelength,For to be measured
The side-play amount average that tobacco shred is compared with i type tobacco shred.Then by tobacco shred to be measured and cut tobacco, stem, reconstituted tobacco silk, expansion
Total drift amount variance VR of cut tobaccoiIt is ranked up, work as VRiWhen value is minimum, makes x=i, complete the judgement to current tobacco shred species.
I：Image processing and analyzing system will be analyzed recognition result and send to sorting system, by sorting system tobacco shred is carried out by
Class sorts；
J：Weigh the quality of each component tobacco shred being sorted out by sorting system respectively, and calculate the ratio of all types of tobacco shreds.
In the present invention, image capture software can be as soft in Motic2.0 image acquisition using existing various software on the market
Part；Image analysis processing system can adopt host computer, and cooperation realizes phase according to the software of conventional images Treatment Analysis technology establishment
Close function, such as MATLAB image processing and analyzing software；Spread out separation system comprises feed belt, vibrosieve, vibration platen etc. can
So that smooth for the tobacco shred to be measured non-overlapping machinery separating drawout or device to be combined；Sorting system comprises mechanical sorting
Device or device combination that all types of tobacco shred components that machine, mechanical hand, malleation or negative pressure straw etc. can will identify that sort out.
Each equipment above-mentioned and corresponding software belong to existing product, will not be described here.
The present invention will be further elaborated with reference to embodiments：
Embodiment 1
1) respectively by cut tobacco, stem, expansive cut tobacco with reconstituted tobacco silk is smooth non-overlapping is placed in Image-capturing platform
On；
2) open excitation source to be irradiated, different tobacco shred groups are gathered successively with reference to image capture software by spectrum camera
The fluoroscopic image dividing；
3) utilize image processing and analyzing system removal step 2) in collection different tobacco shred constitutional diagram pictures in interference and make an uproar
Sound；
4) the spectrum picture feature of all types of tobacco shred components is obtained respectively using image processing and analyzing system, and according to acquisition
Spectrum picture feature calculation pixel average；
5) using image processing and analyzing system, property data base is set up according to the pixel average of all types of tobacco shred components；
6) by tobacco shred to be measured pass through vibrosieve smooth non-overlapping be placed on fluoroscopic image acquisition platform, by spectrum phase
Machine coordinates image capture software, gathers the fluoroscopic image of tobacco shred to be measured；
7) pass through image processing and analyzing system removal step 6) in collection the fluoroscopic image of tobacco shred to be measured in interference and
Noise；
8) by image processing and analyzing system calculate respectively every tobacco shred to be measured in tobacco shred fluoroscopic image to be measured pixel equal
Value, and with step 5) in the property data base set up the pixel average amount of all types of tobacco shred components carry out relatedness computation,
Then tobacco shred to be measured is analyzed identify according to relatedness computation result；
9) by step 8) in the recognition result that draws transfer to mechanical sorting machine, by mechanical sorting machine, tobacco shred is carried out dividing by class
Pick；
10) weigh respectively by step 9) in the quality of each component tobacco shred that sorts out of mechanical sorting machine, and calculate all types of
The ratio of tobacco shred.
Embodiment 2
1) respectively by cut tobacco, stem, expansive cut tobacco with reconstituted tobacco silk is smooth non-overlapping is placed in Image-capturing platform
On；
2) open excitation source to be irradiated, be provided by the CCD camera of bandpass filter and tight shot, in conjunction with figure
As acquisition software gathers the fluoroscopic image of different tobacco shred components successively；
3) utilize image processing and analyzing system removal step 2) in collection different tobacco shred constitutional diagram pictures in interference and make an uproar
Sound；
4) the spectrum picture feature of all types of tobacco shred components is obtained respectively using image processing and analyzing system, and according to acquisition
Spectrum picture feature calculation pixel average；
5) using image processing and analyzing system, property data base is set up according to the pixel average of all types of tobacco shred components；
6) by tobacco shred to be measured pass through vibrosieve smooth non-overlapping be placed on fluoroscopic image acquisition platform, be provided by
Bandpass filter and the CCD camera of tight shot, gather the fluoroscopic image of tobacco shred to be measured in conjunction with image capture software；
7) pass through image processing and analyzing system removal step 6) in collection the fluoroscopic image of tobacco shred to be measured in interference and
Noise；
8) by image processing and analyzing system calculate respectively every tobacco shred to be measured in tobacco shred fluoroscopic image to be measured pixel equal
Value, and with step 5) in the property data base set up the pixel average amount of all types of tobacco shred components carry out relatedness computation,
Then tobacco shred to be measured is analyzed identify according to relatedness computation result；
9) by step 8) in the recognition result that draws transfer to mechanical sorting machine, by mechanical sorting machine, tobacco shred is carried out dividing by class
Pick；
10) weigh respectively by step 9) in the quality of each component tobacco shred that sorts out of mechanical sorting machine, and calculate all types of
The ratio of tobacco shred.
Claims (6)
1. a kind of tobacco shred component recognition methodss based on spectral imaging technology are it is characterised in that comprise the following steps：
A：Respectively by a number of cut tobacco, stem, expansive cut tobacco with reconstituted tobacco silk sample is smooth non-overlapping is placed in figure
As on acquisition platform；
B：Open excitation source to be irradiated, different tobacco shred groups are gathered successively with reference to image capture software by spectrum imaging system
The fluoroscopic image dividing；
C：Using image processing and analyzing system, the fluoroscopic image of tobacco shred is carried out with pretreatment, remove the interference in image and noise；
D：Obtain the spectrum picture feature of all types of tobacco shred components using image processing and analyzing system respectively, then according to spectrogram
Characteristic amount as feature calculation dissimilar tobacco shred component；
E：Using image processing and analyzing system, property data base is set up according to the characteristic amount of all types of tobacco shred components；
F：By tobacco shred to be measured pass through spread out separation system smooth non-overlapping be placed on Image-capturing platform, using light spectrum image-forming
System combines the fluoroscopic image that image capture software gathers tobacco shred to be measured；
G：Using image processing and analyzing system, the fluoroscopic image of tobacco shred to be measured is carried out with pretreatment, remove in tobacco shred image to be measured
Interference and noise；
H：Calculate the characteristic amount of every tobacco shred to be measured in tobacco shred fluoroscopic image to be measured by image processing and analyzing system respectively,
And carry out relatedness computation with the characteristic amount of all types of tobacco shred components in the property data base set up in step E, then
Tobacco shred to be measured is analyzed identify according to relatedness computation result；
I：Image processing and analyzing system will be analyzed recognition result and send to sorting system, by sorting system, tobacco shred be carried out dividing by class
Pick；
J：Weigh the quality of each component tobacco shred being sorted out by sorting system respectively, and calculate the ratio of all types of tobacco shreds.
2. the tobacco shred component recognition methodss based on spectral imaging technology according to claim 1 it is characterised in that：Described
In step B and step F, the fluoroscopic image being collected is lower by specifying excitation source to irradiate by spectrum imaging system collection
Tobacco shred obtains, and in the range of excitation wavelength, each wave band all gathers a width fluoroscopic image.
3. the tobacco shred component recognition methodss based on spectral imaging technology according to claim 2 it is characterised in that：Described
In step C and step G, image processing and analyzing system adopts the scanning window of 5 × 5 pixels that the tobacco shred each group partial image obtaining is pressed
It is scanned according to order from top to bottom, from left to right, calculate tobacco shred each group partial image average and variance in scanning window
Var, if variance Var is more than given threshold TD, then Fast Median Filtering side is adopted to tobacco shred each group partial image in this scanning window
Method is smoothed, and removes the interference in tobacco shred image and noise.
4. the tobacco shred component recognition methodss based on spectral imaging technology according to claim 3 it is characterised in that：Described
In step E, the property data base of each type tobacco shred component is equal by the pixel value in tobacco shred region in the fluoroscopic image of this kind of tobacco shred
ValueComposition, i is tobacco shred species, and including cut tobacco, stem, reconstituted tobacco silk and expansive cut tobacco, j is the ripple of corresponding exciting light
Long, each wavelength j corresponds to a width fluoroscopic image.
5. the tobacco shred component recognition methodss based on spectral imaging technology according to claim 4 it is characterised in that：Described
In step H, image processing and analyzing system calculates the pixel average of every tobacco shred to be measured in fluoroscopic image respectivelyAnd and characteristic number
Carry out coupling according to the characteristic amount of tobacco shreds all types of in storehouse and judge, x is tobacco shred species to be determined；Be
Wavelength is the skew that tobacco shred pixel value average to be measured is mated with the characteristic amount of i type tobacco shred under the excitation light irradiation of j
Amount；The variance of the total drift amount that tobacco shred to be measured is mated with the characteristic amount of i type tobacco shred isWherein n is the start wavelength of exciting light, and m is to terminate wavelength,For cigarette to be measured
The side-play amount average that silk is compared with i type tobacco shred；By tobacco shred to be measured and cut tobacco, stem, reconstituted tobacco silk, expansive cut tobacco
Total drift amount variance VRiIt is ranked up, work as VRiWhen value is minimum, makes x=i, complete the judgement to current tobacco shred species.
6. the tobacco shred component recognition methodss based on spectral imaging technology according to claim 5 it is characterised in that：Described
In step B and step F, described spectrum imaging system using spectrum camera or is provided with bandpass filter and tight shot
CCD camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410491816.9A CN104198457B (en) | 2014-09-04 | 2014-09-22 | Cut tobacco component recognition method based on spectral imaging technology |
Applications Claiming Priority (4)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201420509806.9 | 2014-09-04 | ||
| CN2014205098069 | 2014-09-04 | ||
| CN201420509806 | 2014-09-04 | ||
| CN201410491816.9A CN104198457B (en) | 2014-09-04 | 2014-09-22 | Cut tobacco component recognition method based on spectral imaging technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104198457A CN104198457A (en) | 2014-12-10 |
| CN104198457B true CN104198457B (en) | 2017-02-08 |
Family
ID=52083782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410491816.9A Active CN104198457B (en) | 2014-09-04 | 2014-09-22 | Cut tobacco component recognition method based on spectral imaging technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104198457B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106944361A (en) * | 2016-01-07 | 2017-07-14 | 西派特（北京）科技有限公司 | A kind of technology of High-Speed Automatic sorting tobacco leaf degree |
| CN106768243B (en) * | 2016-12-15 | 2019-03-05 | 芯海科技（深圳）股份有限公司 | A kind of quick lock in accurate weight method |
| CN107578067A (en) * | 2017-09-15 | 2018-01-12 | 国家烟草质量监督检验中心 | A kind of recognition methods of pipe tobacco component and device based on convolutional neural networks |
| CN107952696B (en) * | 2017-11-24 | 2019-07-05 | 中国科学院合肥物质科学研究院 | A kind of detection grading plant and detection method suitable for fresh tobacco leaf |
| CN108562604B (en) * | 2018-01-26 | 2020-07-28 | 江苏警官学院 | Method for identifying cigarette manufacturer |
| CN111562265A (en) * | 2020-03-10 | 2020-08-21 | 自然资源部珠宝玉石首饰管理中心深圳珠宝研究所 | Method for quantitatively analyzing emerald spectral data |
| CN111766241B (en) * | 2020-07-23 | 2023-10-13 | 清研(洛阳)先进制造产业研究院 | Cut tobacco structure detection method based on image processing |
| CN113570584A (en) * | 2021-07-30 | 2021-10-29 | 河南中烟工业有限责任公司 | Cut tobacco structure detection method based on image recognition |
| CN115791768A (en) * | 2022-11-08 | 2023-03-14 | 江苏鑫源烟草薄片有限公司 | Method for detecting blending uniformity of reconstituted tobacco or reconstituted cut stems in cigarettes and application |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251471B (en) * | 2008-03-12 | 2010-06-02 | 湖南中烟工业有限责任公司 | Method for searching analog tobacco leaf based on tobacco leaf near infrared spectra |
| CN101502337B (en) * | 2009-02-26 | 2012-05-02 | 孟科峰 | Method for controlling model building in leaf moisture-regaining process of tobacco shred production |
| WO2010132990A1 (en) * | 2009-05-22 | 2010-11-25 | British Columbia Cancer Agency Branch | Selective excitation light fluorescence imaging methods and apparatus |
| CN101566565B (en) * | 2009-06-03 | 2011-03-30 | 川渝中烟工业公司 | Fast measuring method of tobacco shred mixing ratio |
| CN101598709B (en) * | 2009-07-10 | 2011-08-24 | 中国烟草总公司郑州烟草研究院 | Method for determining fragrance stabilizing capacity of tobacco humectant on additional flavors in cut tobaccos |
| CN101627832B (en) * | 2009-08-12 | 2012-01-25 | 贵州遵义烟叶有限责任公司 | On-line automatic tobacco recognition and classification system |
| CN103512992B (en) * | 2013-09-24 | 2015-08-19 | 贵州中烟工业有限责任公司 | The method of the flavor substance express-analysis of Maillard reaction in a kind of cigarette shreds |
| CN103674885B (en) * | 2013-12-06 | 2016-06-01 | 中国烟草总公司山东省公司 | A kind of method applying the harmless cigarette of discerning the false from the genuine fast of infrared spectrum technology |
| CN103976468A (en) * | 2014-04-30 | 2014-08-13 | 河南科技大学 | Tobacco leaf grading method |
-
2014
- 2014-09-22 CN CN201410491816.9A patent/CN104198457B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN104198457A (en) | 2014-12-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| 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 | |
| CN104256882B (en) | Based on reconstituted tobacco ratio measuring method in the pipe tobacco of computer vision | |
| CN104198325B (en) | Stem ratio measuring method in pipe tobacco based on computer vision | |
| JP6110992B2 (en) | Image-adaptive physiologically relevant color separation | |
| Patil et al. | Leaf disease severity measurement using image processing | |
| CN100480680C (en) | Multiple spectrum meat freshness artificial intelligence measurement method and system | |
| CN110705655A (en) | Tobacco leaf classification method based on coupling of spectrum and machine vision | |
| CN101949686A (en) | Online nondestructive testing (NDT) method and device for comprehensive internal/external qualities of fruits | |
| Cluff et al. | Optical scattering with hyperspectral imaging to classify longissimus dorsi muscle based on beef tenderness using multivariate modeling | |
| Arefi et al. | Wheat class identification using computer vision system and artificial neural networks | |
| JP2012510276A (en) | Method and apparatus suitable for measuring the growth of plant leaf pieces | |
| CN111122590B (en) | Ceramic surface defect detection device and detection method | |
| CN104197866B (en) | Method for quantitative determination of cutin to starch percentage of corn kernel cross section | |
| CN102074031B (en) | Standard establishment method for observational check machine of printed circuit board | |
| CN107891012A (en) | Pearl size and circularity sorting equipment based on equivalent algorithm | |
| CN110319933B (en) | Light source spectrum optimization method based on CAM02-UCS color appearance model | |
| CN114062366B (en) | Online detection method and system for winnowing stem-removing quality in tobacco shred production | |
| CN107578067A (en) | A kind of recognition methods of pipe tobacco component and device based on convolutional neural networks | |
| CN113518182A (en) | Cucumber phenotype characteristic measuring method based on raspberry pie | |
| CN104198491B (en) | Based on expansive cut tobacco ratio measuring method in the tobacco shred of computer vision | |
| CN105628206A (en) | Method for measuring colors of tea leaves at different positions | |
| CN111398138A (en) | Optical detection system and method of dry type blood cell analysis device | |
| CN103208013B (en) | Photo source identification method based on image noise analysis | |
| Liang et al. | A high-throughput and low-cost maize ear traits scorer |
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 |