CN113218885A - Verticillium wilt severity estimation method based on feature extraction method and classification algorithm - Google Patents
Verticillium wilt severity estimation method based on feature extraction method and classification algorithm Download PDFInfo
- Publication number
- CN113218885A CN113218885A CN202110491603.6A CN202110491603A CN113218885A CN 113218885 A CN113218885 A CN 113218885A CN 202110491603 A CN202110491603 A CN 202110491603A CN 113218885 A CN113218885 A CN 113218885A
- Authority
- CN
- China
- Prior art keywords
- cotton
- leaves
- leaf
- classification algorithm
- groups
- 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
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention relates to the technical field of verticillium wilt severity estimation, and discloses a verticillium wilt severity estimation method based on a feature extraction method and a classification algorithm, which comprises the following steps of 1: selecting three groups of holding dishes, and dividing the three groups of holding dishes into a withered cotton leaf holding dish, a yellow spot type cotton leaf holding dish and a fallen leaf type cotton leaf holding dish, wherein the step 2: and selecting diseased cotton leaves by adopting a characteristic extraction method and a classification algorithm, rolling the edges of the cotton leaves, placing the cotton leaves in a yellow spot type cotton leaf containing vessel, placing the cotton leaves with local or palm-shaped withered spots in a leaf withered type cotton leaf containing vessel, and placing the cotton leaves in a fallen leaf type cotton leaf containing vessel in a withered manner. According to the method, the diseased cotton leaves are selected by adopting a characteristic extraction method and a classification algorithm, and then the detection and estimation are carried out by matching with a spectrometer, so that the severity of the verticillium wilt of the diseased cotton leaves of different types can be rapidly known through reflection spectrum data, and further, the severity detection and estimation information of the verticillium wilt can be accurately obtained.
Description
Technical Field
The invention relates to the technical field of verticillium wilt severity estimation, in particular to a verticillium wilt severity estimation method based on a feature extraction method and a classification algorithm.
Background
The verticillium wilt of plants is a vascular bundle disease with serious harm, the pathogenic bacteria of the verticillium wilt are mainly verticillium dahliae and verticillium nigrum, and are deuteromycotina, chromosporiaceae and verticillium, but the current detection means can quickly know the severity of the verticillium wilt of cotton leaves of different types of diseased plants, so that the severity estimation information of the verticillium wilt can be accurately obtained, and the verticillium wilt severity estimation method based on a feature extraction method and a classification algorithm is provided.
Disclosure of Invention
The invention aims to provide a verticillium wilt severity estimation method based on a feature extraction method and a classification algorithm, and solves the problems in the background art.
In order to achieve the purpose, the invention provides the following technical scheme: a verticillium wilt severity estimation method based on a feature extraction method and a classification algorithm comprises the following steps:
step 1: selecting three groups of holding dishes, and dividing the three groups of holding dishes into a withered cotton leaf holding dish, a yellow spot type cotton leaf holding dish and a fallen cotton leaf holding dish;
step 2: selecting diseased cotton leaves by adopting a characteristic extraction method and a classification algorithm, placing the cotton leaves with the edges curled up into a yellow spot type cotton leaf containing vessel, placing the cotton leaves with local or palm-shaped withered spots into a leaf withered type cotton leaf containing vessel, and placing the cotton leaves with withered leaves into a leaf-falling type cotton leaf containing vessel;
and step 3: then cleaning the cotton leaves in the three groups of holding dishes;
and 4, step 4: and then detecting the cotton blades in the three groups of holding dishes by using a spectrometer, so as to obtain the reflection spectrum data of the cotton blades.
In a preferred embodiment of the present invention, in step 1, the three groups of containers are common glass containers, and then corresponding labels are attached.
In a preferred embodiment of the present invention, in step 2, the number of the cotton leaves selected from the three groups of dishes is 30, and the selected cotton leaves are the same in size.
As a preferred embodiment of the present invention, the detailed steps of step 2 are: firstly, selecting a large number of cotton plants in a cotton planting base, picking or picking cotton leaves on the cotton plants, and then placing the cotton leaves with the cotton plants in three groups of containing dishes for treatment by a feature extraction method and a classification algorithm.
As a preferred embodiment of the present invention, the detailed step of step 3 is to firstly contain a large amount of clear water, then use brushes to classify and clean the cotton leaves in the three groups of containers, and then lay the cotton leaves flat for natural airing.
In step 4, the spectrometer measures for 1-1.5s, and the lens is 30cm away from the blade, so as to ensure complete irradiation to the whole blade.
Compared with the prior art, the invention provides a verticillium wilt severity estimation method based on a feature extraction method and a classification algorithm, which has the following beneficial effects:
according to the verticillium wilt severity estimation method based on the feature extraction method and the classification algorithm, the diseased cotton leaves are selected by adopting the feature extraction method and the classification algorithm, and then the spectrum analyzer is used for estimating, so that the severity of verticillium wilt of diseased cotton leaves of different types can be rapidly known through reflection spectrum data, further verticillium wilt severity estimation information can be accurately obtained, and the method has a great practical value for treating the current cotton verticillium wilt.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a schematic flow chart of a greensickness severity assessment method based on a feature extraction method and a classification algorithm.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further described with the specific embodiments.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, it should be noted that unless otherwise explicitly stated or limited, the terms "mounted," "connected," and "disposed" are to be construed broadly, e.g., as meaning fixedly connected, disposed, detachably connected, disposed, or integrally connected and disposed; the type of the electrical appliance provided by the invention is only used for reference. For those skilled in the art, different types of electrical appliances with the same function can be replaced according to actual use conditions, and for those skilled in the art, the specific meaning of the above terms in the present invention can be understood in specific situations.
Referring to fig. 1, the present invention provides a technical solution: a verticillium wilt severity estimation method based on a feature extraction method and a classification algorithm comprises the following steps:
step 1: selecting three groups of holding dishes, and dividing the three groups of holding dishes into a withered cotton leaf holding dish, a yellow spot type cotton leaf holding dish and a fallen cotton leaf holding dish;
step 2: selecting diseased cotton leaves by adopting a characteristic extraction method and a classification algorithm, placing the cotton leaves with the edges curled up into a yellow spot type cotton leaf containing vessel, placing the cotton leaves with local or palm-shaped withered spots into a leaf withered type cotton leaf containing vessel, and placing the cotton leaves with withered leaves into a leaf-falling type cotton leaf containing vessel;
and step 3: then cleaning the cotton leaves in the three groups of holding dishes;
and 4, step 4: and then detecting the cotton blades in the three groups of holding dishes by using a spectrometer, so as to obtain the reflection spectrum data of the cotton blades.
In this embodiment, in step 1, three groups of dishes that hold adopt ordinary glass to hold the household utensils, paste corresponding label again, be convenient for distinguish three groups of dishes that hold, avoid appearing the condition that the cotton leaf confusion, further improve the accuracy that the data was surveyed and is estimated.
In this embodiment, in step 2, the number of the cotton leaves selected from the three groups of holding dishes is 30, and the selected cotton leaves are consistent in size, so as to further improve the accuracy of data estimation.
In this embodiment, the detailed steps of step 2 are: firstly, a large number of cotton plants are selected in a cotton planting base, then cotton leaves on the cotton plants are picked or picked, and then the cotton leaves with the cotton plants are placed in three groups of containing dishes for treatment through a feature extraction method and a classification algorithm, so that the cotton leaves can be distinguished conveniently and rapidly.
In this embodiment, the detailed step of step 3 is, hold earlier and get a large amount of clear water, uses the brush to classify the washing to the cotton leaf in three groups hold the ware again, then the cotton leaf that tiles carries out the nature and dries, and the spectrum appearance of being convenient for carries out reflectance spectroscopy data collection.
In this embodiment, in step 4, the measurement time of the spectrometer is 1-1.5s, and the distance between the lens and the blade is 30cm, so as to ensure that the whole blade is completely irradiated, thereby facilitating reduction of data error of the spectrometer.
When the device works, firstly three groups of holding dishes are selected, the three groups of holding dishes are divided into a leaf withering type cotton leaf holding dish, a yellow spot type cotton leaf holding dish and a fallen leaf type cotton leaf holding dish, corresponding labels are attached to the three groups of holding dishes, the three groups of holding dishes are convenient to distinguish, the condition of cotton leaf confusion is avoided, the accuracy of data estimation is further improved, then a large number of cotton plants are selected in a cotton planting base, cotton leaves on the cotton plants are picked or picked up, then the cotton leaves of the plants are selected through a characteristic extraction method and a classification algorithm, the edges of cotton leaves are curled and placed in the yellow spot type cotton leaf holding dish, the cotton leaves are placed in the leaf withering type cotton leaf holding dish, the cotton leaves are placed in the fallen leaf type cotton leaf holding dish in an unworn mode, the number of the selected cotton leaves in the three groups of holding dishes is 30, the sizes of the selected cotton leaves are consistent, and the accuracy of data estimation is further improved, contain a large amount of clear water again, use the brush to hold the cotton leaf of ware to three groups and classify and wash, then the cotton leaf that tiles dries naturally, the spectrum appearance of being convenient for carries out the reflectance spectrum data collection, then adopt the spectrometer, hold the cotton leaf of ware to three groups respectively and detect to acquire the reflectance spectrum data of cotton leaf, spectrum appearance measuring time is 1-1.5s, and the camera lens is 30cm apart from the blade height, ensures to shine whole blade completely, is convenient for reduce the data error of spectrum appearance.
While there have been shown and described what are at present considered the fundamental principles and essential features of the invention and its advantages, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing exemplary embodiments, but is capable of other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (6)
1. A verticillium wilt severity estimation method based on a feature extraction method and a classification algorithm is characterized in that: the method comprises the following steps:
step 1: selecting three groups of holding dishes, and dividing the three groups of holding dishes into a withered cotton leaf holding dish, a yellow spot type cotton leaf holding dish and a fallen cotton leaf holding dish;
step 2: selecting diseased cotton leaves by adopting a characteristic extraction method and a classification algorithm, placing the cotton leaves with the edges curled up into a yellow spot type cotton leaf containing vessel, placing the cotton leaves with local or palm-shaped withered spots into a leaf withered type cotton leaf containing vessel, and placing the cotton leaves with withered leaves into a leaf-falling type cotton leaf containing vessel;
and step 3: then cleaning the cotton leaves in the three groups of holding dishes;
and 4, step 4: and then detecting the cotton blades in the three groups of holding dishes by using a spectrometer, so as to obtain the reflection spectrum data of the cotton blades.
2. The verticillium wilt severity estimation method based on feature extraction method and classification algorithm as claimed in claim 1, wherein: in the step 1, the three groups of containers are common glass containers, and then corresponding labels are attached.
3. The verticillium wilt severity estimation method based on feature extraction method and classification algorithm as claimed in claim 1, wherein: in the step 2, the number of the cotton leaves selected from the three groups of holding dishes is 30, and the selected cotton leaves are consistent in size.
4. The verticillium wilt severity estimation method based on feature extraction method and classification algorithm as claimed in claim 1, wherein: the detailed steps of the step 2 are as follows: firstly, selecting a large number of cotton plants in a cotton planting base, picking or picking cotton leaves on the cotton plants, and then placing the cotton leaves with the cotton plants in three groups of containing dishes for treatment by a feature extraction method and a classification algorithm.
5. The verticillium wilt severity estimation method based on feature extraction method and classification algorithm as claimed in claim 1, wherein: and 3, containing a large amount of clear water, classifying and cleaning the cotton leaves in the three groups of containing dishes by using brushes, and spreading the cotton leaves for natural drying.
6. The verticillium wilt severity estimation method based on feature extraction method and classification algorithm as claimed in claim 1, wherein: in the step 4, the measurement time of the spectrometer is 1-1.5s, the height of the lens from the blade is 30cm, and the whole blade is ensured to be completely irradiated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110491603.6A CN113218885A (en) | 2021-05-06 | 2021-05-06 | Verticillium wilt severity estimation method based on feature extraction method and classification algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110491603.6A CN113218885A (en) | 2021-05-06 | 2021-05-06 | Verticillium wilt severity estimation method based on feature extraction method and classification algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113218885A true CN113218885A (en) | 2021-08-06 |
Family
ID=77091090
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110491603.6A Pending CN113218885A (en) | 2021-05-06 | 2021-05-06 | Verticillium wilt severity estimation method based on feature extraction method and classification algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113218885A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101642022A (en) * | 2009-08-25 | 2010-02-10 | 河南省农业科学院 | Method for culturing cotton resisting micro-bundle disease |
| CN101818170A (en) * | 2009-07-17 | 2010-09-01 | 西南大学 | Plant expression vector for vascular peculiar promoter to control antimicrobial protein gene and method for cultivating greensickness-resistant cotton |
| CN106022370A (en) * | 2016-05-17 | 2016-10-12 | 北京农业信息技术研究中心 | Leaf wetting time monitoring method and system |
| CN106048033A (en) * | 2016-06-30 | 2016-10-26 | 中国农业科学院棉花研究所 | Evaluation method of Gossypium hirsutum-Gossypium barbadense introgression lines |
| CN111562235A (en) * | 2020-05-18 | 2020-08-21 | 迟衡 | Method for rapidly identifying black-leaf outbreak disease and infection degree of tobacco leaves based on near infrared spectrum |
| CN112285054A (en) * | 2020-09-08 | 2021-01-29 | 塔里木大学 | Apple identity recognition model establishing method and system and identity recognition method and system |
| CN112630184A (en) * | 2020-12-10 | 2021-04-09 | 新疆农业大学 | Method for identifying phenotype of cotton verticillium wilt disease |
-
2021
- 2021-05-06 CN CN202110491603.6A patent/CN113218885A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101818170A (en) * | 2009-07-17 | 2010-09-01 | 西南大学 | Plant expression vector for vascular peculiar promoter to control antimicrobial protein gene and method for cultivating greensickness-resistant cotton |
| CN101642022A (en) * | 2009-08-25 | 2010-02-10 | 河南省农业科学院 | Method for culturing cotton resisting micro-bundle disease |
| CN106022370A (en) * | 2016-05-17 | 2016-10-12 | 北京农业信息技术研究中心 | Leaf wetting time monitoring method and system |
| CN106048033A (en) * | 2016-06-30 | 2016-10-26 | 中国农业科学院棉花研究所 | Evaluation method of Gossypium hirsutum-Gossypium barbadense introgression lines |
| CN111562235A (en) * | 2020-05-18 | 2020-08-21 | 迟衡 | Method for rapidly identifying black-leaf outbreak disease and infection degree of tobacco leaves based on near infrared spectrum |
| CN112285054A (en) * | 2020-09-08 | 2021-01-29 | 塔里木大学 | Apple identity recognition model establishing method and system and identity recognition method and system |
| CN112630184A (en) * | 2020-12-10 | 2021-04-09 | 新疆农业大学 | Method for identifying phenotype of cotton verticillium wilt disease |
Non-Patent Citations (3)
| Title |
|---|
| 王兴国: "基于决策树的棉花病虫害识别研究", 《中国优秀博硕士学位论文全文数据库（硕士）农业科技辑》 * |
| 王姣 等: "基于棉花黄萎病多"症状"特征的植被指数构建及病情遥感监测研究", 《地理与地理信息科学》 * |
| 郭荣成 等: "棉花枯，黄萎病的发生与防治", 《河南农业》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4593269B2 (en) | Methods for measuring chemical and physical properties in laundry or dishwashing environments | |
| CN110089983A (en) | A kind of method, apparatus and storage medium of the cleaning cookware based on intelligent kitchen | |
| AU2020395109A1 (en) | Verification of cleaning process efficacy | |
| Sonnleitner et al. | Microclimatic patterns correlate with the distribution of epiphyllous bryophytes in a tropical lowland rain forest in Costa Rica | |
| CN113218885A (en) | Verticillium wilt severity estimation method based on feature extraction method and classification algorithm | |
| CN204741957U (en) | It collects to be used for potted plant to wither and fall thing and device of decomposition experiment thereof | |
| CN111820834B (en) | Dish washing machine cleaning system and automatic cleaning method | |
| CN103245625A (en) | Method for nondestructive detection on maturity of fresh flue-cured tobacco leaves | |
| CN205018816U (en) | Electric food processing appliance | |
| CN116823363B (en) | Dish-washing machine performance rating system and evaluation method | |
| CN110833368A (en) | Intelligent control method for washing of dish washing machine | |
| CN206074624U (en) | A kind of high-accuracy portable blood coagulation whole bliid platelet analyzer | |
| CN114062505B (en) | Fruit maturity detection method and device, electronic equipment and storage medium | |
| CN207336424U (en) | A kind of pears class fruit maturity nondestructive testing instrument | |
| CN206507916U (en) | For the knife and fork pallet component of dish-washing machine and the dish-washing machine with it | |
| CN210419915U (en) | Biological gene detection device | |
| EP1116471A3 (en) | Method and device for determining the amount of dirt on tableware | |
| CN208443821U (en) | A kind of device for detecting safety of foods | |
| Beier et al. | Methods for evaluation of picking performance of chamomile (Matricaria recutita L.) harvesters. Part II: Development of new methods | |
| CN112790693A (en) | Control method of dish-washing machine and dish-washing machine | |
| CN206390751U (en) | cooker for electromagnetic oven | |
| CN210902824U (en) | Dust collecting box of floor sweeping robot | |
| CN109567704A (en) | A kind of method and system that water basin dish-washing machine is dry based on residual water | |
| CN114227676B (en) | Fruit picking control method and device, electronic equipment and storage medium | |
| CN214683010U (en) | A benthonic animal sorting device for open-air environmental monitoring |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210806 |
|
| RJ01 | Rejection of invention patent application after publication |