CN109187552A - A kind of gibberella saubinetii disease grade determination method based on cloud model - Google Patents
A kind of gibberella saubinetii disease grade determination method based on cloud model Download PDFInfo
- Publication number
- CN109187552A CN109187552A CN201810999005.8A CN201810999005A CN109187552A CN 109187552 A CN109187552 A CN 109187552A CN 201810999005 A CN201810999005 A CN 201810999005A CN 109187552 A CN109187552 A CN 109187552A
- Authority
- CN
- China
- Prior art keywords
- disease
- color
- wheat
- grade
- cloud model
- 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
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 title claims abstract description 101
- 201000010099 disease Diseases 0.000 title claims abstract description 99
- 238000000034 method Methods 0.000 title claims abstract description 25
- 241000223218 Fusarium Species 0.000 title claims abstract description 21
- 241000209140 Triticum Species 0.000 claims abstract description 61
- 235000021307 Triticum Nutrition 0.000 claims abstract description 55
- 206010039509 Scab Diseases 0.000 claims abstract description 17
- 238000013210 evaluation model Methods 0.000 claims abstract description 13
- 238000010276 construction Methods 0.000 claims abstract description 6
- 238000000605 extraction Methods 0.000 claims abstract description 5
- 238000004458 analytical method Methods 0.000 claims abstract description 4
- 239000003086 colorant Substances 0.000 claims description 32
- 238000011156 evaluation Methods 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 7
- 238000003709 image segmentation Methods 0.000 claims description 4
- 241000208340 Araliaceae Species 0.000 claims description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 235000008434 ginseng Nutrition 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 2
- 208000031968 Cadaver Diseases 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 208000037273 Pathologic Processes Diseases 0.000 abstract 1
- 230000009054 pathological process Effects 0.000 abstract 1
- 230000000875 corresponding effect Effects 0.000 description 15
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 7
- 241000196324 Embryophyta Species 0.000 description 5
- 239000000428 dust Substances 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 235000013339 cereals Nutrition 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 241000495841 Oenanthe oenanthe Species 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 239000010977 jade Substances 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000008654 plant damage Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
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
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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
- G01N21/84—Systems specially adapted for particular applications
- G01N2021/8466—Investigation of vegetal material, e.g. leaves, plants, fruits
-
- 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
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8883—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges involving the calculation of gauges, generating models
-
- 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
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (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)
- Image Analysis (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
The invention belongs to corps diseases monitoring technical fields, more particularly to a kind of gibberella saubinetii disease grade determination method based on cloud model, the construction of extraction, color characteristic including disease region, the analysis for generating gibberella saubinetii color characteristic cloud model, establishing comprehensive evaluation model and evaluation model;Using wheat scab in gradually pathological process, the color change in disease region and the relationship of wheat disease tassel yield grade, the color characteristic cloud that disease region is obtained in conjunction with three numerical characteristics of cloud model realizes non-rigid division to wheat scab grade using cloud model, realizes overall merit.
Description
Technical field
The invention belongs to corps diseases monitoring technical fields, and in particular to a kind of gibberella saubinetii disease based on cloud model
Grade determination method.
Background technique
The rapid development of computer technology improves speed and efficiency that plant disease detects identification automatically.Such as EO-1 hyperion
Technology, image processing techniques etc..Such as beam a kind of jade, Du Yingying et al. uses hyperspectral imager, respectively to healthy wheat seed image
With its spectrometer information Reflectivity of head blight wheat seed image analysis.It is eliminated by a series of preprocessing procedures
Then spectrum picture noise identifies textural characteristics, morphological parameters and average gray feature wave band, finally establishes identification mould
Type.Shao Qing, Zhang Nan et al. carry out image denoising to the leaf diseases of wheat, then realize Shape Feature Extraction to disease position,
It is not only a kind of progress on image procossing, while the perfect property data base of wheat diseases.
According to wheat scab Forecast Techniques codes and standards, single plant damage degree of wheat scab severity extent is divided into 4
A grade, but excessive " hard plot " will lead to the extremely close object of two conception of species values, be classified as in different grades.Example
Such as: the disease tassel yield detected is 25.8%, and according to the grade scale of codes and standards, which belongs to 2 grades, but the value is extremely
It is grade classification and unreasonable close to 25%;And at present using the wheat head as the head blight research of object be all by its from living body excision under
Come, it is wheat head grain that some, which is even removed, and by a series of recognition detection method statistic disease tassel yield, but these are all certain fixing shapes
Detection under state, since degree of disease at this time is not it has been determined that the variation of disease process has lacked a dynamic it is found that being equivalent to
Parameter illustrates the variation of its disease process.
Summary of the invention
The present invention on the basis of cloud model representation of knowledge, by single plant living body wheat never fall ill to morbidity color
On the grade scale that codes and standards provide the color characteristic is added, other than disease tassel yield in variation, the characteristic parameter of construction
Another impact factor, generate color characteristic cloud model, realize to being classified more reasonable evaluation.
The present invention has followed up the growth course of living body wheat, never the morbidity state different to each severity extent, counts face
Color change degree, construction feature parameter provide a kind of based on cloud as the index for identifying and evaluating wheat diseases degree
The gibberella saubinetii disease grade determination method of model.It is compared to the wheat detection to having extractd, it is more convincing.
The present invention is achieved by the following technical solutions: a kind of gibberella saubinetii disease grade judgement side based on cloud model
Method, comprising the following steps:
The extraction of S1, disease region
S11, the initial pictures of the wheat wheat head are acquired in field, obtains just handling image by denoising;
S12, image segmentation is carried out to a component of the first processing image under Lab space using Otsu method, obtains a component image;
S13, wheat head edge image is obtained using limb recognition algorithm to first processing image;
S14, bit arithmetic is carried out respectively to the gray value of a component image and wheat head edge image, by a component image and wheat head edge
The identical pixel of gray value of image is set as 0(black), the different pixel of gray value is set as 255(white), then by picture
The pixel that vegetarian refreshments is 255 is denoted as disease pixel, obtains disease pixel distribution map;
It is S15, corresponding with initial pictures using disease pixel distribution map, it extracts in initial pictures and corresponds to disease pixel distribution map
The initial pixel point at place obtains initial pixel point distribution map;
It is S16, red using corresponding position mark of the initial pixel point distribution map in initial pictures, obtain disease tag image;
The construction of S2, color characteristic
S21, using in step S15 obtained initial pixel point color as statistics wheat scab incidence color moment
Basis, the color moment of the calculation formula statistics single plant wheat scab incidence using single order away from, second order away from, third moment, one
Rank is as follows away from, the calculation formula of third moment away from, second order:
Single order away from calculation formula:
Second order away from calculation formula:
Three ranks away from calculation formula;
S22, according to the syntagmatic between color component each in color space HSV, RGB and Lab, construct multiple intermediate colors ginsengs
Number;
S23, note color moment and intermediate color parameter are evaluation color parameter, calculate each evaluation using relevance function corr ()
The related coefficient of color parameter;
S24, the significance of the related coefficient of each evaluation color parameter is judged;
The related coefficient of the evaluation color parameter of table 1
To the correlation analysis of the above evaluation color parameter, it is known that, the correlation of only 21 color parameters and wheat disease tassel yield reaches
To 50% or more, there are 14 color parameters and disease tassel yield negatively correlated;It is generally acknowledged that: related coefficient is no phase in 0-0.09
Guan Xing, 0.1-0.3 are weak correlation, and 0.3-0.5 is medium correlation, and 0.5-1.0 is strong correlation.But simultaneously due to the size of related coefficient
It is unstable, it cannot directly illustrate its correlativity;Because related coefficient is, related coefficient sheet related with the property of data itself
Body can change, and with increasing and decreasing for sample size, the relative coefficient calculated may change, so sentencing
Disconnected power will not only see related coefficient, also see conspicuousness size;Significance is that estimation population parameter falls in a certain section
Probability that is interior, may making mistakes, is indicated with α;α is smaller, and the probability in the section that expression population parameter falls in mistake is smaller, then shows
The estimation of correlativity is easier to be correct, and α is bigger, and the probability in the section that expression population parameter falls in mistake is bigger, i.e., related to close
The estimation of system is more easy to appear mistake;Think that α is less than 0.1 under normal circumstances.In table 1, the * * after related coefficient is represented
Significance reach 0.01, * indicate significance reach 0.05.
The evaluation color parameter that S25, selection significance of correlation coefficient level reach 0.01 is denoted as relevant colors parameter, so
Tetra- relevant colors parameters of h-mean, s-mean, h-std, s-std are chosen herein as wheat scab color characteristic cloud model
Data source;
S3, gibberella saubinetii color characteristic cloud model is generated, the gibberella saubinetii color characteristic cloud model is by it is expected Ex, entropy
Tri- En, super entropy He numerical characteristic descriptions
S31, the different corresponding curves of frequency distribution of wheat disease tassel yield grade is plotted in using relevant colors parameter;
S32, peak point in each curve of frequency distribution is found out, using the corresponding x value of gained peak point as cloud model need to be generated
It is expected that Ex;
S33, entropy En and super entropy He is calculated according to formula;
S4, comprehensive evaluation model is established
Cloud model is made of each water dust, and water dust is different to the contribution of concept, and all water dusts on infinite interval are to concept
Contribution margin should be 1, but in by stages, need the contribution margin size in view of each water dust to concept;According to 3En criterion
Concept takes a by stages of X in cloud model, the water dust on the section is calculated to the average contribution of concept A, put down
ContributeFormula it is as follows:
It is obtained by the formula of average contribution, the element on entire section contributes concept A total
It is as follows with formula:
After analyzing, the element in domain [Ex-3En, Ex+3En] has reached 99.74% to the contribution of concept, is distributed in domain area
Between element other than [Ex-3En, Ex+3En] can disregard its influence substantially since contribution margin is too low;
S41, according to the corresponding numerical characteristic of relevant colors parameter, calculate the value of Ex-0.67En and Ex+0.67En;
S42, according to the grade of different wheat disease tassel yields, respectively with section [Ex-0.67En, Ex+0.67En] construct evaluation mould
Type;
The analysis of S5, evaluation model
S51, the wheat disease tassel yield of certain grade is evaluated, judges the corresponding section of each relevant colors parameter in the grade
[Ex-0.67En, Ex+0.67En] is used as relevant colors parameter evaluation section, the corresponding correlation of all relevant parameters in the grade
If color parameter evaluation interval intersects simultaneously, will wirelessly delimit close to the grade of the wheat disease tassel yield of a high grade current
In grade;Otherwise, then it cannot delimit in present level.
Wherein, the ratio value of the R in the RGB color, G, B indicates chromaticity coordinate (r, g, b), meet r+g+b=
1, calculation formula is respectively as follows: r=R/(R+G+B);G=G/(R+G+B);B=B/(R+G+B).
Wherein, denoising method is median filtering denoising in the step S11;The curve of frequency distribution utilizes the library python
In hist() function draw.
Wherein, the grade of the wheat disease tassel yield include: level-one disease tassel yield be 20-25%, second level disease tassel yield be 45-50%,
Three-level disease tassel yield is 70-75%.
Wherein, the peak point is the local maximum of curve of frequency distribution.
The present invention has the advantage that the judgment criteria that comprehensive classification is utilized in the present invention compared with prior art, can be right
Wheat wheat ear scab incidence is tracked without using living body picking wheat head grain, can effectively alleviate hard plot
Limitation can provide standard for the evaluation of wheat scab, for wheat scab apply water, application reasonable guidance is provided.
Detailed description of the invention
Fig. 1 is the histogram of Lab color space a component and b component;
Fig. 2 is a component image;
Fig. 3 is wheat head edge image;
Fig. 4 is disease pixel distribution map;
Fig. 5 is initial pixel point distribution map;
Fig. 6 is disease tag image;
Fig. 7-10 is four relevant colors parameters frequency distribution curves of level-one disease tassel yield;
Figure 11-14 is four relevant colors parameters frequency distribution curves of second level disease tassel yield;
Figure 15-18 is four relevant colors parameters frequency distribution curves of three-level disease tassel yield;
Figure 19-22 is the cloud model that four relevant colors parameters of level-one disease tassel yield are formed;
Figure 23-26 is the cloud model that four relevant colors parameters of second level disease tassel yield are formed;
Figure 27-30 is the cloud model that four relevant colors parameters of three-level disease tassel yield are formed;
Remarks, wherein initial pixel point and disease label primitive figure are color image in Fig. 4.
Specific embodiment
Detailed description of the preferred embodiments below.It should be understood that described herein specific
Embodiment is merely to illustrate and explain the present invention, and is not intended to restrict the invention.
A kind of gibberella saubinetii disease grade determination method based on cloud model, comprising the following steps:
The extraction of S1, disease region
S11, the initial pictures of the wheat wheat head are acquired in field, obtains just handling image by denoising;
S12, image segmentation is carried out to a component of the first processing image under Lab space using Otsu method, obtains a component image
As shown in Figure 2;
Wherein for Lab relative to other color spaces, color representation is widest in area, and is not illuminated by the light influence, in Lab color space
A component has apparent Wave crest and wave trough when drawing color histogram, compared to b component it can be seen that object outline seems more clear
It is clear, it is specifically shown in Fig. 1;More easily go out target using color segmentation, therefore, a component in the present invention under Lab color space is realized
Image segmentation;
S13, using limb recognition algorithm to obtain wheat head edge image to first processing image as shown in Figure 3;
S14, bit arithmetic is carried out respectively to the gray value of a component image and wheat head edge image, by a component image and wheat head edge
The identical pixel of gray value of image is set as 0(black), the different pixel of gray value is set as 255(white), then by picture
The pixel that vegetarian refreshments is 255 is denoted as disease pixel, and it is as shown in Figure 4 to obtain disease pixel distribution map;
It is S15, corresponding with initial pictures using disease pixel distribution map, it extracts in initial pictures and corresponds to disease pixel distribution map
It is as shown in Figure 5 to obtain initial pixel point distribution map for the initial pixel point at place;
It is S16, red using corresponding position mark of the initial pixel point distribution map in initial pictures, obtain disease tag image such as Fig. 6
Shown in;
The construction of S2, color characteristic
S21, using in step S15 obtained initial pixel point color as statistics wheat scab incidence color moment
Basis, the color moment of the calculation formula statistics single plant wheat scab incidence using single order away from, second order away from, third moment;
S22, according to the syntagmatic between color component each in color space HSV, RGB and Lab, construct multiple intermediate colors ginsengs
Number;The ratio value of R in the RGB color, G, B indicate chromaticity coordinate (r, g, b), meet r+g+b=1, calculate public
Formula is respectively as follows: r=R/(R+G+B);G=G/(R+G+B);B=B/(R+G+B);
S23, note color moment and intermediate color parameter are evaluation color parameter, calculate each evaluation using relevance function corr ()
The related coefficient of color parameter;
S24, particular content, which is shown in Table 1, to be judged to the significance of the related coefficient of each evaluation color parameter;
To the correlation analysis of the above evaluation color parameter, it is known that, only 21 color parameters are related to wheat disease tassel yield
Property has reached 50% or more, has 14 color parameters and disease tassel yield negatively correlated;It is generally acknowledged that: related coefficient is not in 0-0.09
There is correlation, 0.1-0.3 is weak correlation, and 0.3-0.5 is medium correlation, and 0.5-1.0 is strong correlation.But it is big due to related coefficient
It is small and unstable, it cannot directly illustrate its correlativity;Because related coefficient is, phase relation related with the property of data itself
Number can change in itself, and with increasing and decreasing for sample size, the relative coefficient calculated may change, institute
Related coefficient is not only seen with judgement power, also to see conspicuousness size;Significance be estimation population parameter fall in it is a certain
In section, the probability that may be made mistakes is indicated with α;α is smaller, and the probability in the section that expression population parameter falls in mistake is smaller, then
Show that the estimation of correlativity is easier to be correct, α is bigger, and the probability in the section that expression population parameter falls in mistake is bigger, i.e. phase
The estimation of pass relationship is more easy to appear mistake;Think that α is less than 0.1 under normal circumstances.* * in table 1, after related coefficient
Represent significance reach 0.01, * indicate significance reach 0.05.
The evaluation color parameter that S25, selection significance of correlation coefficient level reach 0.01 is denoted as relevant colors parameter, so
Tetra- relevant colors parameters of h-mean, s-mean, h-std, s-std are chosen herein as wheat scab color characteristic cloud model
Data source;
S3, gibberella saubinetii color characteristic cloud model is generated, the gibberella saubinetii color characteristic cloud model is by it is expected Ex, entropy
Tri- En, super entropy He numerical characteristic descriptions
S31, using the corresponding data source of tetra- relevant colors parameters of h-mean, s-mean, h-std, s-std, be plotted in difference
The corresponding curve of frequency distribution of wheat disease tassel yield grade;
The grade of the wheat disease tassel yield include: level-one disease tassel yield be 20-25%, second level disease tassel yield is 45-50%, three-level disease tassel yield
For 70-75%;
Four relevant colors parameters frequency distribution curves of level-one disease tassel yield are shown in Fig. 7-10;
Four relevant colors parameters frequency distribution curves of second level disease tassel yield are shown in Figure 11-14;
Four relevant colors parameters frequency distribution curves of three-level disease tassel yield are shown in Figure 15-18;
S32, peak point in each curve of frequency distribution is found out, using the corresponding x value of gained peak point as cloud model need to be generated
It is expected that Ex;
S33, entropy En and super entropy He is calculated according to formula;
2 relevant colors parameter of table is in the corresponding three numerical characteristics cloud parameter of different disease tassel yield grades
The cloud model that four relevant colors parameters of level-one disease tassel yield are formed is to see Figure 19-22;
The cloud model that four relevant colors parameters of second level disease tassel yield are formed is to see Figure 23-26;
The cloud model that four relevant colors parameters of three-level disease tassel yield are formed is to see Figure 27-30;
S4, comprehensive evaluation model is established
S41, according to the corresponding numerical characteristic of relevant colors parameter, calculate the value of Ex-0.67En and Ex+0.67En;
3 relevant colors parameter of table corresponds to the value of Ex-0.67En and Ex+0.67En
;
S42, according to the grade of different wheat disease tassel yields, respectively with section [Ex-0.67En, Ex+0.67En] construct evaluation mould
Type;
Show that the corresponding evaluation model of wheat disease tassel yield three grades is as follows:
Level-one disease tassel yield evaluation model
Second level disease tassel yield evaluation model
Three-level disease tassel yield evaluation model
;
The analysis of S5, evaluation model
S51, according to above-mentioned different grades of disease tassel yield evaluation model, it will thus be seen that
(1) when disease tassel yield value is in 20%-25%:
: the value of color characteristic h-mean is located at section;
: the value of color characteristic s-mean is located at section;
: the value of color characteristic h-std is located at section;
: the value of color characteristic s-std is located at section;
The grade of the wheat head of this plant of infinite approach second level can be determined in the range of level-one if meeting condition;If being unsatisfactory for
Above-mentioned condition cannot be then divided into level-one, this is because the element that condition is not satisfied, to concept value " level-one "
Degree of membership is lower;
(2) when disease tassel yield value is in 45%-50%:
: the value of color characteristic h-mean is located at section;
: the value of color characteristic s-mean is located at;
: the value of color characteristic h-std is located at;
: the value of color characteristic s-std is located at;
The grade of the wheat head of this plant of infinite approach three-level can be determined in the range of second level if meeting condition.If being unsatisfactory for
Above-mentioned condition cannot be then divided into second level.
(3) when disease tassel yield value is in 70%-75%:
: the value of color characteristic h-mean is located at section;
: the value of color characteristic s-mean is located at;
: the value of color characteristic h-std is located at;
: the value of color characteristic s-std is located at;
This plant of infinite approach level Four (in aforementioned undeclared level Four disease tassel yield, can be provided into level Four disease herein if meeting condition
Fringe rate determines in the range of three-level for the grade of the wheat head of > 80%).If being unsatisfactory for above-mentioned condition, three cannot be divided into
In grade.
The limitation of " hard plot " can be alleviated, effectively according to the evaluation criterion of comprehensive classification for applying for wheat scab
Water application, provides reasonable guidance.
The preferred embodiment of the present invention has been described above in detail, still, during present invention is not limited to the embodiments described above
Detail within the scope of the technical concept of the present invention can be with various simple variants of the technical solution of the present invention are made, this
A little simple variants all belong to the scope of protection of the present invention.
It is further to note that specific technical features described in the above specific embodiments, in not lance
In the case where shield, can be combined in any appropriate way, in order to avoid unnecessary repetition, the present invention to it is various can
No further explanation will be given for the combination of energy.
In addition, various embodiments of the present invention can be combined randomly, as long as it is without prejudice to originally
The thought of invention, it should also be regarded as the disclosure of the present invention.
Claims (7)
1. a kind of gibberella saubinetii disease grade determination method based on cloud model, which comprises the following steps:
The extraction of S1, disease region
S11, the initial pictures of the wheat wheat head are acquired in field, obtains just handling image by denoising;
S12, image segmentation is carried out to a component of the first processing image under Lab space using Otsu method, obtains a component image;
S13, wheat head edge image is obtained using limb recognition algorithm to first processing image;
S14, bit arithmetic is carried out respectively to the gray value of a component image and wheat head edge image, by a component image and wheat head edge
The identical pixel of gray value of image is set as 0, and the different pixel of gray value is set as 255, the picture for being then 255 by pixel
Vegetarian refreshments is denoted as disease pixel, obtains disease pixel distribution map;
It is S15, corresponding with initial pictures using disease pixel distribution map, it extracts in initial pictures and corresponds to disease pixel distribution map
The initial pixel point at place obtains initial pixel point distribution map;
It is S16, red using corresponding position mark of the initial pixel point distribution map in initial pictures, obtain disease tag image;
The construction of S2, color characteristic
S21, using in step S15 obtained initial pixel point color as statistics wheat scab incidence color moment
Basis, the color moment of the calculation formula statistics single plant wheat scab incidence using single order away from, second order away from, third moment, one
Rank is as follows away from, the calculation formula of third moment away from, second order:
Single order away from calculation formula:
Second order away from calculation formula:
Three ranks away from calculation formula:
;
S22, according to the syntagmatic between color component each in color space HSV, RGB and Lab, construct multiple intermediate colors ginsengs
Number;
S23, note color moment and intermediate color parameter are evaluation color parameter, calculate each evaluation face using relevance function corr ()
The related coefficient of color parameter;
S24, the significance of the related coefficient of each evaluation color parameter is judged;
The evaluation color parameter that S25, selection significance of correlation coefficient level reach 0.01 is denoted as relevant colors parameter, by related face
Data source of the color parameter as wheat scab color characteristic cloud model;
S3, gibberella saubinetii color characteristic cloud model is generated, the gibberella saubinetii color characteristic cloud model is by it is expected Ex, entropy
Tri- En, super entropy He numerical characteristic descriptions
S31, the different corresponding curves of frequency distribution of wheat disease tassel yield grade is plotted in using relevant colors parameter;
S32, peak point in each curve of frequency distribution is found out, using the corresponding x value of gained peak point as cloud model need to be generated
It is expected that Ex;
S33, entropy En and super entropy He is calculated according to formula;
S4, comprehensive evaluation model is established
S41, according to the corresponding numerical characteristic of relevant colors parameter, calculate the value of Ex-0.67En and Ex+0.67En;
S42, according to the grade of different wheat disease tassel yields, respectively with section [Ex-0.67En, Ex+0.67En] construct evaluation mould
Type;
The analysis of S5, evaluation model
S51, the wheat disease tassel yield of certain grade is evaluated, judges the corresponding section of each relevant colors parameter in the grade
[Ex-0.67En, Ex+0.67En] is used as relevant colors parameter evaluation section, the corresponding correlation of all relevant parameters in the grade
If color parameter evaluation interval intersects simultaneously, will wirelessly delimit close to the grade of the wheat disease tassel yield of a high grade current
In grade;Otherwise, then it cannot delimit in present level.
2. a kind of gibberella saubinetii disease grade determination method based on cloud model as described in claim 1, which is characterized in that described
Denoising method is median filtering denoising in step S11.
3. a kind of gibberella saubinetii disease grade determination method based on cloud model as described in claim 1, which is characterized in that described
The ratio value of R in RGB color, G, B indicate chromaticity coordinate (r, g, b), meet r+g+b=1, calculation formula difference
Are as follows: r=R/(R+G+B);G=G/(R+G+B);B=B/(R+G+B).
4. a kind of gibberella saubinetii disease grade determination method based on cloud model as described in claim 1, which is characterized in that described
The evaluation color parameter that significance of correlation coefficient level reaches 0.01 is h-mean, s-mean, h-std, s-std.
5. a kind of gibberella saubinetii disease grade determination method based on cloud model as described in claim 1, which is characterized in that described
Curve of frequency distribution utilizes the hist(in the library python) function drafting.
6. a kind of gibberella saubinetii disease grade determination method based on cloud model as described in claim 1, which is characterized in that described
The grade of wheat disease tassel yield include: level-one disease tassel yield be 20-25%, second level disease tassel yield is 45-50%, three-level disease tassel yield is 70-
75%。
7. a kind of gibberella saubinetii disease grade determination method based on cloud model as described in claim 1, which is characterized in that described
Peak point is the local maximum of curve of frequency distribution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810999005.8A CN109187552B (en) | 2018-08-30 | 2018-08-30 | Wheat scab damage grade determination method based on cloud model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810999005.8A CN109187552B (en) | 2018-08-30 | 2018-08-30 | Wheat scab damage grade determination method based on cloud model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109187552A true CN109187552A (en) | 2019-01-11 |
CN109187552B CN109187552B (en) | 2021-07-09 |
Family
ID=64916685
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810999005.8A Active CN109187552B (en) | 2018-08-30 | 2018-08-30 | Wheat scab damage grade determination method based on cloud model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109187552B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110082298A (en) * | 2019-05-15 | 2019-08-02 | 南京农业大学 | A kind of wheat breed head blight comprehensive resistance identification method based on high spectrum image |
CN110089297A (en) * | 2019-05-18 | 2019-08-06 | 安徽大学 | Severity diagnostic method and device under the environment of wheat scab crop field |
CN110132860A (en) * | 2019-05-29 | 2019-08-16 | 安徽大学 | A kind of winter wheat head blight high-spectrum remote-sensing monitoring method based on wheat head dimensional analysis |
CN110346312A (en) * | 2019-07-19 | 2019-10-18 | 安徽大学 | Winter wheat fringe head blight recognition methods based on Fei Shi linear discriminant and support vector machines technology |
CN110689534A (en) * | 2019-09-29 | 2020-01-14 | 珠海中科先进技术研究院有限公司 | Mould detection method and system |
CN110736750A (en) * | 2019-10-28 | 2020-01-31 | 安徽大学 | wheat scab detection method based on multi-angle field high-definition imaging |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104063686A (en) * | 2014-06-17 | 2014-09-24 | 中国科学院合肥物质科学研究院 | System and method for performing interactive diagnosis on crop leaf segment disease images |
CN105550493A (en) * | 2015-12-02 | 2016-05-04 | 江西理工大学 | Method for predicting concentration of chlorophyll a in water body based on harmony searching of cloud model |
US20160217562A1 (en) * | 2014-06-30 | 2016-07-28 | Trimble Navigation Limited | Active Imaging Systems for Plant Growth Monitoring |
WO2018081043A1 (en) * | 2016-10-24 | 2018-05-03 | Board Of Trustees Of Michigan State University | Methods for mapping temporal and spatial stability and sustainability of a cropping system |
-
2018
- 2018-08-30 CN CN201810999005.8A patent/CN109187552B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104063686A (en) * | 2014-06-17 | 2014-09-24 | 中国科学院合肥物质科学研究院 | System and method for performing interactive diagnosis on crop leaf segment disease images |
US20160217562A1 (en) * | 2014-06-30 | 2016-07-28 | Trimble Navigation Limited | Active Imaging Systems for Plant Growth Monitoring |
CN105550493A (en) * | 2015-12-02 | 2016-05-04 | 江西理工大学 | Method for predicting concentration of chlorophyll a in water body based on harmony searching of cloud model |
WO2018081043A1 (en) * | 2016-10-24 | 2018-05-03 | Board Of Trustees Of Michigan State University | Methods for mapping temporal and spatial stability and sustainability of a cropping system |
Non-Patent Citations (2)
Title |
---|
杨天东 等: "基于图像分析技术的小麦叶面积指数智能估算", 《农业网络信息》 * |
程鲁玉等: "关于果林中果害虫图像特征高效分类识别仿真", 《计算机仿真》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110082298A (en) * | 2019-05-15 | 2019-08-02 | 南京农业大学 | A kind of wheat breed head blight comprehensive resistance identification method based on high spectrum image |
CN110082298B (en) * | 2019-05-15 | 2020-05-19 | 南京农业大学 | Hyperspectral image-based wheat variety gibberellic disease comprehensive resistance identification method |
CN110089297A (en) * | 2019-05-18 | 2019-08-06 | 安徽大学 | Severity diagnostic method and device under the environment of wheat scab crop field |
CN110132860A (en) * | 2019-05-29 | 2019-08-16 | 安徽大学 | A kind of winter wheat head blight high-spectrum remote-sensing monitoring method based on wheat head dimensional analysis |
CN110132860B (en) * | 2019-05-29 | 2021-09-14 | 安徽大学 | Winter wheat scab hyperspectral remote sensing monitoring method based on wheat ear scale analysis |
CN110346312A (en) * | 2019-07-19 | 2019-10-18 | 安徽大学 | Winter wheat fringe head blight recognition methods based on Fei Shi linear discriminant and support vector machines technology |
CN110346312B (en) * | 2019-07-19 | 2021-08-10 | 安徽大学 | Winter wheat head gibberellic disease identification method based on Fisher linear discrimination and support vector machine technology |
CN110689534A (en) * | 2019-09-29 | 2020-01-14 | 珠海中科先进技术研究院有限公司 | Mould detection method and system |
CN110689534B (en) * | 2019-09-29 | 2022-08-09 | 珠海中科先进技术研究院有限公司 | Mould detection method and system |
CN110736750A (en) * | 2019-10-28 | 2020-01-31 | 安徽大学 | wheat scab detection method based on multi-angle field high-definition imaging |
CN110736750B (en) * | 2019-10-28 | 2022-03-04 | 安徽大学 | Wheat scab detection method based on multi-angle field high-definition imaging |
Also Published As
Publication number | Publication date |
---|---|
CN109187552B (en) | 2021-07-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109187552A (en) | A kind of gibberella saubinetii disease grade determination method based on cloud model | |
CN109154978B (en) | System and method for detecting plant diseases | |
Shin et al. | Does colorspace transformation make any difference on skin detection? | |
CN102426649B (en) | Simple steel seal digital automatic identification method with high accuracy rate | |
Siraj et al. | Digital image classification for Malaysian blooming flower | |
CN103034838B (en) | A kind of special vehicle instrument type identification based on characteristics of image and scaling method | |
Qing et al. | Automated detection and identification of white-backed planthoppers in paddy fields using image processing | |
CN103177445B (en) | Based on the outdoor tomato recognition methods of fragmentation threshold Iamge Segmentation and spot identification | |
Kaur | Plant leaf disease detection using ensemble classification and feature extraction | |
CN106294705A (en) | A kind of batch remote sensing image preprocess method | |
Netto et al. | Segmentation of RGB images using different vegetation indices and thresholding methods | |
CN105512612A (en) | SVM-based image classification method for capsule endoscope | |
CN105184771A (en) | Adaptive moving target detection system and detection method | |
CN107705268A (en) | One kind is based on improved Retinex and the enhancing of Welsh near-infrared images and colorization algorithm | |
CN110223344A (en) | A kind of infrared small target detection method based on morphology and vision noticing mechanism | |
Zhang et al. | Citrus canker detection based on leaf images analysis | |
Kent et al. | Early symptom detection of basal stem rot disease in oil palm trees using a deep learning approach on UAV images | |
Laytner et al. | Robust face detection from still images | |
CN114049566A (en) | Method and device for detecting cloud and cloud shadow of land satellite image in step-by-step refinement manner | |
Xiong et al. | Bleeding detection in wireless capsule endoscopy based on MST clustering and SVM | |
KR101437999B1 (en) | A method for detecting human using cs-lbp based on luminance saliency map and random forests in thermal images | |
CN107358224B (en) | Method for detecting outer iris outline in cataract surgery | |
CN109948520A (en) | A kind of Crop classification method based on multidate dual polarization SAR indicatrix | |
Trivedi et al. | K-mean and HSV model based segmentation of unhealthy plant leaves and classification using machine learning approach | |
CN110427950B (en) | Purple soil image shadow detection method |
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 | ||
TR01 | Transfer of patent right |
Effective date of registration: 20220121 Address after: 230000 room 808, 8 / F, building C, phase II, Hefei Innovation Industrial Park, innovation Avenue, high tech Zone, Hefei, Anhui Province Patentee after: Anhui Analysys Technology Co.,Ltd. Address before: 230036 School of information and computer, Anhui Agricultural University, 130 Changjiang West Road, Hefei City, Anhui Province Patentee before: Anhui Agricultural University |
|
TR01 | Transfer of patent right |