CN104198457A - 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
- CN104198457A CN104198457A CN201410491816.9A CN201410491816A CN104198457A CN 104198457 A CN104198457 A CN 104198457A CN 201410491816 A CN201410491816 A CN 201410491816A CN 104198457 A CN104198457 A CN 104198457A
- Authority
- CN
- China
- Prior art keywords
- pipe tobacco
- image
- tobacco
- measured
- pipe
- 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
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 the recognition methods of a kind of pipe tobacco component, relate in particular to a kind of pipe tobacco component recognition methods based on light spectrum image-forming technology.
Background technology
Cigarette composition design is basis and the core of cigarette enterprise product design.In the tobacco shred blending link of production of cigarettes, there is impact in various degree to cigarette physical index, flue gas characteristic and aesthetic quality in the dosage of mixing of the components such as cut tobacco, stem, expansive cut tobacco, reconstituted tobacco silk.Therefore, determine rapidly and accurately the ratio of each component in pipe tobacco, to examination formula Design target, stablize pipe tobacco hybrid technique quality and homogeneity production is significant.
Because the feature of detected object is complicated and relate to correlation technique bottleneck, the mensuration of pipe tobacco constituent still relies on hand-sorting and people is interpretation, current normally used pipe tobacco component recognition methods step is as follows: first artificial cognition goes out each component in pipe tobacco, then by hand-sorting and specific solvent, each component is screened one by one, last poidometer is separately calculated the ratio of cut tobacco, stem, reconstituted tobacco silk, each composition of expansive cut tobacco.Existing pipe tobacco component recognition methods poor operability, length consuming time, workload are huge, are difficult to be applied to batch detection, and it measures efficiency and the difficult requirement that has adapted to modern detection demand and high-quality production of cigarettes of precision.In addition, the use of organic solvent has also increased the protection difficulty in experimentation, is unfavorable for that reviewer's is healthy.
Summary of the invention
The object of this invention is to provide a kind of pipe tobacco component recognition methods based on light spectrum image-forming technology, the feature difference that can show on fluoroscopic image according to the pipe tobacco of different component carries out the identification of different component pipe tobacco, finally realize each component of pipe tobacco carry out fast, accurately, automatic assay, improve determination efficiency and accuracy, reduce intensity of workers.
The present invention adopts following technical proposals:
A pipe tobacco component recognition methods based on light spectrum image-forming technology, comprises the following steps:
A: respectively by smooth non-overlapping the putting on image acquisition platform of the cut tobacco of some, stem, expansive cut tobacco and reconstituted tobacco silk sample;
B: open excitation source and irradiate, gather successively the fluoroscopic image of different pipe tobacco components by spectrum imaging system combining image acquisition software;
C: utilize image processing and analyzing system to carry out pre-service to the fluoroscopic image of pipe tobacco, remove interference and noise in image;
D: utilize image processing and analyzing system to obtain respectively the spectrum picture feature of all types of pipe tobacco components, then according to the characteristic amount of the dissimilar pipe tobacco component of spectrum picture feature calculation;
E: utilize image processing and analyzing system to set up property data base according to the characteristic amount of all types of pipe tobacco components;
F: by sprawling smooth non-overlapping being placed on image acquisition platform of piece-rate system, utilize spectrum imaging system combining image acquisition software to gather the fluoroscopic image of pipe tobacco to be measured in pipe tobacco to be measured;
G: utilize image processing and analyzing system to carry out pre-service to the fluoroscopic image of pipe tobacco to be measured, remove interference and noise in pipe tobacco image to be measured;
H: the characteristic amount of calculating respectively every pipe tobacco to be measured in pipe tobacco fluoroscopic image to be measured by image processing and analyzing system, and with step e in the property data base set up the characteristic amount of all types of pipe tobacco components carry out relatedness computation, then according to relatedness computation result, pipe tobacco to be measured is analyzed to identification;
I: image processing and analyzing system is sent to sorting system by analysis recognition result, is carried out sorting by class to pipe tobacco by sorting system;
J: weigh respectively the quality of each component pipe tobacco being sorted out by sorting system, and calculate the ratio of all types of pipe tobaccos.
In described step B and step F, the fluoroscopic image collecting is that within the scope of excitation wavelength, each wave band all gathers a width fluoroscopic image by specified the pipe tobacco under excitation source irradiation to obtain by spectrum imaging system collection.
In described step C and step G, the scanning window that image processing and analyzing system adopts 5 * 5 pixels scans according to order from top to bottom, from left to right each constitutional diagram picture of the pipe tobacco to be measured obtaining, calculate interior each constitutional diagram of pipe tobacco to be measured of scanning window as average and variance Var, if variance Var is greater than setting threshold T
d, to this point, adopt Fast Median Filtering method to carry out smoothing processing, remove interference and noise in pipe tobacco image to be measured.
In described step e, the pixel value average in the property data base of every type of pipe tobacco component pipe tobacco region in the fluoroscopic image of this kind of pipe tobacco
form, i is pipe tobacco kind, comprises cut tobacco, stem, reconstituted tobacco silk and expansive cut tobacco, and j is that correspondence excites light wavelength, the corresponding width fluoroscopic image of each wavelength j.
In described step H, image processing and analyzing system is calculated respectively the pixel average of every pipe tobacco to be measured in fluoroscopic image
and mating judgement with the characteristic amount of all types of pipe tobaccos in property data base, x is pipe tobacco kind to be determined;
under the exciting light irradiation that is j at wavelength, the side-play amount that pipe tobacco pixel value average to be measured is mated with the characteristic amount of i type pipe tobacco; Pipe tobacco to be measured with the variance of the total drift amount that the characteristic amount of i type pipe tobacco is mated is
the initial wavelength that wherein n is exciting light, m is termination wavelength,
the side-play amount average of comparing for pipe tobacco to be measured and i type pipe tobacco; By the total drift amount variance VR of pipe tobacco to be measured and cut tobacco, stem, reconstituted tobacco silk, expansive cut tobacco
isort, work as VR
ivalue hour, makes x=i, completes the judgement to current pipe tobacco kind.
In described step B and step F, described spectrum imaging system adopts spectrum camera or is provided with bandpass filter and the CCD camera of tight shot.
The present invention utilizes the difference between the different component of pipe tobacco, based on light spectrum image-forming technology, under the excitation source of appointment irradiates, the image that the fluorescence that utilizes spectrum imaging system collection pipe tobacco to give off becomes, the feature difference showing on fluoroscopic image according to the pipe tobacco of different component carries out the identification of different component pipe tobacco, can complete rapidly and accurately the identification of pipe tobacco component automatic assay, greatly improve determination efficiency and accuracy, reduce intensity of workers.Meanwhile, the present invention does not relate to any chemical reagent, can not work the mischief to operating personnel are healthy.
Accompanying drawing explanation
Fig. 1 is testing process schematic diagram of the present invention.
Embodiment
Due to the difference of job operation and raw material self character, between the different component of pipe tobacco, there is the difference of texture, color, form, edge-smoothing degree, each component of identification that exists for of these differences provides characteristic parameter.Therefore, can utilize the difference between the different component of pipe tobacco, based on light spectrum image-forming technology, under the excitation source of appointment irradiates, the image that the fluorescence that utilizes spectrum imaging system collection pipe tobacco to give off becomes, the feature difference showing on fluoroscopic image according to the pipe tobacco of different component carries out the identification of different component pipe tobacco.
As shown in Figure 1, the pipe tobacco component recognition methods based on light spectrum image-forming technology of the present invention, comprises the following steps:
A: respectively by smooth non-overlapping the putting on image acquisition platform of the cut tobacco of some, stem, expansive cut tobacco and reconstituted tobacco silk sample.
B: open excitation source and irradiate, gather successively the fluoroscopic image of different pipe tobacco components by spectrum imaging system combining image acquisition software.The fluoroscopic image collecting is that within the scope of excitation wavelength, each wave band all gathers a width fluoroscopic image by specified the pipe tobacco under excitation source irradiation to obtain by spectrum imaging system collection.Spectrum imaging system can adopt spectrum camera or be provided with bandpass filter and the CCD camera of tight shot.
C: utilize image processing and analyzing system to carry out pre-service to the fluoroscopic image of pipe tobacco, remove interference and noise in image.The scanning window that image processing and analyzing system adopts 5 * 5 pixels scans according to order from top to bottom, from left to right each constitutional diagram picture of the pipe tobacco to be measured obtaining, calculate interior each constitutional diagram of pipe tobacco to be measured of scanning window as average and variance Var, if variance Var is greater than setting threshold T
d, to this point, adopt Fast Median Filtering method to carry out smoothing processing, remove interference and noise in pipe tobacco image to be measured.
D: utilize image processing and analyzing system to obtain respectively the spectrum picture feature of all types of pipe tobacco components, then according to the characteristic amount of the dissimilar pipe tobacco component of spectrum picture feature calculation;
E: utilize image processing and analyzing system to set up property data base according to the characteristic amount of all types of pipe tobacco components.The pixel value average in the property data base of every type of pipe tobacco component pipe tobacco region in the fluoroscopic image of this kind of pipe tobacco
form, i is pipe tobacco kind, comprises cut tobacco, stem, reconstituted tobacco silk and expansive cut tobacco, and j is that correspondence excites light wavelength, the corresponding width fluoroscopic image of each wavelength j.
F: by sprawling smooth non-overlapping being placed on image acquisition platform of piece-rate system, utilize spectrum imaging system combining image acquisition software to gather the fluoroscopic image of pipe tobacco to be measured in pipe tobacco to be measured; In this step fluoroscopic image obtain unanimously with step B, do not repeat them here.
G: utilize image processing and analyzing system to carry out pre-service to the fluoroscopic image of pipe tobacco to be measured, remove interference and noise in pipe tobacco image to be measured; The method of removing interference in pipe tobacco image to be measured and noise is consistent with step C, does not repeat them here.
H: the characteristic amount of calculating respectively every pipe tobacco to be measured in pipe tobacco fluoroscopic image to be measured by image processing and analyzing system, and with step e in the property data base set up the characteristic amount of all types of pipe tobacco components carry out relatedness computation, then according to relatedness computation result, pipe tobacco to be measured is analyzed to identification.Concrete analysis recognition method is as follows:
First by image processing and analyzing system, calculated respectively the pixel average of every pipe tobacco to be measured in fluoroscopic image
and mating judgement with the characteristic amount of all types of pipe tobaccos in property data base, x is pipe tobacco kind to be determined;
under the exciting light irradiation that is j at wavelength, the side-play amount that pipe tobacco pixel value average to be measured is mated with the characteristic amount of i type pipe tobacco; Pipe tobacco to be measured with the variance of the total drift amount that the characteristic amount of i type pipe tobacco is mated is
the initial wavelength that wherein n is exciting light, m is termination wavelength,
the side-play amount average of comparing for pipe tobacco to be measured and i type pipe tobacco.Then by the total drift amount variance VR of pipe tobacco to be measured and cut tobacco, stem, reconstituted tobacco silk, expansive cut tobacco
isort, work as VR
ivalue hour, makes x=i, completes the judgement to current pipe tobacco kind.
I: image processing and analyzing system is sent to sorting system by analysis recognition result, is carried out sorting by class to pipe tobacco by sorting system;
J: weigh respectively the quality of each component pipe tobacco being sorted out by sorting system, and calculate the ratio of all types of pipe tobaccos.
In the present invention, image capture software can adopt existing various software on the market, as Motic2.0 image capture software; Image analysis processing system can adopt host computer, coordinates according to the software of conventional images Treatment Analysis technology establishment and realizes correlation function, as MATLAB image processing and analyzing software; Sprawl piece-rate system comprise feed belt, vibratory screening apparatus, shaking platform etc. can be by the mechanical hook-up of the smooth non-overlapping separated drawout of pipe tobacco to be measured or device combination; Sorting system comprises device or the device combination that mechanical sorting machine, mechanical arm, malleation or negative pressure straw etc. can sort out all types of pipe tobacco components that identify.Above-mentioned each equipment and corresponding software all belong to existing product, do not repeat them here.
Below in conjunction with embodiment, the present invention will be further elaborated:
Embodiment 1
1) respectively by smooth non-overlapping the putting on image acquisition platform of cut tobacco, stem, expansive cut tobacco and reconstituted tobacco silk;
2) open excitation source and irradiate, by spectrum camera combining image acquisition software, gather successively the fluoroscopic image of different pipe tobacco components;
3) utilize image processing and analyzing system to remove step 2) in interference and noise in the different pipe tobacco constitutional diagram pictures that gather;
4) utilize image processing and analyzing system to obtain respectively the spectrum picture feature of all types of pipe tobacco components, and according to the spectrum picture feature calculation pixel average of obtaining;
5) utilize image processing and analyzing system to set up property data base according to the pixel average of all types of pipe tobacco components;
6) by pipe tobacco to be measured by smooth non-overlapping being placed on fluoroscopic image acquisition platform of vibratory screening apparatus, by spectrum camera, coordinate image capture software, gather the fluoroscopic image of pipe tobacco to be measured;
7) by image processing and analyzing system, remove step 6) in interference and noise in the fluoroscopic image of the pipe tobacco to be measured that gathers;
8) by image processing and analyzing system, calculate respectively the pixel average of every pipe tobacco to be measured in pipe tobacco fluoroscopic image to be measured, and with step 5) in the property data base set up the pixel average amount of all types of pipe tobacco components carry out relatedness computation, then according to relatedness computation result, pipe tobacco to be measured is analyzed to identification;
9) by step 8) in the recognition result that draws transfer to mechanical sorting machine, by mechanical sorting machine, pipe tobacco is carried out sorting by class;
10) weigh by step 9 respectively) in the quality of each component pipe tobacco of sorting out of mechanical sorting machine, and calculate the ratio of all types of pipe tobaccos.
Embodiment 2
1) respectively by smooth non-overlapping the putting on image acquisition platform of cut tobacco, stem, expansive cut tobacco and reconstituted tobacco silk;
2) open excitation source and irradiate, by being provided with the CCD camera of bandpass filter and tight shot, combining image acquisition software gathers the fluoroscopic image of different pipe tobacco components successively;
3) utilize image processing and analyzing system to remove step 2) in interference and noise in the different pipe tobacco constitutional diagram pictures that gather;
4) utilize image processing and analyzing system to obtain respectively the spectrum picture feature of all types of pipe tobacco components, and according to the spectrum picture feature calculation pixel average of obtaining;
5) utilize image processing and analyzing system to set up property data base according to the pixel average of all types of pipe tobacco components;
6) by pipe tobacco to be measured by smooth non-overlapping being placed on fluoroscopic image acquisition platform of vibratory screening apparatus, by being provided with the CCD camera of bandpass filter and tight shot, combining image acquisition software gathers the fluoroscopic image of pipe tobacco to be measured;
7) by image processing and analyzing system, remove step 6) in interference and noise in the fluoroscopic image of the pipe tobacco to be measured that gathers;
8) by image processing and analyzing system, calculate respectively the pixel average of every pipe tobacco to be measured in pipe tobacco fluoroscopic image to be measured, and with step 5) in the property data base set up the pixel average amount of all types of pipe tobacco components carry out relatedness computation, then according to relatedness computation result, pipe tobacco to be measured is analyzed to identification;
9) by step 8) in the recognition result that draws transfer to mechanical sorting machine, by mechanical sorting machine, pipe tobacco is carried out sorting by class;
10) weigh by step 9 respectively) in the quality of each component pipe tobacco of sorting out of mechanical sorting machine, and calculate the ratio of all types of pipe tobaccos.
Claims (6)
1. the pipe tobacco component recognition methods based on light spectrum image-forming technology, is characterized in that, comprises the following steps:
A: respectively by smooth non-overlapping the putting on image acquisition platform of the cut tobacco of some, stem, expansive cut tobacco and reconstituted tobacco silk sample;
B: open excitation source and irradiate, gather successively the fluoroscopic image of different pipe tobacco components by spectrum imaging system combining image acquisition software;
C: utilize image processing and analyzing system to carry out pre-service to the fluoroscopic image of pipe tobacco, remove interference and noise in image;
D: utilize image processing and analyzing system to obtain respectively the spectrum picture feature of all types of pipe tobacco components, then according to the characteristic amount of the dissimilar pipe tobacco component of spectrum picture feature calculation;
E: utilize image processing and analyzing system to set up property data base according to the characteristic amount of all types of pipe tobacco components;
F: by sprawling smooth non-overlapping being placed on image acquisition platform of piece-rate system, utilize spectrum imaging system combining image acquisition software to gather the fluoroscopic image of pipe tobacco to be measured in pipe tobacco to be measured;
G: utilize image processing and analyzing system to carry out pre-service to the fluoroscopic image of pipe tobacco to be measured, remove interference and noise in pipe tobacco image to be measured;
H: the characteristic amount of calculating respectively every pipe tobacco to be measured in pipe tobacco fluoroscopic image to be measured by image processing and analyzing system, and with step e in the property data base set up the characteristic amount of all types of pipe tobacco components carry out relatedness computation, then according to relatedness computation result, pipe tobacco to be measured is analyzed to identification;
I: image processing and analyzing system is sent to sorting system by analysis recognition result, is carried out sorting by class to pipe tobacco by sorting system;
J: weigh respectively the quality of each component pipe tobacco being sorted out by sorting system, and calculate the ratio of all types of pipe tobaccos.
2. the pipe tobacco component recognition methods based on light spectrum image-forming technology according to claim 1, it is characterized in that: in described step B and step F, the fluoroscopic image collecting is that within the scope of excitation wavelength, each wave band all gathers a width fluoroscopic image by specified the pipe tobacco under excitation source irradiation to obtain by spectrum imaging system collection.
3. the pipe tobacco component recognition methods based on light spectrum image-forming technology according to claim 2, it is characterized in that: in described step C and step G, the scanning window that image processing and analyzing system adopts 5 * 5 pixels scans according to order from top to bottom, from left to right each constitutional diagram picture of the pipe tobacco to be measured obtaining, calculate interior each constitutional diagram of pipe tobacco to be measured of scanning window as average and variance Var, if variance Var is greater than setting threshold T
d, to this point, adopt Fast Median Filtering method to carry out smoothing processing, remove interference and noise in pipe tobacco image to be measured.
4. the pipe tobacco component recognition methods based on light spectrum image-forming technology according to claim 3, is characterized in that: in described step e, and the pixel value average in the property data base of every type of pipe tobacco component pipe tobacco region in the fluoroscopic image of this kind of pipe tobacco
form, i is pipe tobacco kind, comprises cut tobacco, stem, reconstituted tobacco silk and expansive cut tobacco, and j is that correspondence excites light wavelength, the corresponding width fluoroscopic image of each wavelength j.
5. the pipe tobacco component recognition methods based on light spectrum image-forming technology according to claim 4, is characterized in that: in described step H, image processing and analyzing system is calculated respectively the pixel average of every pipe tobacco to be measured in fluoroscopic image
and mating judgement with the characteristic amount of all types of pipe tobaccos in property data base, x is pipe tobacco kind to be determined;
under the exciting light irradiation that is j at wavelength, the side-play amount that pipe tobacco pixel value average to be measured is mated with the characteristic amount of i type pipe tobacco; Pipe tobacco to be measured with the variance of the total drift amount that the characteristic amount of i type pipe tobacco is mated is
the initial wavelength that wherein n is exciting light, m is termination wavelength,
the side-play amount average of comparing for pipe tobacco to be measured and i type pipe tobacco; By the total drift amount variance VR of pipe tobacco to be measured and cut tobacco, stem, reconstituted tobacco silk, expansive cut tobacco
isort, work as VR
ivalue hour, makes x=i, completes the judgement to current pipe tobacco kind.
6. the pipe tobacco component recognition methods based on light spectrum image-forming technology according to claim 5, is characterized in that: in described step B and step F, described spectrum imaging system adopts spectrum camera or is provided with bandpass filter and the CCD camera of tight shot.
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 | 2014-09-04 | ||
| CN201420509806.9 | 2014-09-04 | ||
| CN2014205098069 | 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 true CN104198457A (en) | 2014-12-10 |
| CN104198457B 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) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106768243A (en) * | 2016-12-15 | 2017-05-31 | 芯海科技（深圳）股份有限公司 | A kind of quick lock in accurate weight method |
| 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 |
| 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 |
| CN107952696A (en) * | 2017-11-24 | 2018-04-24 | 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 |
| CN108562604A (en) * | 2018-01-26 | 2018-09-21 | 江苏警官学院 | A method of identification production of cigarettes 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 |
| CN111766241A (en) * | 2020-07-23 | 2020-10-13 | 清华大学天津高端装备研究院洛阳先进制造产业研发基地 | 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 |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251471A (en) * | 2008-03-12 | 2008-08-27 | 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 |
| CN101502337A (en) * | 2009-02-26 | 2009-08-12 | 孟科峰 | Method for controlling model building in leaf moisture-regaining process of tobacco shred production |
| CN101566565A (en) * | 2009-06-03 | 2009-10-28 | 川渝中烟工业公司 | Fast measuring method of tobacco shred mixing ratio |
| CN101598709A (en) * | 2009-07-10 | 2009-12-09 | 中国烟草总公司郑州烟草研究院 | A kind of method of measuring tobacco humectant to pipe tobacco China and foreign countries perfuming fixation ability |
| CN101627832A (en) * | 2009-08-12 | 2010-01-20 | 贵州遵义烟叶有限责任公司 | On-line automatic tobacco recognition and classification system |
| WO2010132990A1 (en) * | 2009-05-22 | 2010-11-25 | British Columbia Cancer Agency Branch | Selective excitation light fluorescence imaging methods and apparatus |
| CN103512992A (en) * | 2013-09-24 | 2014-01-15 | 贵州中烟工业有限责任公司 | Rapid analysis method for flavor substances of maillard reaction in cigarette tobacco shreds |
| CN103674885A (en) * | 2013-12-06 | 2014-03-26 | 中国烟草总公司山东省公司 | Lossless rapid method for discriminating true and false cigarettes by applying infrared spectroscopy 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
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251471A (en) * | 2008-03-12 | 2008-08-27 | 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 |
| CN101502337A (en) * | 2009-02-26 | 2009-08-12 | 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 |
| CN101566565A (en) * | 2009-06-03 | 2009-10-28 | 川渝中烟工业公司 | Fast measuring method of tobacco shred mixing ratio |
| CN101598709A (en) * | 2009-07-10 | 2009-12-09 | 中国烟草总公司郑州烟草研究院 | A kind of method of measuring tobacco humectant to pipe tobacco China and foreign countries perfuming fixation ability |
| CN101627832A (en) * | 2009-08-12 | 2010-01-20 | 贵州遵义烟叶有限责任公司 | On-line automatic tobacco recognition and classification system |
| CN103512992A (en) * | 2013-09-24 | 2014-01-15 | 贵州中烟工业有限责任公司 | Rapid analysis method for flavor substances of maillard reaction in cigarette tobacco shreds |
| CN103674885A (en) * | 2013-12-06 | 2014-03-26 | 中国烟草总公司山东省公司 | Lossless rapid method for discriminating true and false cigarettes by applying infrared spectroscopy technology |
| CN103976468A (en) * | 2014-04-30 | 2014-08-13 | 河南科技大学 | Tobacco leaf grading method |
Cited By (12)
| 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 |
| CN106768243A (en) * | 2016-12-15 | 2017-05-31 | 芯海科技（深圳）股份有限公司 | A kind of quick lock in accurate weight method |
| 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 |
| CN107952696A (en) * | 2017-11-24 | 2018-04-24 | 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 |
| CN108562604A (en) * | 2018-01-26 | 2018-09-21 | 江苏警官学院 | A method of identification production of cigarettes manufacturer |
| 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 |
| CN111766241A (en) * | 2020-07-23 | 2020-10-13 | 清华大学天津高端装备研究院洛阳先进制造产业研发基地 | Cut tobacco structure detection method based on image processing |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104198457B (en) | 2017-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104198457B (en) | Cut tobacco component recognition method based on spectral imaging technology | |
| JP6110992B2 (en) | Image-adaptive physiologically relevant color separation | |
| 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 | |
| JP4317566B2 (en) | X-ray inspection apparatus and method for generating image processing procedure of X-ray inspection apparatus | |
| CN104198325B (en) | Stem ratio measuring method in pipe tobacco based on computer vision | |
| JP6517788B2 (en) | System and method for adaptive histopathology image decomposition | |
| JP5396484B2 (en) | Method and apparatus suitable for measuring the growth of plant leaf pieces | |
| CN103345617B (en) | Chinese medicine knows method for distinguishing and system thereof | |
| CN110705655A (en) | Tobacco leaf classification method based on coupling of spectrum and machine vision | |
| JPWO2019151393A1 (en) | Food inspection system, food inspection program, food inspection method and food production method | |
| CN101949686A (en) | Online nondestructive testing (NDT) method and device for comprehensive internal/external qualities of fruits | |
| MY164318A (en) | A system for fruit grading and quality determination | |
| CN111122590B (en) | Ceramic surface defect detection device and detection method | |
| CN108198176A (en) | A kind of method of discrimination based on image analysis tobacco maturity | |
| CN107578067A (en) | A kind of recognition methods of pipe tobacco component and device based on convolutional neural networks | |
| CN114521664A (en) | Automatic tobacco leaf grading system and device based on multi-mode image data and deep neural network | |
| CN104198491B (en) | Based on expansive cut tobacco ratio measuring method in the tobacco shred of computer vision | |
| JP2013167491A (en) | Detection device, detection method, detection program and storage medium for detecting detection target from specimen | |
| CN103208013B (en) | Photo source identification method based on image noise analysis | |
| CN105628206A (en) | Method for measuring colors of tea leaves at different positions | |
| TWI455039B (en) | Calculation method of average particle size distribution of batch coke | |
| MX2024000342A (en) | Inspection method, classification method, management method, steel material manufacturing method, training model generation method, training model, inspection device, and steel material manufacturing facility. | |
| JP2019533140A (en) | Segregation analyzer and method | |
| Afor et al. | Color Detection System for Diamond Sorting Using Machine Learning |
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 |