CN110542658A - tobacco non-smoke substance classification method based on hyperspectral imaging technology - Google Patents
tobacco non-smoke substance classification method based on hyperspectral imaging technology Download PDFInfo
- Publication number
- CN110542658A CN110542658A CN201910850623.0A CN201910850623A CN110542658A CN 110542658 A CN110542658 A CN 110542658A CN 201910850623 A CN201910850623 A CN 201910850623A CN 110542658 A CN110542658 A CN 110542658A
- Authority
- CN
- China
- Prior art keywords
- sample
- tobacco
- hyperspectral
- spectral
- spectrum
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
A tobacco non-smoke substance classification method based on a hyperspectral imaging technology is characterized by comprising the following steps: the tobacco leaves and the impurities are classified by utilizing a short wave imaging hyperspectral technology, a spectrum library comprising different substances is established, then image data are collected for a sample to be detected, a reference spectrum in the spectrum library is used for matching the sample to be detected and judging the sample to be detected, and then effective classification and identification of the tobacco leaves and the impurities are completed. The invention combines spectroscopic and two-dimensional imaging techniques. Compared with the prior art, the method has the following remarkable progress: 1. the invention utilizes the short wave imaging hyperspectral technology to classify tobacco leaves and sundries and establishes a spectrum library containing different substances. 2. The method does not use toxic and harmful chemicals in the experimental process, is simple, convenient and quick, and has no destructiveness to samples and no pollution to the environment. 3. The invention has the advantages of simple, convenient, rapid and accurate operation, low cost and high efficiency.
Description
Technical Field
The invention belongs to the field of hyperspectral agricultural production application, and particularly relates to a tobacco non-smoke substance classification method based on a hyperspectral imaging technology.
background
Hyperspectral imaging (Hyperspectral Image) is a comprehensive technology integrating a detector technology, a precise optical machine, weak signal detection, a computer technology and an information processing technology. The hyperspectral imaging simultaneously detects two-dimensional geometric space and one-dimensional spectral information of a target and acquires continuous and narrow-band image data with hyperspectral resolution, and is a multidimensional information acquisition technology combining an imaging technology and a spectral technology. Therefore, the object can be reflected finely by utilizing the hyperspectral image technology. In the tobacco industry, the quality and purity of tobacco raw materials are directly related to the quality of cigarette products. If non-tobacco leaf sundries (one class sundries comprise metal, feather, plastic and the like; the second class sundries comprise paper, stone, hemp ropes, glass and the like; and the third class sundries comprise non-tobacco leaf, seeds, bamboo sticks and the like) are mixed in the production, purchase, transportation and processing processes of tobacco leaves, the tobacco leaves cause great quality hidden troubles for cigarette finished products processed in the cigarette industry.
The impurity removal mode that adopts on the present cigarette production processing line mainly has: the method comprises the steps of wind power impurity removal, photoelectric impurity removal, magnetic impurity removal and manual selection impurity removal, wherein the wind power impurity removal, the photoelectric impurity removal and the magnetic impurity removal are all targeted for specific attribute differences of impurities to be identified and removed, such as specific gravity differences, color differences and magnetic differences, so that only one kind of impurities can be identified and removed by one impurity removal mode. Most of non-smoke impurities can be identified by manual impurity removal, but human eyes are easy to fatigue and the working efficiency is low.
The unique chemical composition and physical detection characteristics of the tobacco leaves result in unique diagnostic characteristic absorption bands, and the characteristic bands have more stable wavelength positions and unique waveforms. From the chemical analysis of tobacco leaves, the main chemical components in the tobacco leaves are carbohydrate, nitrogen-containing compounds, organic acid and mineral substances. Wherein, the absorption characteristics of the carbohydrate are represented in 1000-2500nm, the absorption characteristics of the nitrogen compound are represented in 1500-1750 nm, and the carbon compound and the nitrogen compound are used as important chemical components of the tobacco leaves and are not reflected in a visible light wave band (400-1000 nm). The spectrum of the tobacco leaves forms stronger absorption peaks near the carbohydrate and the nitrogen compound, and the absorption peaks can be used as important basis for distinguishing the tobacco leaves. By utilizing a spectrum information technology, non-tobacco leaf impurities and tobacco leaves form different specific spectra under the same optical environment, different substances are identified, and the classification of the tobacco leaves and the impurities is completed.
chinese patent (200910059486.5) discloses a method for rapidly determining the tobacco shred blending ratio based on a near infrared spectrometer. Compared with the method provided by the patent, the two methods are mainly different from each other in two points: first, the application range of the two is different. The Chinese patent (200910059486.5) is mainly used for measuring the tobacco shred blending ratio, and the method is mainly used for identifying impurities in tobacco leaves; secondly, because the used experimental instruments are different (Chinese patent (200910059486.5) uses a near-infrared spectrometer, and the method uses a hyperspectral imager), the method is simpler, more convenient and faster to operate, does not need to carry out operations such as sample crushing, screening and the like, and can carry out online labeling.
chinese patent (201410491816.9) mainly discloses a tobacco shred component identification method based on a spectral imaging technology. Compared with the method disclosed in the patent, the method has the following differences. 1. The instrument used in the method is a hyperspectral imager, the resolution is 12nm, and the identification precision is higher. 2. The spectrum camera used in the patent consists of a band-pass filter and a CCD camera with a fixed-focus lens, and the band customized by the band-pass filter only performs imaging and image processing analysis on tobacco shreds and cannot analyze and identify other substances. 3. The method provided by the patent is only used for measuring the components of tobacco shreds (cut tobacco leaves, cut stems, reconstituted tobacco cut leaves and expanded cut leaves), and the method provided by the patent is used for identifying tobacco leaves and non-tobacco substances which are inconsistent in function.
in conclusion, the method for measuring the content of tobacco shreds by using the spectrum technology and the method for quantitatively measuring the content of chemical substances in tobacco in a hyperspectral manner have certain research and application in the industry. And by utilizing a spectrum information technology, different specific spectrums are formed according to the non-tobacco impurities and the tobacco leaves in the same optical environment, different substances are identified, and the classification of the tobacco leaves and the non-tobacco substances is still blank.
Disclosure of Invention
the invention aims to provide a tobacco non-smoke substance classification method based on a hyperspectral imaging technology based on the prior art, which can quickly and accurately distinguish tobacco leaves and impurities and prevent the non-smoke impurities from entering tobacco sheet finished products.
the purpose of the invention is realized by the following technical scheme:
A tobacco leaf sundry classification and identification method based on hyperspectral imaging is characterized in that tobacco leaves and sundries are classified by utilizing a shortwave hyperspectral imaging technology, a spectrum library comprising different substances is established, hyperspectral image data are collected for samples to be detected, reference spectra in the spectrum library are used for matching the samples to be detected and judging the samples to be detected, and then effective classification and identification of the tobacco leaves and the sundries are completed.
The method comprises the following specific steps:
1) Collecting samples: obtaining samples of first-class sundries, second-class sundries and third-class sundries including pure tobacco leaves;
The sample surface remained dry and clean with no other attachments.
The sundries comprise metal, feather and plastic; the second class of sundries comprises paper, stones, hemp ropes and glass; the three kinds of impurities comprise non-tobacco leaves, seeds and bamboo sticks.
2) Sample preparation and hyperspectral imaging are carried out, and black and white frame correction is carried out;
And (3) taking a halogen tungsten lamp as an illumination light source, and performing hyperspectral image acquisition on the obtained tobacco leaf and sundry samples to obtain hyperspectral images of the samples. In order to reduce the noise influence, black and white frame correction is carried out on the hyperspectral image. The black and white frame correction formula is as follows:
In the formula: r-a corrected hyperspectral image; i-an original hyperspectral image; b, closing the all-black image collected by the camera lens; w-scanning the white correction plate to obtain a full white image.
3) Preprocessing a hyperspectral image and acquiring a characteristic image;
In order to improve the signal-to-noise ratio of data, the hyperspectral image data is preprocessed, and the preprocessing method comprises the following steps:
by using a Savitzky-Golay convolution smoothing filtering algorithm, baseline drift and inclination are removed, noise is removed, and smoothness of a spectral curve is improved;
And then reducing the scattering effect on the surface of the object by Multivariate Scattering Correction (MSC) to enhance the spectral absorption information among the same substances.
4) extracting sample spectrum information and establishing a spectrum library file;
Specific processes include, but are not limited to:
The tobacco leaf and sundries sample comprises: a pure tobacco leaf sample, a first class sundry sample, a second class sundry sample and a third class sundry sample;
respectively selecting tobacco leaves and regions of interest (ROI) of the first, second and third sundries, extracting spectral characteristics at the selected region of interest of the sample, and obtaining an average spectrum;
and establishing a spectrum information library file, and importing the average spectrum obtained from the ROI area of the sample into the library file for storage.
5) the tobacco leaf sundries are classified:
performing dimensionality reduction on a hyperspectral image of an acquired sample by adopting a Principal Component Analysis (PCA), matching a target spectrum by utilizing a spectral angle matching method (SAM), judging whether impurities are mixed in the tobacco sample or not according to a spectral feature vector, and marking different samples.
the specific process is as follows: the tobacco leaves mixed with the first, second and third impurities are subjected to image acquisition by a short wave hyperspectral imager, the acquired data are preprocessed and then compared with spectral information recorded in a spectral library, and the hyperspectral images are subjected to dimensionality reduction and characteristic identification of the tobacco leaves and the impurities by a Principal Component Analysis (PCA) and a Spectral Angle Matching (SAM) algorithm, wherein the method comprises the following steps:
Firstly, scanning and obtaining short-wave hyperspectral imaging information of the sample;
secondly, performing dimensionality reduction on the collected sample by adopting a principal component analysis method;
And finally, calculating by a spectral angle matching algorithm, judging whether impurities are mixed in the tobacco leaf sample according to the spectral feature vector, and marking different samples.
The preprocessing method in the step 3) can also adopt one of mean centering (mean centering), standardization (autoscaling), normalization (normalization), standard normal variable transformation (SNV), derivative, smooth denoising algorithm and wavelet transformation
The tobacco leaf impurity classification method based on the short wave imaging hyperspectral technology combines the spectrum technology and the two-dimensional image imaging technology. Compared with the prior art, the method has the following remarkable progress:
1. The invention utilizes the short wave imaging hyperspectral technology to classify tobacco leaves and sundries and establishes a spectrum library containing different substances.
2. The method does not use toxic and harmful chemicals in the experimental process, is simple, convenient and quick, and has no destructiveness to samples and no pollution to the environment.
3. the invention has the advantages of simple, convenient, rapid and accurate operation, low cost and high efficiency.
drawings
FIG. 1 is a flow chart of a tobacco leaf impurity identification and classification method based on a short-wave hyperspectral imaging technology, provided by the invention;
FIG. 2 is a spectrum of mixed impurities in tobacco leaves.
Detailed Description
The following describes embodiments of the present invention in further detail with reference to the accompanying drawings.
Laboratory instruments and parameters
The SWIR type hyperspectral imager produced by GaiaSorter-N25E of Sichuan Shuangli Spectroscopy technology Limited has the wavelength range of 1000-2500nm, the spectral resolution of 12nm, the image resolution of 384 pixels by 288 pixels, the number of spectrometer frames of 400 and the exposure time of 20 ms; the experimental platform uses a gaiastarter-Dual type dark box system which comprises a halogen tungsten lamp light source, an electric control platform and the like. In order to avoid the influence of an external stray light source, the hyperspectral image acquisition process is carried out in a dark box system.
step 1: collection of samples
In order to make the established spectral database have wider applicability, the embodiment selects the first and second types of sundries such as feathers, cloth strips, plastic ropes and the like provided by the tobacco leaf and the middle tobacco of the certain tobacco baking machine in 2018.
Step 2: sample preparation and hyperspectral imaging and black and white frame correction
and (3) selecting pure tobacco leaves, cloth strips, feathers and plastic ropes with the surfaces free of attachments after dust removal treatment, flatly paving the pure tobacco leaves, the cloth strips, the feathers and the plastic ropes on the black back plate, and marking the positions of the pure tobacco leaves, the cloth strips, the feathers and the plastic ropes. A SWIR type hyperspectral imager manufactured by Shuangli Hepianshan corporation is adopted, a lens cover is closed at first, and a completely black calibration image with zero reflectivity is collected. And then opening a lens cover, scanning a standard white board, collecting a full white calibration image with the emissivity of 99.9%, and then performing hyperspectral imaging on the tobacco leaf and the sundry sample. And (3) collecting the image by using SpecView software, correcting a black-white frame of the collected sample hyperspectral image according to the collected all-black and all-white calibration images to reduce noise caused by external stray light, and finally storing the hyperspectral image as an original spectral data format.
The black and white frame correction formula is as follows:
In the formula: r-a corrected hyperspectral image; i-an original hyperspectral image; b, closing a full black calibration image acquired by a camera lens; and W-scanning the white correction plate to obtain a full white calibration image.
And step 3: hyperspectral image preprocessing and characteristic image acquisition
in order to remove baseline drift and inclination, remove the influence of noise and improve the smoothness of a spectral curve, a Savitzky-Golay convolution smoothing filtering algorithm is used.
Savitzky-Golay filtering can improve the smoothness of a spectral curve and reduce the interference of noise. The key to the convolution smoothing is the solution to the matrix operator. And introducing Mean Square Error (MSE) to select proper window width n and filter kernel center point number m, wherein the MSE value is smaller and the noise is smaller. Assuming that the width of the filter window is 2m +1 and each measurement point is x (-m, -m +1 … 0 … m-1, m), fitting the data points within the window using a k-1 degree polynomial:
y＝a+ax+ax+…+ax
there are n of the above equations, constituting a k-wire linear system. For the solution of the system of equations, let n > k, the fitting parameters a are solved by the least squares method, from which:
expressed in a matrix as:
Y＝X·A+E
The least squares solution of a is:
the model predicted value or filtered value of Y is:
the spectral characteristics of the collected sample can be corrected by utilizing Multivariate Scattering Correction (MSC), and the spectral signal-to-noise ratio is improved.
Calculating the average spectrum of the spectrum to be corrected:
unary linear regression:
And (3) multivariate scattering correction:
in the formula, A-calibration spectrum data matrix, n-calibration sample number, and p-wavelength point number during spectrum collection; -average spectral vector.
and 4, step 4: extracting sample spectrum information and establishing a spectrum library file
the method comprises the steps of collecting hyperspectral images of first, second and third impurities including pure tobacco leaf samples, selecting regions of interest among different collected samples, extracting average spectral information among the samples, and establishing a spectral library file.
and 5: implementation of tobacco leaf sundry classification
the method comprises the steps of adopting a Principal Component Analysis (PCA) method to carry out dimensionality reduction on a hyperspectral image of an acquired sample, and then utilizing a spectrum angle matching method (SAM) algorithm to match a sample spectrum, thereby realizing the purpose of classifying impurities in tobacco leaves.
And (3) selecting the characteristic vector by a Principal Component Analysis (PCA) to realize the dimensionality reduction of the multi-index vector. The dimension reduction model is as follows:
y＝lx+lx+…+lx
y＝lx+lx+…+lx
y＝lx+lx+…+lx
In the formula, x is an n-dimensional multi-index vector, and y is an m-dimensional principal component vector obtained after processing.
The principal component analysis eigenvalues and variance contribution rates in the examples are shown in table 1 below.
TABLE 1 principal component analysis eigenvalues and variance contribution rates
the spectral angle matching method uses the reference spectrum in the spectral library to match the unknown sample, and uses the set narrow-sense spectral angle threshold value to judge the unknown sample. The formula is as follows:
Where T is the standard principal component score vector and R is the reference principal component score vector (T, R is both non-zero vectors).
Further, the spectral information of the hyperspectral image of the line push-broom imaging is compared with a spectral library established by supervision and classification, and an identification result is obtained.
the hyperspectral imaging-based classification identification method provided by the embodiment at least has the following beneficial effects:
1. By utilizing Savitzky-Golay filtering, the smoothness of a spectral curve is improved, and noise interference is reduced; the signal-to-noise ratio of the spectral signal is improved by utilizing multivariate scattering correction; both provide the basis for subsequent image processing work
2. and acquiring the spectral information of different substances by hyperspectral image acquisition. And establishing a spectrum library file, and storing sample spectrum information.
3. the method for analyzing the principal components is used for reducing the dimension, reducing the image calculation amount, eliminating the influence caused by non-important features and greatly reducing the calculation time. And matching unknown samples by using the reference spectrum in the spectrum library through a spectrum angle matching algorithm, and judging the unknown samples by using the set narrowly defined spectrum angle threshold value to finish the effective classification and identification of the tobacco leaves and the impurities, thereby obtaining a more accurate classification effect.
4. Compare in traditional artifical edulcoration, promoted work efficiency and detection speed. Meanwhile, more precise component information can be obtained by utilizing a hyperspectral imaging technology, and the resolution accuracy is improved.
the present invention has been described in detail with reference to the examples, but the present invention is not limited to the embodiments, and various changes, modifications, substitutions and alterations can be made without departing from the principle and spirit of the present invention within the knowledge of those skilled in the art. The scope of the invention is defined by the claims and their equivalents.
Claims (10)
1. A tobacco non-smoke substance classification method based on a hyperspectral imaging technology is characterized by comprising the following steps: tobacco leaves and impurities are classified by utilizing a short-wave hyperspectral imaging technology, a spectrum library comprising different substances is established, hyperspectral image data are collected for a sample to be detected, a reference spectrum in the spectrum library is used for matching the sample to be detected and judging the sample to be detected, and then effective classification and identification of the tobacco leaves and the impurities are completed.
2. The hyperspectral imaging technology-based tobacco non-smoke substance classification method according to claim 1, characterized in that: the method comprises the following specific steps:
1) Collecting samples: obtaining samples of first-class sundries, second-class sundries and third-class sundries including pure tobacco leaves;
2) Sample preparation and hyperspectral imaging are carried out, and black and white frame correction is carried out;
3) preprocessing a hyperspectral image and acquiring a characteristic image;
4) Extracting sample spectrum information and establishing a spectrum library file;
5) the tobacco leaf sundries are classified:
performing dimensionality reduction on a hyperspectral image of an acquired sample by adopting a Principal Component Analysis (PCA), matching a target spectrum by utilizing a spectral angle matching method (SAM), judging whether impurities are mixed in the tobacco sample or not according to a spectral feature vector, and marking different samples.
3. The tobacco non-smoke substance classification method based on the hyperspectral imaging technology according to claim 2, characterized in that: and 2) using a halogen tungsten lamp as an illumination light source, and performing hyperspectral image acquisition on the obtained tobacco leaf and sundry samples to obtain hyperspectral images of the samples. In order to reduce the noise influence, the hyperspectral image is corrected by a black and white frame correction formula as follows:
In the formula: r-a corrected hyperspectral image; i-an original hyperspectral image; b, closing the all-black image collected by the camera lens; w-scanning the white correction plate to obtain a full white image.
4. The tobacco non-smoke substance classification method based on the hyperspectral imaging technology according to claim 2, characterized in that: in step 3), in order to improve the signal-to-noise ratio of the data, the hyperspectral image data is preprocessed, and the preprocessing method includes but is not limited to:
By using a Savitzky-Golay convolution smoothing filtering algorithm, baseline drift and inclination are removed, noise is removed, and smoothness of a spectral curve is improved;
And then reducing the scattering effect on the surface of the object by Multivariate Scattering Correction (MSC) to enhance the spectral absorption information among the same substances.
5. the tobacco non-smoke substance classification method based on the hyperspectral imaging technology according to claim 2, characterized in that: in step 4), the specific processes include but are not limited to:
The tobacco leaf and sundries sample comprises: a pure tobacco leaf sample, a first class sundry sample, a second class sundry sample and a third class sundry sample;
Respectively selecting tobacco leaves and regions of interest (ROI) of the first, second and third sundries, extracting spectral characteristics at the selected region of interest of the sample, and obtaining an average spectrum;
and establishing a spectrum information library file, and importing the average spectrum obtained from the ROI area of the sample into the library file for storage.
6. The tobacco non-smoke substance classification method based on the hyperspectral imaging technology according to claim 2, characterized in that: the specific process in step 5) is as follows: the tobacco leaves mixed with the first, second and third impurities are subjected to image acquisition by a short wave hyperspectral imager, the acquired data are preprocessed and then compared with spectral information recorded in a spectral library, and the hyperspectral images are subjected to dimensionality reduction and characteristic identification of the tobacco leaves and the impurities by a Principal Component Analysis (PCA) and a Spectral Angle Matching (SAM) algorithm, wherein the method comprises the following steps:
Firstly, scanning and obtaining short-wave hyperspectral imaging information of the sample;
secondly, performing dimensionality reduction on the collected sample by adopting a principal component analysis method;
And finally, calculating by a spectral angle matching algorithm, judging whether impurities are mixed in the tobacco leaf sample according to the spectral feature vector, and marking different samples.
7. The hyperspectral imaging technology-based tobacco non-smoke substance classification method according to claim 4, characterized in that: the preprocessing method in step 3 may further adopt one of mean centering (mean centering), normalization (normalization), standard normal variable transformation (SNV), derivative, smooth denoising algorithm, and wavelet transformation.
8. The tobacco non-smoke substance classification method based on hyperspectral imaging technology according to claim 1 or 2, characterized in that: the sample surface remained dry and clean with no other attachments.
9. the tobacco non-smoke substance classification method based on hyperspectral imaging technology according to claim 1 or 2, characterized in that: the hyperspectral imager is used for hyperspectral imaging, the wavelength range is 1000-2500nm, the spectral resolution is 12nm, the image resolution is 384 × 288 pixels, and the spectrometer frame number is 400.
10. A tobacco non-smoke substance classification method based on hyperspectral imaging technology according to claim 2 or 5, characterized in that: the sundries comprise metal, feather and plastic; the second class of sundries comprises paper, stones, hemp ropes and glass; the three kinds of impurities comprise non-tobacco leaves, seeds and bamboo sticks.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910850623.0A CN110542658A (en) | 2019-09-10 | 2019-09-10 | tobacco non-smoke substance classification method based on hyperspectral imaging technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910850623.0A CN110542658A (en) | 2019-09-10 | 2019-09-10 | tobacco non-smoke substance classification method based on hyperspectral imaging technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110542658A true CN110542658A (en) | 2019-12-06 |
Family
ID=68713013
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910850623.0A Pending CN110542658A (en) | 2019-09-10 | 2019-09-10 | tobacco non-smoke substance classification method based on hyperspectral imaging technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110542658A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112189877A (en) * | 2020-10-13 | 2021-01-08 | 燕山大学 | On-line detection method for tobacco shred impurities in tobacco production line |
| CN112613413A (en) * | 2020-12-25 | 2021-04-06 | 平安国际智慧城市科技股份有限公司 | Perishable garbage classification quality determination method and device and computer readable storage medium |
| CN112697726A (en) * | 2020-12-09 | 2021-04-23 | 云南省烟草农业科学研究院 | Hyperspectral field tobacco nicotine content prediction method and system based on unmanned aerial vehicle |
| CN112697725A (en) * | 2020-12-09 | 2021-04-23 | 云南省烟草农业科学研究院 | Method and system for predicting total sugar content of tobacco leaves in field based on hyperspectrum of unmanned aerial vehicle |
| CN113210264A (en) * | 2021-05-19 | 2021-08-06 | 江苏鑫源烟草薄片有限公司 | Method and device for removing tobacco impurities |
| CN113237836A (en) * | 2021-05-10 | 2021-08-10 | 福建省烟草公司南平市公司 | Flue-cured tobacco leaf moisture content estimation method based on hyperspectral image |
| 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 |
| CN113655072A (en) * | 2021-08-20 | 2021-11-16 | 福建中烟工业有限责任公司 | Method, apparatus and computer readable medium for detecting contaminants on a surface of a sample |
| CN113681156A (en) * | 2021-06-24 | 2021-11-23 | 中国烟草总公司郑州烟草研究院 | Cigarette raw material slitting device and method based on ultraviolet laser |
| CN114155385A (en) * | 2021-11-30 | 2022-03-08 | 江苏鑫源烟草薄片有限公司 | Tobacco identification method based on deep learning RGB and hyperspectral |
| CN114486774A (en) * | 2021-12-31 | 2022-05-13 | 中科谱光(郑州)应用科学技术研究院有限公司 | Artificial intelligence algorithm matching method based on hyperspectral big data |
| CN114659994A (en) * | 2022-05-23 | 2022-06-24 | 武汉大学 | Tobacco foreign matter extraction and detection system |
| CN115128033A (en) * | 2022-07-04 | 2022-09-30 | 厦门烟草工业有限责任公司 | Tobacco leaf detection method, device and system and storage medium |
| CN115165772A (en) * | 2022-07-25 | 2022-10-11 | 江苏大学 | High-spectrum-based detection device and detection method for impurity content of grains |
| CN115165795A (en) * | 2022-06-28 | 2022-10-11 | 中国烟草总公司郑州烟草研究院 | Tobacco chemical composition prediction method and device based on spectrum conversion |
| CN115356297A (en) * | 2022-08-26 | 2022-11-18 | 中国烟草总公司郑州烟草研究院 | Method and device for identifying slight green of flue-cured tobacco leaves |
| CN115356275A (en) * | 2022-08-26 | 2022-11-18 | 中国烟草总公司郑州烟草研究院 | Tobacco leaf grade evaluation method |
| CN117611828A (en) * | 2024-01-19 | 2024-02-27 | 云南烟叶复烤有限责任公司 | Non-smoke sundry detection method based on hyperspectral image segmentation technology |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105842173A (en) * | 2016-06-06 | 2016-08-10 | 南京大学 | Method for identifying hyperspectral material |
| CN106501208A (en) * | 2016-09-20 | 2017-03-15 | 广西中烟工业有限责任公司 | A kind of tobacco style similitude sorting technique based near infrared light spectrum signature |
| CN107843593A (en) * | 2017-10-13 | 2018-03-27 | 上海工程技术大学 | A kind of textile material recognition methods and system based on high light spectrum image-forming technology |
| CN207379913U (en) * | 2017-10-19 | 2018-05-18 | 新疆农业大学 | A kind of moits detection device based on reflection and transmission high light spectrum image-forming |
-
2019
- 2019-09-10 CN CN201910850623.0A patent/CN110542658A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105842173A (en) * | 2016-06-06 | 2016-08-10 | 南京大学 | Method for identifying hyperspectral material |
| CN106501208A (en) * | 2016-09-20 | 2017-03-15 | 广西中烟工业有限责任公司 | A kind of tobacco style similitude sorting technique based near infrared light spectrum signature |
| CN107843593A (en) * | 2017-10-13 | 2018-03-27 | 上海工程技术大学 | A kind of textile material recognition methods and system based on high light spectrum image-forming technology |
| CN207379913U (en) * | 2017-10-19 | 2018-05-18 | 新疆农业大学 | A kind of moits detection device based on reflection and transmission high light spectrum image-forming |
Non-Patent Citations (1)
| Title |
|---|
| 赵冬娥等: "高光谱成像的垃圾分类识别研究", 《光谱学与光谱分析》 * |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112189877A (en) * | 2020-10-13 | 2021-01-08 | 燕山大学 | On-line detection method for tobacco shred impurities in tobacco production line |
| CN112697726A (en) * | 2020-12-09 | 2021-04-23 | 云南省烟草农业科学研究院 | Hyperspectral field tobacco nicotine content prediction method and system based on unmanned aerial vehicle |
| CN112697725A (en) * | 2020-12-09 | 2021-04-23 | 云南省烟草农业科学研究院 | Method and system for predicting total sugar content of tobacco leaves in field based on hyperspectrum of unmanned aerial vehicle |
| CN112613413A (en) * | 2020-12-25 | 2021-04-06 | 平安国际智慧城市科技股份有限公司 | Perishable garbage classification quality determination method and device and computer readable storage medium |
| CN113237836A (en) * | 2021-05-10 | 2021-08-10 | 福建省烟草公司南平市公司 | Flue-cured tobacco leaf moisture content estimation method based on hyperspectral image |
| CN113210264A (en) * | 2021-05-19 | 2021-08-06 | 江苏鑫源烟草薄片有限公司 | Method and device for removing tobacco impurities |
| CN113210264B (en) * | 2021-05-19 | 2023-09-05 | 江苏鑫源烟草薄片有限公司 | Tobacco sundry removing method and device |
| 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 |
| CN113681156A (en) * | 2021-06-24 | 2021-11-23 | 中国烟草总公司郑州烟草研究院 | Cigarette raw material slitting device and method based on ultraviolet laser |
| CN113681156B (en) * | 2021-06-24 | 2023-08-08 | 中国烟草总公司郑州烟草研究院 | Device and method for cutting raw materials for cigarettes based on ultraviolet laser |
| CN113655072B (en) * | 2021-08-20 | 2023-12-26 | 福建中烟工业有限责任公司 | Method, apparatus and computer readable medium for detecting contaminants on a sample surface |
| CN113655072A (en) * | 2021-08-20 | 2021-11-16 | 福建中烟工业有限责任公司 | Method, apparatus and computer readable medium for detecting contaminants on a surface of a sample |
| CN114155385A (en) * | 2021-11-30 | 2022-03-08 | 江苏鑫源烟草薄片有限公司 | Tobacco identification method based on deep learning RGB and hyperspectral |
| CN114155385B (en) * | 2021-11-30 | 2022-09-27 | 江苏鑫源烟草薄片有限公司 | Tobacco identification method based on deep learning RGB and hyperspectral |
| CN114486774A (en) * | 2021-12-31 | 2022-05-13 | 中科谱光(郑州)应用科学技术研究院有限公司 | Artificial intelligence algorithm matching method based on hyperspectral big data |
| CN114659994B (en) * | 2022-05-23 | 2022-08-05 | 武汉大学 | Tobacco foreign matter extraction and detection system |
| CN114659994A (en) * | 2022-05-23 | 2022-06-24 | 武汉大学 | Tobacco foreign matter extraction and detection system |
| CN115165795A (en) * | 2022-06-28 | 2022-10-11 | 中国烟草总公司郑州烟草研究院 | Tobacco chemical composition prediction method and device based on spectrum conversion |
| CN115128033A (en) * | 2022-07-04 | 2022-09-30 | 厦门烟草工业有限责任公司 | Tobacco leaf detection method, device and system and storage medium |
| CN115165772A (en) * | 2022-07-25 | 2022-10-11 | 江苏大学 | High-spectrum-based detection device and detection method for impurity content of grains |
| CN115356297A (en) * | 2022-08-26 | 2022-11-18 | 中国烟草总公司郑州烟草研究院 | Method and device for identifying slight green of flue-cured tobacco leaves |
| CN115356275A (en) * | 2022-08-26 | 2022-11-18 | 中国烟草总公司郑州烟草研究院 | Tobacco leaf grade evaluation method |
| CN117611828A (en) * | 2024-01-19 | 2024-02-27 | 云南烟叶复烤有限责任公司 | Non-smoke sundry detection method based on hyperspectral image segmentation technology |
| CN117611828B (en) * | 2024-01-19 | 2024-05-24 | 云南烟叶复烤有限责任公司 | Non-smoke sundry detection method based on hyperspectral image segmentation technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110542658A (en) | tobacco non-smoke substance classification method based on hyperspectral imaging technology | |
| Zhao et al. | Application of hyperspectral imaging and chemometrics for variety classification of maize seeds | |
| Weng et al. | Hyperspectral imaging for accurate determination of rice variety using a deep learning network with multi-feature fusion | |
| Chen et al. | Predicting the anthocyanin content of wine grapes by NIR hyperspectral imaging | |
| Liu et al. | Research on moisture content detection method during green tea processing based on machine vision and near-infrared spectroscopy technology | |
| CN109540831B (en) | Wolfberry variety identification method based on hyperspectral imaging technology | |
| Li et al. | Hyperspectral imaging and their applications in the nondestructive quality assessment of fruits and vegetables | |
| Singh et al. | Nondestructive identification of barley seeds variety using near‐infrared hyperspectral imaging coupled with convolutional neural network | |
| Bauriegel et al. | Early detection of Fusarium infection in wheat using hyper-spectral imaging | |
| CN110763698B (en) | Hyperspectral citrus leaf disease identification method based on characteristic wavelength | |
| Yang et al. | Multispectral image based germination detection of potato by using supervised multiple threshold segmentation model and Canny edge detector | |
| CN113390799B (en) | Method for identifying and detecting stems in tobacco leaves | |
| Marcelo et al. | Fast inline tobacco classification by near-infrared hyperspectral imaging and support vector machine-discriminant analysis | |
| CN110376202B (en) | Tea tree anthracnose lesion identification method based on imaging hyperspectral technology | |
| Wang et al. | Spatial distribution of total polyphenols in multi-type of tea using near-infrared hyperspectral imaging | |
| Xu et al. | A polarized hyperspectral imaging system for in vivo detection: Multiple applications in sunflower leaf analysis | |
| Chen et al. | Quality detection and variety classification of pecan seeds using hyperspectral imaging technology combined with machine learning | |
| Wen et al. | Visualization of chlorophyll content distribution in apple leaves based on hyperspectral imaging technology | |
| JP2019190927A (en) | Analysis system, image capturing device, and program | |
| Long et al. | Application of hyperspectral imaging technology in classification of tobacco leaves and impurities | |
| CN115931738B (en) | Method and system for evaluating quality stability of finished tobacco flakes | |
| Cheng et al. | Identification of wine grape varieties based on near-infrared hyperspectral imaging | |
| CN113970531A (en) | Method for correcting spectrum | |
| Shi et al. | Application of spectral features for separating homochromatic foreign matter from mixed congee | |
| Xu et al. | Detection of Cucumber Powdery Mildew Based on Spectral and Image Information |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191206 |