CN112539785A - Tobacco grade identification system and method based on multi-dimensional characteristic information - Google Patents
Tobacco grade identification system and method based on multi-dimensional characteristic information Download PDFInfo
- Publication number
- CN112539785A CN112539785A CN202011460291.4A CN202011460291A CN112539785A CN 112539785 A CN112539785 A CN 112539785A CN 202011460291 A CN202011460291 A CN 202011460291A CN 112539785 A CN112539785 A CN 112539785A
- Authority
- CN
- China
- Prior art keywords
- grade
- module
- tobacco
- tobacco leaves
- leaf
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Manufacture Of Tobacco Products (AREA)
Abstract
The invention relates to a tobacco grade identification system and method based on multi-dimensional characteristic information, and belongs to the technical field of tobacco grade identification. The system comprises a central processing module, an image acquisition module, an image processing module, a thickness measuring module, a weighing module, an information input module and a grade output module; the central processing module is respectively connected with the image processing module, the thickness measuring module, the weighing module, the information input module and the grade output module; the tobacco grade judging model is established based on the image characteristics, the weight, the thickness, the image extraction physical indexes, the chemical component indexes and other multidimensional indexes, so that the tobacco grade is accurately, quickly and automatically identified and determined, the dimensionality indexes are more, the information is richer, and the identification accuracy is higher.
Description
Technical Field
The invention belongs to the technical field of tobacco leaf grade identification, and particularly relates to a tobacco leaf grade identification system and method based on multi-dimensional characteristic information.
Background
In the tobacco industry, the quality detection of tobacco leaves has important significance. With the upgrade and innovation of Chinese cigarette brands entering a new development stage, cigarette brand development and product innovation put forward new higher and more difficult requirements on threshing and redrying, and industrial enterprises pay more and more attention to raw cigarette selection.
The existing tobacco grade identification method adopts an artificial or machine identification mode, and the tobacco grade identification can be different due to different eye light of each person in artificial selection. The machine identification mainly carries out the identification and the affirmation of tobacco leaf grade through the AI artificial intelligence operation based on image characteristics, and the dimension index is less, only utilizes the color and the shape of the image, and the error rate is higher.
For example, 201811528533.1A method for intelligent purchasing tobacco leaves and a system thereof, the method comprises the following steps: a. acquiring the identity information of the selling party and verifying the identity; b. preliminarily inspecting the tobacco leaf products, grading the tobacco leaf products subjected to preliminary inspection, and setting RFID tag cards of corresponding grades; c. automatically transmitting the weighing, collecting the current weighing image, and reading the information of the RFID tag card; d. and (5) code scanning and unbinding are carried out, and after the two-dimensional codes are associated, the codes are packed and put in storage. This patent application adopts the manual work to carry out the rating to tobacco leaf product, exists because of artifical eye light difference, and the difference that produces the rating.
For another example, 201410001552.4 an automatic grading system based on massive tobacco leaf data, the system analyzes and preprocesses the tobacco leaf image, keeps the image part concerned by vision, removes noise, then extracts the relevant detail feature of tobacco leaf, guarantees the sparsity and relevance of data; then, acquiring different types of tobacco leaf characteristic data from a tobacco leaf characteristic database, constructing a model, and finally grading the tobacco leaves by adopting the constructed model; the technical scheme identifies the tobacco grade through the image, has single dimension index, can distinguish the parts, but can not distinguish the green and the impurity and the tobacco of the adjacent grade, has not good effect,
therefore, how to overcome the defects of the prior art is a problem to be solved urgently in the technical field of tobacco grade identification at present.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a tobacco grade identification system and method based on multi-dimensional characteristic information.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a tobacco leaf grade identification system based on multi-dimensional characteristic information comprises: the device comprises a central processing module, an image acquisition module, an image processing module, a thickness measuring module, a weighing module, an information input module and a grade output module;
the central processing module is respectively connected with the image processing module, the thickness measuring module, the weighing module, the information input module and the grade output module;
the image acquisition module is used for acquiring images of the front side and the back side of the tobacco leaf;
the image processing module is connected with the image acquisition module and used for processing according to the image acquired by the image acquisition module to obtain the length, width, area, tip included angle, pulse phase and color value ratio of the tobacco leaves; the thickness measuring module is used for acquiring the thickness information of the tobacco leaves;
the weighing module is used for collecting the weight of the tobacco leaves;
the information input module is used for inputting the grade qualification rate and grade purity index data of the tobacco leaves;
a tobacco grade judgment model is prestored in the central processing module, and an upper adjacent grade and a lower adjacent grade of the original grade of the flue-cured tobacco and the corresponding purity tolerance range of the original grade of the flue-cured tobacco are also prestored; the central processing module is used for identifying the grade of a certain batch of tobacco leaves according to the data obtained after the processing of the image processing module, the data measured by the thickness measuring module, the data measured by the weighing module and the data input by the information input module, and then outputting the grade through the grade output module.
Further, preferably, the grade output module is a USB interface; the image acquisition module is a camera; the thickness measuring module is a laser thickness gauge.
Further, preferably, the tobacco leaf batch further comprises a display module, wherein the display module is connected with the grade output module and is used for displaying the image of each tobacco leaf in the batch of tobacco leaves, the length, the width, the area, the tip included angle, the pulse phase, the color value, the thickness and the weight of the tobacco leaves and the identification grade of the batch of tobacco leaves.
Further, preferably, the construction method of the tobacco grade determination model is as follows: taking the length, width, area, tip included angle, pulse phase, color value ratio, thickness and weight of the tobacco leaves as input, taking the grade of the tobacco leaves as output, and training a BP neural network model until the prediction precision of the BP neural network model meets the requirement, wherein the obtained BP neural network model is the tobacco leaf grade judgment model; the color proportion of the color value is the proportion of lemon yellow, orange yellow and red brown in the tobacco leaf, and the proportion of other colors except the lemon yellow, orange yellow and red brown; the pulse phase is the average value of the diameters of the main pulses at the leaf apex, the leaf lobe and the leaf base, and the ratio of the covered pulse phase to the total pulse phase; the thickness comprises the thickness of a blade tip, a blade leaf and a blade base.
Further, preferably, the BP neural network model includes an input layer, a hidden layer and an output layer, [ x, y ] is a sample p, and x = [ x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13, x14] is the length, width, area, tip angle, average value of main vein diameter, ratio of covered vein phases to total vein phases, ratio of lemon yellow to orange to yellow to red brown to other colors to tip thickness, leaf base thickness, weight, y = [ y1] is the grade of the tobacco leaf;
the training of the BP neural network model comprises the following steps: reading sample data and carrying out forward propagation; checking whether the prediction precision of the BP neural network model meets the preset precision requirement or not; if not, performing backward propagation, and then returning to the step of performing forward propagation; if so, ending the process of learning and training.
Further, preferably, a cat swarm algorithm is used for optimizing the weight and the threshold of the BP neural network.
Further, it is preferable that the grade yield = (number of original grade tobacco leaves/total tobacco leaves) × 100%;
grade purity = (original grade tobacco leaf number + adjacent grade tobacco leaf number within purity tolerance range)/total tobacco leaf number of the selected tobacco leaf × 100%;
and if the grade qualified rate obtained by detection is lower than the grade qualified rate input by the information input module, outputting the grade of all the tobacco leaves by the grade output module when the grade output module outputs the grade, and prompting that the grade qualified rate of the batch of tobacco leaves is lower.
And if the grade purity obtained by detection is lower than the grade purity input by the information input module, outputting the grade of all the tobacco leaves by the grade output module when the grade output module outputs the grade, and prompting that the grade purity of the batch of tobacco leaves is relatively low.
Further, preferably, the system also comprises a near infrared spectrum detection module and a chemical component analysis module; the chemical component analysis module is respectively connected with the near infrared spectrum detection module and the central processing module;
the near infrared spectrum acquisition module is used for acquiring the near infrared spectrum of the tobacco leaves;
the chemical component analysis module is used for analyzing according to the near infrared spectrum of the tobacco leaves to obtain the chemical components of the tobacco leaves;
the central processing module is internally pre-stored with the range values of the chemical components of the tobacco leaves of each grade; if the chemical components of the tobacco leaves obtained by the analysis of the chemical component analysis module are lower than the pre-stored range value, when the grade output module outputs the chemical components, the grades of all the tobacco leaves are output after the tobacco leaves are planed, and the unqualified chemical components of the tobacco leaves are prompted;
the chemical components include total sugar, reducing sugar, total nitrogen, nicotine, potassium and chlorine content.
The invention also provides a tobacco grade identification method based on multi-dimensional characteristic information, which adopts the tobacco grade identification system based on the multi-dimensional characteristic information and comprises the following steps:
step (1), sample preparation: spreading each tobacco leaf in the batch to be detected in a standard environment;
step (2), image acquisition and processing: acquiring images of the front and back of each tobacco leaf on line in a standard environment, and extracting the length, width, area, tip included angle, pulse phase and color value ratio of the tobacco leaf from the images;
and (3) measuring key physical property indexes: under a standard environment, measuring the thickness of each piece of tobacco leaves on line through a thickness measuring module, and measuring the weight of each piece of tobacco leaves on line through a weight detection device;
and (4) inputting the grade qualification rate and the grade purity into a tobacco grade judgment model, and judging through the information of each tobacco leaf extracted in the step (2) and the information of each tobacco leaf measured in the step (3) to obtain the grade of the batch of tobacco leaves.
Further, it is preferable that the standard environment is a light source having a color temperature of (5500 + -100) K, an illuminance of (2000 + -200) lx, and a color rendering index RaNot less than 92; the ambient temperature is (22 +/-2) DEG C, and the relative humidity is (70 +/-5)%.
Compared with the prior art, the invention has the beneficial effects that:
the tobacco grade judging model is established based on the image characteristics, the weight, the thickness, the image extraction physical indexes, the chemical component indexes and other multidimensional indexes, so that the tobacco grade is accurately, quickly and automatically identified and determined, the dimensionality indexes are more, the information is richer, and the identification accuracy is higher.
The invention solves the problems that the subjective judgment has volatility and the efficiency is low when the tobacco grade is manually identified; the problem that the identification model index is single and the tobacco grade identification accuracy is low when the machine identifies the tobacco grade is also solved, a unified tobacco grade identification standard is established, online rapid detection can be realized, and the machine is easy to popularize and apply.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a tobacco leaf grade identification system based on multi-dimensional feature information in embodiment 1;
FIG. 2 is a schematic structural diagram of a tobacco leaf grade identification system based on multi-dimensional feature information in embodiment 2-3;
fig. 3 is a schematic structural diagram of a tobacco leaf grade identification system based on multi-dimensional feature information in embodiment 4;
wherein, 1, a central processing module; 2. an image acquisition module; 3. an image processing module; 4. a thickness measuring module; 5. a weighing module; 6. an information input module; 7. a grade output module; 8. a display module; 9. a near infrared spectrum acquisition module; 10. a chemical composition analysis module;
FIG. 4 is an image of a certain tobacco leaf collected from a tobacco leaf of which the identification result is X2F grade in an application example; wherein (a) is the front; (b) is a back surface;
FIG. 5 is a near infrared spectrum of the tobacco leaf of FIG. 4;
FIG. 6 is an image of a certain tobacco leaf collected from a certain identification result of C3F grade tobacco leaf in an application example; wherein (a) is the front; (b) is a back surface;
FIG. 7 is a near infrared spectrum of the tobacco leaf of FIG. 6;
FIG. 8 is an image of a certain tobacco leaf collected from a certain identified tobacco leaf with a grade B2F in an application example; wherein (a) is the front; (b) is a back surface;
FIG. 9 is a near infrared spectrum of the tobacco leaf of FIG. 8.
Detailed Description
The present invention will be described in further detail with reference to examples.
It will be appreciated by those skilled in the art that the following examples are illustrative of the invention only and should not be taken as limiting the scope of the invention. The examples do not specify particular techniques or conditions, and are performed according to the techniques or conditions described in the literature in the art or according to the product specifications. The materials or equipment used are not indicated by manufacturers, and all are conventional products available by purchase.
It will be appreciated by those skilled in the art that the following examples are illustrative of the invention only and should not be taken as limiting the scope of the invention. The specific techniques, connections, conditions, or the like, which are not specified in the examples, are performed according to the techniques, connections, conditions, or the like described in the literature in the art or according to the product specification. The materials, instruments or equipment are not indicated by manufacturers, and all the materials, instruments or equipment are conventional products which can be obtained by purchasing.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present. Further, "connected" as used herein may include wirelessly connected.
In the description of the present invention, "a plurality" means two or more unless otherwise specified. The terms "inner," "upper," "lower," and the like, refer to an orientation or a state relationship based on that shown in the drawings, which is for convenience in describing and simplifying the description, and do not indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the invention.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "provided" are to be construed broadly, e.g., as being fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; may be directly connected or indirectly connected through an intermediate. To those of ordinary skill in the art, the specific meanings of the above terms in the present invention are understood according to specific situations.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Example 1
As shown in fig. 1, a tobacco grade identification system based on multi-dimensional feature information includes: the device comprises a central processing module 1, an image acquisition module 2, an image processing module 3, a thickness measuring module 4, a weighing module 5, an information input module 6 and a grade output module 7;
the central processing module 1 is respectively connected with the image processing module 3, the thickness measuring module 4, the weighing module 5, the information input module 6 and the grade output module 7;
the image acquisition module 2 is used for acquiring images of the front and back of the tobacco leaves;
the image processing module 3 is connected with the image acquisition module 2 and used for processing according to the image acquired by the image acquisition module to obtain the length, width, area, tip included angle, pulse phase and color value ratio of the tobacco leaves; the thickness measuring module 4 is used for acquiring thickness information of the tobacco leaves;
the weighing module 5 is used for collecting the weight of the tobacco leaves;
the information input module 6 is used for inputting the grade qualification rate and grade purity index data of the tobacco leaves;
a tobacco grade judging model is prestored in the central processing module 1, and an upper adjacent grade and a lower adjacent grade of the original grade of the flue-cured tobacco and the corresponding purity tolerance range of the original grade of the flue-cured tobacco are also prestored; the central processing module 1 is used for identifying the grade of a certain batch of tobacco leaves according to the data processed by the image processing module 3, the data measured by the thickness measuring module 4, the data measured by the weighing module 5 and the data input by the information input module 6, and then outputting the grade through the grade output module 7.
A tobacco grade identification method based on multi-dimensional characteristic information adopts the tobacco grade identification system based on the multi-dimensional characteristic information, and comprises the following steps:
step (1), sample preparation: spreading each tobacco leaf in the batch to be detected in a standard environment;
step (2), image acquisition and processing: acquiring images of the front and back of each tobacco leaf on line in a standard environment, and extracting the length, width, area, tip included angle, pulse phase and color value ratio of the tobacco leaf from the images;
and (3) measuring key physical property indexes: under a standard environment, measuring the thickness of each piece of tobacco leaves on line through a thickness measuring module, and measuring the weight of each piece of tobacco leaves on line through a weight detection device;
and (4) inputting the grade qualification rate and the grade purity into a tobacco grade judgment model, and judging through the information of each tobacco leaf extracted in the step (2) and the information of each tobacco leaf measured in the step (3) to obtain the grade of the batch of tobacco leaves.
Example 2
As shown in fig. 2, a tobacco grade identification system based on multi-dimensional feature information includes: the device comprises a central processing module 1, an image acquisition module 2, an image processing module 3, a thickness measuring module 4, a weighing module 5, an information input module 6 and a grade output module 7;
the central processing module 1 is respectively connected with the image processing module 3, the thickness measuring module 4, the weighing module 5, the information input module 6 and the grade output module 7;
the image acquisition module 2 is used for acquiring images of the front and back of the tobacco leaves;
the image processing module 3 is connected with the image acquisition module 2 and used for processing according to the image acquired by the image acquisition module to obtain the length, width, area, tip included angle, pulse phase and color value ratio of the tobacco leaves; the thickness measuring module 4 is used for acquiring thickness information of the tobacco leaves;
the weighing module 5 is used for collecting the weight of the tobacco leaves;
the information input module 6 is used for inputting the grade qualification rate and grade purity index data of the tobacco leaves;
a tobacco grade judging model is prestored in the central processing module 1, and an upper adjacent grade and a lower adjacent grade of the original grade of the flue-cured tobacco and the corresponding purity tolerance range of the original grade of the flue-cured tobacco are also prestored; the central processing module 1 is used for identifying the grade of a certain batch of tobacco leaves according to the data processed by the image processing module 3, the data measured by the thickness measuring module 4, the data measured by the weighing module 5 and the data input by the information input module 6, and then outputting the grade through the grade output module 7.
The grade output module 7 is a USB interface; the image acquisition module 2 is a camera; the thickness measuring module 4 is a laser thickness gauge.
The tobacco leaf batch recognition system further comprises a display module 8, wherein the display module 8 is connected with the grade output module 7 and used for displaying the image of each tobacco leaf in the batch of tobacco leaves, the length, the width, the area, the included angle of the leaf tips, the vein phase, the color value, the thickness and the weight of the tobacco leaves and the recognition grade of the batch of tobacco leaves.
A tobacco grade identification method based on multi-dimensional characteristic information adopts the tobacco grade identification system based on the multi-dimensional characteristic information, and comprises the following steps:
step (1), sample preparation: spreading each tobacco leaf in the batch to be detected in a standard environment;
step (2), image acquisition and processing: acquiring images of the front and back of each tobacco leaf on line in a standard environment, and extracting the length, width, area, tip included angle, pulse phase and color value ratio of the tobacco leaf from the images;
and (3) measuring key physical property indexes: under a standard environment, measuring the thickness of each piece of tobacco leaves on line through a thickness measuring module, and measuring the weight of each piece of tobacco leaves on line through a weight detection device;
and (4) inputting the grade qualification rate and the grade purity into a tobacco grade judgment model, and judging through the information of each tobacco leaf extracted in the step (2) and the information of each tobacco leaf measured in the step (3) to obtain the grade of the batch of tobacco leaves.
Example 3
As shown in fig. 2, a tobacco grade identification system based on multi-dimensional feature information includes: the device comprises a central processing module 1, an image acquisition module 2, an image processing module 3, a thickness measuring module 4, a weighing module 5, an information input module 6 and a grade output module 7;
the central processing module 1 is respectively connected with the image processing module 3, the thickness measuring module 4, the weighing module 5, the information input module 6 and the grade output module 7;
the image acquisition module 2 is used for acquiring images of the front and back of the tobacco leaves;
the image processing module 3 is connected with the image acquisition module 2 and used for processing according to the image acquired by the image acquisition module to obtain the length, width, area, tip included angle, pulse phase and color value ratio of the tobacco leaves; the thickness measuring module 4 is used for acquiring thickness information of the tobacco leaves;
the weighing module 5 is used for collecting the weight of the tobacco leaves;
the information input module 6 is used for inputting the grade qualification rate and grade purity index data of the tobacco leaves;
a tobacco grade judging model is prestored in the central processing module 1, and an upper adjacent grade and a lower adjacent grade of the original grade of the flue-cured tobacco and the corresponding purity tolerance range of the original grade of the flue-cured tobacco are also prestored; the central processing module 1 is used for identifying the grade of a certain batch of tobacco leaves according to the data processed by the image processing module 3, the data measured by the thickness measuring module 4, the data measured by the weighing module 5 and the data input by the information input module 6, and then outputting the grade through the grade output module 7.
The grade output module 7 is a USB interface; the image acquisition module 2 is a camera; the thickness measuring module 4 is a laser thickness gauge.
The tobacco leaf batch recognition system further comprises a display module 8, wherein the display module 8 is connected with the grade output module 7 and used for displaying the image of each tobacco leaf in the batch of tobacco leaves, the length, the width, the area, the included angle of the leaf tips, the vein phase, the color value, the thickness and the weight of the tobacco leaves and the recognition grade of the batch of tobacco leaves.
The construction method of the tobacco grade judgment model comprises the following steps: taking the length, width, area, tip included angle, pulse phase, color value ratio, thickness and weight of the tobacco leaves as input, taking the grade of the tobacco leaves as output, and training a BP neural network model until the prediction precision of the BP neural network model meets the requirement, wherein the obtained BP neural network model is the tobacco leaf grade judgment model; the color proportion of the color value is the proportion of lemon yellow, orange yellow and red brown in the tobacco leaf, and the proportion of other colors except the lemon yellow, orange yellow and red brown; the pulse phase is the average value of the diameters of the main pulses at the leaf apex, the leaf lobe and the leaf base, and the ratio of the covered pulse phase to the total pulse phase; the thickness comprises the thickness of a blade tip, a blade leaf and a blade base.
A tobacco grade identification method based on multi-dimensional characteristic information adopts the tobacco grade identification system based on the multi-dimensional characteristic information, and comprises the following steps:
step (1), sample preparation: spreading each tobacco leaf in the batch to be detected in a standard environment;
step (2), image acquisition and processing: acquiring images of the front and back of each tobacco leaf on line in a standard environment, and extracting the length, width, area, tip included angle, pulse phase and color value ratio of the tobacco leaf from the images;
and (3) measuring key physical property indexes: under a standard environment, measuring the thickness of each piece of tobacco leaves on line through a thickness measuring module, and measuring the weight of each piece of tobacco leaves on line through a weight detection device;
and (4) inputting the grade qualification rate and the grade purity into a tobacco grade judgment model, and judging through the information of each tobacco leaf extracted in the step (2) and the information of each tobacco leaf measured in the step (3) to obtain the grade of the batch of tobacco leaves.
Example 4
As shown in fig. 3, a tobacco grade identification system based on multi-dimensional feature information includes: the device comprises a central processing module 1, an image acquisition module 2, an image processing module 3, a thickness measuring module 4, a weighing module 5, an information input module 6 and a grade output module 7;
the central processing module 1 is respectively connected with the image processing module 3, the thickness measuring module 4, the weighing module 5, the information input module 6 and the grade output module 7;
the image acquisition module 2 is used for acquiring images of the front and back of the tobacco leaves;
the image processing module 3 is connected with the image acquisition module 2 and used for processing according to the image acquired by the image acquisition module to obtain the length, width, area, tip included angle, pulse phase and color value ratio of the tobacco leaves; the thickness measuring module 4 is used for acquiring thickness information of the tobacco leaves;
the weighing module 5 is used for collecting the weight of the tobacco leaves;
the information input module 6 is used for inputting the grade qualification rate and grade purity index data of the tobacco leaves;
a tobacco grade judgment model is prestored in the central processing module 1, and an upper adjacent grade and a lower adjacent grade of the original grade of the cured tobacco and the corresponding purity tolerance range of the original grade of the cured tobacco are also prestored, as shown in table 1; the central processing module 1 is used for identifying the grade of a certain batch of tobacco leaves according to the data processed by the image processing module 3, the data measured by the thickness measuring module 4, the data measured by the weighing module 5 and the data input by the information input module 6, and then outputting the grade through the grade output module 7.
The grade output module 7 is a USB interface; the image acquisition module 2 is a camera; the thickness measuring module 4 is a laser thickness gauge.
The tobacco leaf batch recognition system further comprises a display module 8, wherein the display module 8 is connected with the grade output module 7 and used for displaying the image of each tobacco leaf in the batch of tobacco leaves, the length, the width, the area, the included angle of the leaf tips, the vein phase, the color value, the thickness and the weight of the tobacco leaves and the recognition grade of the batch of tobacco leaves.
The construction method of the tobacco grade judgment model comprises the following steps: taking the length, width, area, tip included angle, pulse phase, color value ratio, thickness and weight of the tobacco leaves as input, taking the grade of the tobacco leaves as output, and training a BP neural network model until the prediction precision of the BP neural network model meets the requirement, wherein the obtained BP neural network model is the tobacco leaf grade judgment model; the color proportion of the color value is the proportion of lemon yellow, orange yellow and red brown in the tobacco leaf, and the proportion of other colors except the lemon yellow, orange yellow and red brown; the pulse phase is the average value of the diameters of the main pulses at the leaf apex, the leaf lobe and the leaf base, and the ratio of the covered pulse phase to the total pulse phase; the thickness comprises the thickness of a blade tip, a blade leaf and a blade base.
The BP neural network model comprises an input layer, a hidden layer and an output layer, [ x, y ] is a sample p, x = [ x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13 and x14] is the length, width, area, tip angle, average value of main vein diameter, ratio of covered vein to total vein, lemon yellow ratio, orange yellow ratio, red-brown ratio, other color ratios, tip thickness, leaf base thickness and weight of the tobacco leaf, and y = [ y1] is the grade of the tobacco leaf;
the training of the BP neural network model comprises the following steps: reading sample data and carrying out forward propagation; checking whether the prediction precision of the BP neural network model meets the preset precision requirement or not; if not, performing backward propagation, and then returning to the step of performing forward propagation; if so, ending the process of learning and training.
And optimizing the weight and the threshold of the BP neural network by using a cat swarm algorithm.
Grade yield = (original grade tobacco leaf number/total tobacco leaf number) × 100%;
grade purity = (original grade tobacco leaf number + adjacent grade tobacco leaf number within purity tolerance range)/total tobacco leaf number of the selected tobacco leaf × 100%;
and if the grade qualified rate obtained by detection is lower than the grade qualified rate input by the information input module 6, outputting the grade of all the tobacco leaves by the grade output module 7, and prompting that the grade qualified rate of the batch of tobacco leaves is lower.
And if the detected grade purity is lower than the grade purity input by the information input module 6, outputting the grade of all the tobacco leaves by the grade output module 7, and prompting that the grade purity of the batch of tobacco leaves is relatively low.
The device also comprises a near infrared spectrum detection module 9 and a chemical component analysis module 10; the chemical component analysis module 10 is respectively connected with the near infrared spectrum detection module 9 and the central processing module 1;
the near infrared spectrum acquisition module 9 is used for acquiring the near infrared spectrum of the tobacco leaves;
the chemical component analysis module 10 is used for analyzing according to the near infrared spectrum of the tobacco leaves to obtain the chemical components of the tobacco leaves;
the central processing module 1 is internally pre-stored with the range values of the chemical components of the tobacco leaves of each grade; if the chemical components of the tobacco leaves obtained by the analysis of the chemical component analysis module 10 are lower than the pre-stored range value, when the grade output module 7 outputs the chemical components, the grades of all the tobacco leaves are output after the tobacco leaves are planed, and the unqualified chemical components of the tobacco leaves are prompted;
the chemical components include total sugar, reducing sugar, total nitrogen, nicotine, potassium and chlorine content.
A tobacco grade identification method based on multi-dimensional characteristic information adopts the tobacco grade identification system based on the multi-dimensional characteristic information, and comprises the following steps:
step (1), sample preparation: spreading each tobacco leaf in the batch to be detected in a standard environment;
step (2), image acquisition and processing: acquiring images of the front and back of each tobacco leaf on line in a standard environment, and extracting the length, width, area, tip included angle, pulse phase and color value ratio of the tobacco leaf from the images;
and (3) measuring key physical property indexes: under a standard environment, measuring the thickness of each piece of tobacco leaves on line through a thickness measuring module, and measuring the weight of each piece of tobacco leaves on line through a weight detection device;
and (4) inputting the grade qualification rate and the grade purity into a tobacco grade judgment model, and judging through the information of each tobacco leaf extracted in the step (2) and the information of each tobacco leaf measured in the step (3) to obtain the grade of the batch of tobacco leaves.
The standard environment is that the color temperature of the light source is (5500 +/-100) K, the illuminance is (2000 +/-200) lx, and the color rendering index RaNot less than 92; the ambient temperature is (22 +/-2) DEG C, and the relative humidity is (70 +/-5)%.
TABLE 1
Note: the above level symbols are all expressed according to the current standard.
Examples of the applications
The method and the system of embodiment 4 are adopted to identify the grade of the tobacco leaf sample in the red river state of Yunnan province.
The following were all performed under standard circumstances:
step one, sample preparation: spreading each tobacco leaf in the batch to be detected in a standard environment;
secondly, image acquisition and processing: acquiring images of the front and back of each tobacco leaf on line in a standard environment, and extracting the length, width, area, tip included angle, pulse phase and color value ratio of the tobacco leaf from the images; part of the acquired images are shown in fig. 4, 5 and 8; the collected partial data are shown in table 1;
thirdly, measuring key physical characteristic indexes: under a standard environment, measuring the thickness of each piece of tobacco leaves on line through a thickness measuring module, and measuring the weight of each piece of tobacco leaves on line through a weight detection device;
fourthly, the near infrared spectrum of the tobacco leaves is scanned in a line mode, and chemical components (total sugar, reducing sugar, total nitrogen, nicotine, potassium and chlorine content) of the tobacco leaves are predicted; a portion of the collected spectra are shown in fig. 5, 7 and 9; the obtained data of the chemical components of the tobacco leaves are shown in a table 2;
and fifthly, inputting the grade qualification rate and the grade purity into a tobacco grade judgment model, judging through the information of each tobacco leaf extracted in the second step, the information of each tobacco leaf measured in the third step and the chemical components of the tobacco leaves obtained in the fourth step, obtaining the grade of the batch of tobacco leaves and outputting.
By identifying 200 tobacco leaves, the identification result is consistent with the manual identification result, and the accuracy is 11% higher than that of the visual machine identification result based on image identification.
TABLE 1
TABLE 2
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. A tobacco grade identification system based on multi-dimensional characteristic information is characterized by comprising the following components: the device comprises a central processing module (1), an image acquisition module (2), an image processing module (3), a thickness measuring module (4), a weighing module (5), an information input module (6) and a grade output module (7);
the central processing module (1) is respectively connected with the image processing module (3), the thickness measuring module (4), the weighing module (5), the information input module (6) and the grade output module (7);
the image acquisition module (2) is used for acquiring images of the front side and the back side of the tobacco leaf;
the image processing module (3) is connected with the image acquisition module (2) and is used for processing according to the image acquired by the image acquisition module to obtain the length, width, area, tip included angle, pulse phase and color value ratio of the tobacco leaves; the thickness measuring module (4) is used for acquiring the thickness information of the tobacco leaves;
the weighing module (5) is used for collecting the weight of the tobacco leaves;
the information input module (6) is used for inputting the grade qualification rate and grade purity index data of the tobacco leaves;
a tobacco grade judgment model is prestored in the central processing module (1), and an upper adjacent grade and a lower adjacent grade of a tobacco raw grade and a corresponding purity tolerance range are also prestored; the central processing module (1) is used for identifying the grade of a certain batch of tobacco leaves according to the data obtained after the processing of the image processing module (3), the data measured by the thickness measuring module (4), the data measured by the weighing module (5) and the data input by the information input module (6), and then outputting the grade through the grade output module (7).
2. The tobacco grade identification system based on multi-dimensional characteristic information according to claim 1, wherein the grade output module (7) is a USB interface; the image acquisition module (2) is a camera; the thickness measuring module (4) is a laser thickness gauge.
3. The tobacco grade identification system based on the multi-dimensional characteristic information according to claim 1, further comprising a display module (8), wherein the display module (8) is connected with the grade output module (7) and is used for displaying the image of each tobacco leaf in the batch of tobacco leaves, the length, the width, the area, the tip included angle, the vein phase, the color value, the thickness and the weight of the tobacco leaves and the identification grade of the batch of tobacco leaves.
4. The tobacco grade identification system based on multi-dimensional characteristic information according to claim 1, wherein the tobacco grade judgment model is constructed by the following steps: taking the length, width, area, tip included angle, pulse phase, color value ratio, thickness and weight of the tobacco leaves as input, taking the grade of the tobacco leaves as output, and training a BP neural network model until the prediction precision of the BP neural network model meets the requirement, wherein the obtained BP neural network model is the tobacco leaf grade judgment model; the color proportion of the color value is the proportion of lemon yellow, orange yellow and red brown in the tobacco leaf, and the proportion of other colors except the lemon yellow, orange yellow and red brown; the pulse phase is the average value of the diameters of the main pulses at the leaf apex, the leaf lobe and the leaf base, and the ratio of the covered pulse phase to the total pulse phase; the thickness comprises the thickness of a blade tip, a blade leaf and a blade base.
5. The tobacco grade identifying system based on multi-dimensional characteristic information according to claim 4, wherein the BP neural network model comprises an input layer, a hidden layer and an output layer, [ x, y ] is a sample p, x = [ x1, x2, x3, x4, x5, x6, x7, x8, x9, x10, x11, x12, x13, x14] is the length, width, area, tip angle, average value of main vein diameter, ratio of covered vein to total vein phase, lemon yellow ratio, orange yellow ratio, red brown ratio, other color ratio, tip thickness, leaf base thickness, weight, y = [ y1] is the grade of tobacco;
the training of the BP neural network model comprises the following steps: reading sample data and carrying out forward propagation; checking whether the prediction precision of the BP neural network model meets the preset precision requirement or not; if not, performing backward propagation, and then returning to the step of performing forward propagation; if so, ending the process of learning and training.
6. The tobacco grade identification system based on multi-dimensional feature information according to claim 5, wherein a cat swarm algorithm is applied to optimize BP neural network weights and thresholds.
7. The tobacco grade identification system based on multi-dimensional characteristic information according to claim 1, wherein the grade yield = (original grade tobacco leaf number/total tobacco leaf number) × 100%;
grade purity = (original grade tobacco leaf number + adjacent grade tobacco leaf number within purity tolerance range)/total tobacco leaf number of the selected tobacco leaf × 100%;
if the grade qualified rate obtained by detection is lower than the grade qualified rate input by the information input module (6), when the grade output module (7) outputs the grade, the grades of all the tobacco leaves are output, and the grade qualified rate of the batch of the tobacco leaves is prompted to be lower;
and if the grade purity obtained by detection is lower than the grade purity input by the information input module (6), outputting the grade of all the tobacco leaves by the grade output module (7), and prompting that the grade purity of the batch of tobacco leaves is relatively low.
8. The tobacco grade identification system based on multi-dimensional characteristic information according to claim 1, characterized by further comprising a near infrared spectrum detection module (9) and a chemical component analysis module (10); the chemical component analysis module (10) is respectively connected with the near infrared spectrum detection module (9) and the central processing module (1);
the near infrared spectrum acquisition module (9) is used for acquiring the near infrared spectrum of the tobacco leaves;
the chemical component analysis module (10) is used for analyzing according to the near infrared spectrum of the tobacco leaves to obtain the chemical components of the tobacco leaves;
the central processing module (1) is internally pre-stored with the range values of the chemical components of the tobacco leaves of each grade; if the chemical components of the tobacco leaves obtained by the analysis of the chemical component analysis module (10) are lower than the pre-stored range value, when the grade output module (7) outputs the chemical components, the grades of all the tobacco leaves are output after the tobacco leaves are planed, and the unqualified chemical components of the tobacco leaves are prompted;
the chemical components include total sugar, reducing sugar, total nitrogen, nicotine, potassium and chlorine content.
9. A tobacco grade identification method based on multi-dimensional characteristic information adopts the tobacco grade identification system based on multi-dimensional characteristic information as claimed in claims 1-8, and is characterized by comprising the following steps:
step (1), sample preparation: spreading each tobacco leaf in the batch to be detected in a standard environment;
step (2), image acquisition and processing: acquiring images of the front and back of each tobacco leaf on line in a standard environment, and extracting the length, width, area, tip included angle, pulse phase and color value ratio of the tobacco leaf from the images;
and (3) measuring key physical property indexes: under a standard environment, measuring the thickness of each piece of tobacco leaves on line through a thickness measuring module, and measuring the weight of each piece of tobacco leaves on line through a weight detection device;
and (4) inputting the grade qualification rate and the grade purity into a tobacco grade judgment model, and judging through the information of each tobacco leaf extracted in the step (2) and the information of each tobacco leaf measured in the step (3) to obtain the grade of the batch of tobacco leaves.
10. The method for identifying tobacco grade based on multi-dimensional characteristic information according to claim 9, wherein the standard environment is that the color temperature of the light source is (5500 ± 100) K, the illuminance is (2000 ± 200) lx, and the color rendering index R isaNot less than 92; the ambient temperature is (22 +/-2) DEG C, and the relative humidity is (70 +/-5)%.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011460291.4A CN112539785B (en) | 2020-12-11 | 2020-12-11 | Tobacco grade identification system and method based on multi-dimensional characteristic information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011460291.4A CN112539785B (en) | 2020-12-11 | 2020-12-11 | Tobacco grade identification system and method based on multi-dimensional characteristic information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112539785A true CN112539785A (en) | 2021-03-23 |
| CN112539785B CN112539785B (en) | 2022-09-09 |
Family
ID=75018500
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011460291.4A Active CN112539785B (en) | 2020-12-11 | 2020-12-11 | Tobacco grade identification system and method based on multi-dimensional characteristic information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112539785B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113516617A (en) * | 2021-04-02 | 2021-10-19 | 云南省烟草质量监督检测站 | Flue-cured tobacco grade identification modeling method based on machine vision and AI deep learning |
| 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 |
| CN114091920A (en) * | 2021-11-24 | 2022-02-25 | 江苏中烟工业有限责任公司 | Tobacco lamina grading method and system |
| CN114192432A (en) * | 2021-11-27 | 2022-03-18 | 云南省农业科学院生物技术与种质资源研究所 | Full-automatic intelligent grading plant of dry product of white meat glossy ganoderma |
| CN114766706A (en) * | 2022-05-09 | 2022-07-22 | 北京天地数联科技有限公司 | Tobacco leaf impurity removal and grading method |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS49498A (en) * | 1972-03-16 | 1974-01-05 | ||
| US3939983A (en) * | 1972-03-16 | 1976-02-24 | Asfour Emil S | Apparatus for sorting tobacco leaves |
| JPH0360774A (en) * | 1989-07-31 | 1991-03-15 | Japan Tobacco Inc | Color detection type device for discriminating kind of leaf tobacco |
| US20090234709A1 (en) * | 2007-11-20 | 2009-09-17 | Philip Morris Usa Inc. | Mobile tobacco receiving station |
| CN103743486A (en) * | 2014-01-02 | 2014-04-23 | 上海大学 | Automatic grading system and method based on mass tobacco leaf data |
| CN110632068A (en) * | 2019-08-09 | 2019-12-31 | 上海创和亿电子科技发展有限公司 | Method for measuring processing resistance of tobacco leaves |
| CN110639832A (en) * | 2019-08-14 | 2020-01-03 | 南京焦耳科技有限责任公司 | Tobacco leaf processing method and system |
| CN110646425A (en) * | 2019-09-12 | 2020-01-03 | 厦门中软海晟信息技术有限公司 | Tobacco leaf online auxiliary grading method and system |
| CN111067131A (en) * | 2019-12-25 | 2020-04-28 | 福建武夷烟叶有限公司 | Automatic tobacco grade identification and sorting method |
| CN111274860A (en) * | 2019-11-08 | 2020-06-12 | 杭州安脉盛智能技术有限公司 | Machine vision-based online automatic tobacco leaf grade sorting identification method |
-
2020
- 2020-12-11 CN CN202011460291.4A patent/CN112539785B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS49498A (en) * | 1972-03-16 | 1974-01-05 | ||
| US3939983A (en) * | 1972-03-16 | 1976-02-24 | Asfour Emil S | Apparatus for sorting tobacco leaves |
| JPH0360774A (en) * | 1989-07-31 | 1991-03-15 | Japan Tobacco Inc | Color detection type device for discriminating kind of leaf tobacco |
| US20090234709A1 (en) * | 2007-11-20 | 2009-09-17 | Philip Morris Usa Inc. | Mobile tobacco receiving station |
| CN103743486A (en) * | 2014-01-02 | 2014-04-23 | 上海大学 | Automatic grading system and method based on mass tobacco leaf data |
| CN110632068A (en) * | 2019-08-09 | 2019-12-31 | 上海创和亿电子科技发展有限公司 | Method for measuring processing resistance of tobacco leaves |
| CN110639832A (en) * | 2019-08-14 | 2020-01-03 | 南京焦耳科技有限责任公司 | Tobacco leaf processing method and system |
| CN110646425A (en) * | 2019-09-12 | 2020-01-03 | 厦门中软海晟信息技术有限公司 | Tobacco leaf online auxiliary grading method and system |
| CN111274860A (en) * | 2019-11-08 | 2020-06-12 | 杭州安脉盛智能技术有限公司 | Machine vision-based online automatic tobacco leaf grade sorting identification method |
| CN111067131A (en) * | 2019-12-25 | 2020-04-28 | 福建武夷烟叶有限公司 | Automatic tobacco grade identification and sorting method |
Non-Patent Citations (6)
| Title |
|---|
| FAN ZHANG: "Classification and Quality Evaluation of Tobacco Leaves Based on Image Processing and Fuzzy Comprehensive Evaluation", 《SENSORS 2011》 * |
| 李锐: "烟叶分级指标量化研究的技术创新过程", 《中国烟草科学》 * |
| 杜东亮等: "基于计算机视觉的烟叶自动分级系统硬件设计", 《传感器与微系统》 * |
| 牛文娟: "基于图像处理的烟叶分级研究", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》 * |
| 王戈等: "计算机视觉和智能识别技术在烤烟烟叶分级中的应用", 《计算机与应用化学》 * |
| 顾金梅等: "基于BP神经网络的烟叶颜色自动分级研究", 《中国农机化学报》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113516617A (en) * | 2021-04-02 | 2021-10-19 | 云南省烟草质量监督检测站 | Flue-cured tobacco grade identification modeling method based on machine vision and AI deep learning |
| 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 |
| CN114091920A (en) * | 2021-11-24 | 2022-02-25 | 江苏中烟工业有限责任公司 | Tobacco lamina grading method and system |
| CN114192432A (en) * | 2021-11-27 | 2022-03-18 | 云南省农业科学院生物技术与种质资源研究所 | Full-automatic intelligent grading plant of dry product of white meat glossy ganoderma |
| CN114192432B (en) * | 2021-11-27 | 2023-06-09 | 云南省农业科学院生物技术与种质资源研究所 | Full-automatic intelligent grading plant of white meat glossy ganoderma dry product |
| CN114766706A (en) * | 2022-05-09 | 2022-07-22 | 北京天地数联科技有限公司 | Tobacco leaf impurity removal and grading method |
| CN114766706B (en) * | 2022-05-09 | 2023-09-12 | 北京天地数联科技有限公司 | Tobacco impurity removing and grading method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112539785B (en) | 2022-09-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112539785B (en) | Tobacco grade identification system and method based on multi-dimensional characteristic information | |
| CN110763698B (en) | Hyperspectral citrus leaf disease identification method based on characteristic wavelength | |
| CN111414891B (en) | Power transmission line channel tree height inversion method based on laser radar and optical remote sensing | |
| CN101692052B (en) | Hyperspectrum image technique-based method and hyperspectrum image technique-based device for identifying true and false famous tea | |
| CN104502320B (en) | A kind of three-dimensional fluorescence spectrum combines the method that PCA SVM differentiates aromatic Chinese spirit | |
| CN104990892B (en) | The spectrum picture Undamaged determination method for establishing model and seeds idenmtification method of seed | |
| CN108198176A (en) | A kind of method of discrimination based on image analysis tobacco maturity | |
| CN110646425B (en) | Tobacco leaf online auxiliary grading method and system | |
| CN110705655A (en) | Tobacco leaf classification method based on coupling of spectrum and machine vision | |
| CN112699756B (en) | Hyperspectral image-based tea origin identification method and system | |
| CN104977258A (en) | Tea/cosmetics quality detecting method based on two-dimensional correlation spectra | |
| CN102636452A (en) | NIR (Near Infrared Spectrum) undamaged identification authenticity method for wild ginseng | |
| CN111896495A (en) | Method and system for discriminating Taiping Houkui production places based on deep learning and near infrared spectrum | |
| CN111474137A (en) | Citrus sugar degree nondestructive testing method based on convolutional neural network | |
| WO2023108514A1 (en) | Spectral peak automatic detection and reconstruction method and system in tea near-infrared spectral analysis | |
| CN115587988A (en) | Method for distinguishing maturity and height of tobacco leaves based on digital image processing | |
| CN107976417A (en) | A kind of crude oil category identification method based on infrared spectrum | |
| CN112540971B (en) | Full-information online acquisition system and method based on tobacco leaf characteristics | |
| CN109387484A (en) | A kind of ramee variety recognition methods of combination EO-1 hyperion and support vector cassification | |
| CN203572772U (en) | Cloud traditional Chinese medicine quality detection system based on multi-wavelength LED fluorescence spectrum | |
| CN109001181A (en) | A kind of edible oil type method for quick identification of Raman spectrum canonical correlation analysis fusion | |
| CN102521830B (en) | Optimum band selection method for hyperspectral images of canopy of crop under disease stress | |
| CN108535250A (en) | ' Fuji ' ripe apples degree lossless detection method based on Streif indexes | |
| CN102680427A (en) | Method for identifying surface fragrance quality of cigarettes by near infrared spectral analysis technology | |
| CN111709927A (en) | Automatic identification method and system for type abnormal pattern spots |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |