CN109187552B - Wheat scab damage grade determination method based on cloud model - Google Patents
Wheat scab damage grade determination method based on cloud model Download PDFInfo
- Publication number
- CN109187552B CN109187552B CN201810999005.8A CN201810999005A CN109187552B CN 109187552 B CN109187552 B CN 109187552B CN 201810999005 A CN201810999005 A CN 201810999005A CN 109187552 B CN109187552 B CN 109187552B
- Authority
- CN
- China
- Prior art keywords
- color
- wheat
- image
- grade
- ear
- 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.)
- Active
Links
- 241000209140 Triticum Species 0.000 title claims abstract description 52
- 235000021307 Triticum Nutrition 0.000 title claims abstract description 51
- 206010039509 Scab Diseases 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 30
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 40
- 201000010099 disease Diseases 0.000 claims abstract description 39
- 238000011156 evaluation Methods 0.000 claims abstract description 25
- 238000013210 evaluation model Methods 0.000 claims abstract description 15
- 208000032625 disorder of ear Diseases 0.000 claims description 40
- 241000495841 Oenanthe oenanthe Species 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 6
- 241000196324 Embryophyta Species 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 241000223218 Fusarium Species 0.000 claims description 3
- 238000005314 correlation function Methods 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 2
- 230000008859 change Effects 0.000 abstract description 5
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 abstract description 2
- 230000003902 lesion Effects 0.000 abstract 1
- 230000000875 corresponding effect Effects 0.000 description 17
- 235000013339 cereals Nutrition 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 241001024327 Oenanthe <Aves> Species 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 239000000575 pesticide Substances 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000010977 jade Substances 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 208000037921 secondary disease Diseases 0.000 description 1
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
- G01N21/84—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 the technical field of crop disease monitoring, and particularly relates to a wheat scab damage grade determination method based on a cloud model, which comprises the steps of extracting a disease area, constructing color characteristics, generating a wheat scab color characteristic cloud model, establishing a comprehensive evaluation model and analyzing the evaluation model; the relation between the color change of a disease area and the grade of the wheat scab rate in the gradual lesion process of the wheat scab is utilized, the color feature cloud of the disease area is obtained by combining three digital features of the cloud model, and the cloud model is utilized to realize non-rigid division of the grade of the wheat scab so as to realize comprehensive evaluation.
Description
Technical Field
The invention belongs to the technical field of crop disease monitoring, and particularly relates to a wheat scab disease grade determination method based on a cloud model.
Background
The rapid development of computer technology improves the speed and efficiency of automatic detection and identification of plant diseases. Such as hyperspectral techniques, image processing techniques, etc. Like jade, glittering and translucent and the like use a hyperspectral imager to analyze spectrometer information reflectivity characteristics of healthy wheat grain images and gibberellic disease wheat grain images respectively. Eliminating spectral image noise through a series of spectral preprocessing methods, then identifying texture features, morphological parameters and average gray level feature wave bands, and finally establishing an identification model. Shaohqing, Zhang nan and the like perform image denoising on the diseases of the leaves of wheat, and then realize shape feature extraction on the disease parts, so that the method is an improvement on image processing and simultaneously perfects a feature database of the diseases of the wheat.
According to the technical standard of wheat scab prediction, the disease degree of the incidence degree of wheat scab is divided into 4 grades, but two objects with extremely close conceptual values are classified into different grades due to excessive hard division. For example: the detected ear disease rate is 25.8%, the single wheat plant belongs to grade 2 according to the classification standard of the standard, but the value is extremely close to 25%, and the classification is not reasonable; at present, the scab of wheat ears is removed from living bodies in the study, some wheat ears are even stripped to form wheat ear grains, and the ear disease rate is counted through a series of identification detection methods.
Disclosure of Invention
On the basis of cloud model knowledge representation, the color change from no morbidity to initial morbidity of single living wheat and the constructed characteristic parameters are added to the grading standard given by the standard to serve as another influence factor except the morbidity to generate a color characteristic cloud model, so that more reasonable evaluation on grading is realized.
The invention follows the growth process of living wheat, counts the color change degree and constructs characteristic parameters from no disease occurrence to different disease degrees, and provides a wheat scab damage grade determination method based on a cloud model as an index for identifying and evaluating the wheat disease degree. Compared with the detection of the extirpated wheat, the method is more convincing.
The invention is realized by the following technical scheme: a wheat scab damage grade judging method based on a cloud model comprises the following steps:
s1, extraction of disease area
S11, collecting an initial image of the wheat ear in the field, and denoising to obtain a primary processing image;
s12, performing image segmentation on the a component of the primary processing image in Lab space by adopting an Otsu method to obtain an a component image;
s13, obtaining an ear edge image by adopting an edge recognition algorithm on the primary processing image;
s14, performing bit operation on the gray values of the a component image and the ear edge image respectively, setting pixel points with the same gray values of the a component image and the ear edge image as 0 (black), setting pixel points with different gray values as 255 (white), and marking the pixel points with the gray values of 255 as disease pixel points to obtain a disease pixel point distribution graph;
s15, extracting initial pixel points at positions corresponding to the disease pixel point distribution graph in the initial image by utilizing the corresponding of the disease pixel point distribution graph and the initial image to obtain an initial pixel point distribution graph;
s16, marking red at the corresponding position in the initial image by using the initial pixel point distribution map to obtain a disease marking image;
s2 structure of color feature
S21, taking the color of the initial pixel point obtained in the step S15 as a basis for counting the color moment of the wheat scab incidence, and counting the color moment of the wheat scab incidence of the single plant by using a calculation formula of first order distance, second order distance and third order moment, wherein the calculation formula of the first order distance, the second order distance and the third order moment is as follows:
s22, constructing a plurality of intermediate color parameters according to the combination relationship among the color components in the color spaces HSV, RGB and Lab;
s23, recording the color moments and the intermediate color parameters as evaluation color parameters, and calculating the correlation coefficient of each evaluation color parameter by using a correlation function corr ();
s24, judging the significance level of the correlation coefficient of each evaluation color parameter;
table 1 evaluation of correlation coefficients of color parameters
Through analysis of the correlation coefficients of the evaluation color parameters, it can be known that the correlation between only 21 color parameters and the ear disease rate of wheat reaches more than 50%, and 14 color parameters are negatively correlated with the ear disease rate; it is generally believed that: the correlation coefficient is no correlation between 0 and 0.09, weak correlation between 0.1 and 0.3, medium correlation between 0.3 and 0.5, and strong correlation between 0.5 and 1.0. However, the correlation relationship cannot be directly explained because the magnitude of the correlation coefficient is unstable; because the correlation coefficient is related to the nature of the data, the correlation coefficient is variable, and the calculated correlation coefficient may change along with the increase and decrease of the sample size, the strength of the judgment needs to be determined according to not only the correlation coefficient but also the significance; the significance level is the probability that the estimated overall parameter falls in a certain interval and can make errors, and is expressed by alpha; the smaller alpha is, the smaller the probability of indicating that the overall parameter falls in the wrong interval is, the more easily correct the estimation of the correlation is indicated, and the larger alpha is, the greater the probability of indicating that the overall parameter falls in the wrong interval is, namely, the more easily the estimation of the correlation is wrong; generally, alpha is considered to be less than 0.1In (1). In table 1, the left of the correlation coefficient represents that the significance level reached 0.01, indicating that the significance level reached 0.05.
S25, selecting an evaluation color parameter with a correlation coefficient significance level reaching 0.01 as a correlation color parameter, and selecting four correlation color parameters of h-mean, S-mean, h-std and S-std as data sources of the wheat scab color feature cloud model;
s3, generating a wheat gibberella color feature cloud model which is described by three digital features of expected Ex, entropy En and super-entropy He
S31, drawing frequency distribution curves corresponding to different wheat ear disease rate grades by using the related color parameters;
s32, solving peak points in each frequency distribution curve, and taking x values corresponding to the obtained peak points as expected Ex of the cloud model to be generated;
s33, calculating entropy En and super-entropy He according to formulas;
s4, establishing a comprehensive evaluation model
The cloud model is composed of cloud droplets, the cloud droplets contribute to concepts differently, the contribution value of all the cloud droplets on an infinite interval to the concepts is 1, and the contribution value of each cloud droplet to the concepts needs to be considered in the interval of the partition; according to the concept of 3En criterion, taking a partition space of X in the cloud modelCalculate the average contribution of cloud droplets on this interval to concept AMean contribution ofThe formula of (1) is as follows:
the sum formula of the contribution of the elements over the whole interval to the concept a is given as follows:
after analysis, the contribution of elements in the domain of discourse [ Ex-3En, Ex +3En ] to the concept reaches 99.74%, and the elements distributed outside the domain of discourse [ Ex-3En, Ex +3En ] can be basically ignored due to the excessively low contribution value;
s41, calculating the values of Ex-0.67En and Ex +0.67En according to the digital characteristics corresponding to the relevant color parameters;
s42, respectively constructing an evaluation model according to the grades of different wheat ear diseases rates by using intervals [ Ex-0.67En, Ex +0.67En ];
s5 analysis of evaluation model
S51, evaluating the wheat ear disease rate of a certain grade, and judging an interval [ Ex-0.67En, Ex +0.67En ] corresponding to each relevant color parameter in the grade as a relevant color parameter evaluation interval, wherein if the relevant color parameter evaluation intervals corresponding to all relevant parameters in the grade are intersected at the same time, the grade of the wheat ear disease rate close to a higher grade in a wireless mode is defined in the current grade; otherwise, it may not be classified into the current level.
Wherein, the proportional value of R, G, B in the RGB color space represents chromaticity coordinates (R, G, B), and satisfies R + G + B =1, and the calculation formulas thereof are respectively: r = R/(R + G + B); g = G/(R + G + B); b = B/(R + G + B).
The denoising method in the step S11 is median filtering denoising; the frequency distribution curve is plotted using the hist () function in the python library.
Wherein the grade of the wheat ear disease rate comprises: the first-level ear disease rate is 20-25%, the second-level ear disease rate is 45-50%, and the third-level ear disease rate is 70-75%.
Wherein the peak point is a local maximum of the frequency distribution curve.
Compared with the prior art, the invention has the following advantages: according to the method, the comprehensive grading evaluation standard is utilized, the incidence situation of wheat head gibberellic disease caused by picking wheat head grains without using living bodies can be tracked, the limitation of hard grading can be effectively relieved, the standard can be provided for the evaluation of the wheat head gibberellic disease, and reasonable guidance is provided for the water application and the pesticide application of the wheat head gibberellic disease.
Drawings
FIG. 1 is a histogram of the a and b components of the Lab color space;
FIG. 2 is an a-component image;
FIG. 3 is an image of an ear edge;
FIG. 4 is a distribution diagram of diseased pixels;
FIG. 5 is a distribution diagram of initial pixel points;
FIG. 6 is a disease signature image;
FIGS. 7-10 are frequency distribution curves of four relevant color parameters for first-order ear-of-disease rate;
FIGS. 11-14 are frequency distribution curves of four relevant color parameters for secondary ear rate;
FIGS. 15-18 are four relevant color parameter frequency distribution curves for tertiary ear disease rate;
FIGS. 19-22 are cloud models formed by four relevant color parameters for primary ear rate;
FIGS. 23-26 are cloud models formed by four relevant color parameters for secondary ear rate;
FIGS. 27-30 are cloud models formed by four relevant color parameters for the tertiary prevalence;
note that the initial pixel points and the original image of the disease marker map in fig. 4 are color images.
Detailed Description
The following describes in detail specific embodiments of the present invention. It should be understood that the detailed description and specific examples, while indicating the present invention, are given by way of illustration and explanation only, not limitation.
A wheat scab damage grade judging method based on a cloud model comprises the following steps:
s1, extraction of disease area
S11, collecting an initial image of the wheat ear in the field, and denoising to obtain a primary processing image;
s12, performing image segmentation on the a component of the primary processing image in Lab space by adopting an Otsu method to obtain an a component image as shown in FIG. 2;
compared with other color spaces, the Lab color space has the widest color representation range and is not influenced by illumination, the component a in the Lab color space has obvious peaks and troughs when a color histogram is drawn, and compared with the component b, the outline of an object can be seen to be clearer, and the detail is shown in FIG. 1; the target is easier to be divided by using the color, so the a component in the Lab color space realizes image division in the invention;
s13, obtaining an ear edge image by adopting an edge recognition algorithm on the primary processing image as shown in figure 3;
s14, performing bit operation on the gray values of the a-component image and the ear edge image, setting the pixel points with the same gray value as the gray value of the a-component image and the ear edge image as 0 (black), setting the pixel points with different gray values as 255 (white), and then marking the pixel points with the gray value of 255 as disease pixel points to obtain a disease pixel point distribution map as shown in fig. 4;
s15, extracting initial pixel points at positions corresponding to the disease pixel point distribution graph in the initial image by utilizing the corresponding relationship between the disease pixel point distribution graph and the initial image, and obtaining the initial pixel point distribution graph as shown in FIG. 5;
s16, marking red at the corresponding position in the initial image by using the initial pixel point distribution map to obtain a disease marking image as shown in FIG. 6;
s2 structure of color feature
S21, taking the color of the initial pixel point obtained in the step S15 as a basis for counting the color moment of the wheat scab incidence, and counting the color moment of the wheat scab incidence of the single plant by using a calculation formula of first-order distance, second-order distance and third-order moment;
s22, constructing a plurality of intermediate color parameters according to the combination relationship among the color components in the color spaces HSV, RGB and Lab; the proportional values of R, G, B in the RGB color space represent chromaticity coordinates (R, G, B), and satisfy R + G + B =1, and the calculation formulas thereof are: r = R/(R + G + B); g = G/(R + G + B); b = B/(R + G + B);
s23, recording the color moments and the intermediate color parameters as evaluation color parameters, and calculating the correlation coefficient of each evaluation color parameter by using a correlation function corr ();
s24, judging the significance level of the correlation coefficient of each evaluation color parameter, wherein the specific content is shown in Table 1;
through analysis of the correlation coefficients of the evaluation color parameters, it can be known that the correlation between only 21 color parameters and the ear disease rate of wheat reaches more than 50%, and 14 color parameters are negatively correlated with the ear disease rate; it is generally believed that: the correlation coefficient is no correlation between 0 and 0.09, weak correlation between 0.1 and 0.3, medium correlation between 0.3 and 0.5, and strong correlation between 0.5 and 1.0. However, the correlation relationship cannot be directly explained because the magnitude of the correlation coefficient is unstable; because the correlation coefficient is related to the nature of the data, the correlation coefficient is variable, and the calculated correlation coefficient may change along with the increase and decrease of the sample size, the strength of the judgment needs to be determined according to not only the correlation coefficient but also the significance; the significance level is the probability that the estimated overall parameter falls in a certain interval and can make errors, and is expressed by alpha; the smaller alpha is, the smaller the probability of indicating that the overall parameter falls in the wrong interval is, the more easily correct the estimation of the correlation is indicated, and the larger alpha is, the greater the probability of indicating that the overall parameter falls in the wrong interval is, namely, the more easily the estimation of the correlation is wrong; typically, α is considered to be less than 0.1. In table 1, the left of the correlation coefficient represents that the significance level reached 0.01, indicating that the significance level reached 0.05.
S25, selecting an evaluation color parameter with a correlation coefficient significance level reaching 0.01 as a correlation color parameter, and selecting four correlation color parameters of h-mean, S-mean, h-std and S-std as data sources of the wheat scab color feature cloud model;
s3, generating a wheat gibberella color feature cloud model which is described by three digital features of expected Ex, entropy En and super-entropy He
S31, drawing frequency distribution curves corresponding to different wheat ear disease rate levels by using data sources corresponding to four relevant color parameters of h-mean, S-mean, h-std and S-std;
the grade of the wheat ear disease rate comprises: the first-level ear disease rate is 20-25%, the second-level ear disease rate is 45-50%, and the third-level ear disease rate is 70-75%;
the frequency distribution curve of four related color parameters of the first-level ear disease rate is shown in figures 7-10;
the frequency distribution curves of four related color parameters of the secondary ear disease rate are shown in FIGS. 11-14;
the frequency distribution curves of four related color parameters of the third-level ear disease rate are shown in the figure 15-18;
s32, solving peak points in each frequency distribution curve, and taking x values corresponding to the obtained peak points as expected Ex of the cloud model to be generated;
s33, calculating entropy En and super-entropy He according to formulas;
TABLE 2 three digital characteristic cloud parameters corresponding to the relevant color parameters at different ear-disease rate levels
The cloud model formed by the four relevant color parameters of the primary ear disease rate is shown in figures 19-22;
the cloud model formed by the four relevant color parameters of the secondary ear disease rate is shown in figures 23-26;
the cloud model formed by the four relevant color parameters of the third-level ear disease rate is shown in the figures 27-30;
s4, establishing a comprehensive evaluation model
S41, calculating the values of Ex-0.67En and Ex +0.67En according to the digital characteristics corresponding to the relevant color parameters;
TABLE 3 associated color parameters correspond to Ex-0.67En and Ex +0.67En values
S42, respectively constructing an evaluation model according to the grades of different wheat ear diseases rates by using intervals [ Ex-0.67En, Ex +0.67En ];
obtaining the evaluation models corresponding to the three grades of the wheat spike disease rate as follows:
Three-stage ear disease rate evaluation model
S5 analysis of evaluation model
S51, according to the above models for evaluating the ear disease rate with different grades, it can be seen that:
(1) when the sick spike rate value is 20% -25%:
If the condition is met, the grade of the wheat ear infinitely approaching to the second grade can be determined to be in the first grade range; if the condition is not met, the elements cannot be classified into one level, because the membership degree of the elements which do not meet the condition to the concept value of the first level is lower;
(2) when the ear disease rate value is 45% -50%:
If the condition is satisfied, the grade of the ear infinitely close to the third grade can be determined to be in the second grade range. If the conditions are not met, the method cannot be divided into two stages.
(3) When the sick spike rate value is 70% -75%:
If the condition is satisfied, the grade of the ear of the plant infinitely close to the fourth grade (the fourth grade ear disease rate is not specified, and the fourth grade ear disease rate is specified to be > 80%) can be determined to be within the range of the third grade. If the conditions are not met, the method cannot be divided into three levels.
The method can effectively relieve the limitation of hard division according to the evaluation standard of comprehensive grading, and provides reasonable guidance for water application and pesticide application of wheat scab.
The preferred embodiments of the present invention have been described in detail, however, the present invention is not limited to the specific details of the above embodiments, and various simple modifications may be made to the technical solution of the present invention within the technical idea of the present invention, and these simple modifications are within the protective scope of the present invention.
It should be noted that the various technical features described in the above embodiments can be combined in any suitable manner without contradiction, and the invention is not described in any way for the possible combinations in order to avoid unnecessary repetition.
In addition, any combination of the various embodiments of the present invention is also possible, and the same should be considered as the disclosure of the present invention as long as it does not depart from the spirit of the present invention.
Claims (7)
1. A wheat scab damage grade judging method based on a cloud model is characterized by comprising the following steps:
s1, extraction of disease area
S11, collecting an initial image of the wheat ear in the field, and denoising to obtain a primary processing image;
s12, performing image segmentation on the a component of the primary processing image in Lab space by adopting an Otsu method to obtain an a component image;
s13, obtaining an ear edge image by adopting an edge recognition algorithm on the primary processing image;
s14, performing bit operation on the gray values of the a component image and the ear edge image respectively, setting the pixel points with the same gray values of the a component image and the ear edge image as 0, setting the pixel points with different gray values as 255, and then marking the pixel points with the gray values of 255 as disease pixel points to obtain a disease pixel point distribution graph;
s15, extracting initial pixel points at positions corresponding to the disease pixel point distribution graph in the initial image by utilizing the corresponding of the disease pixel point distribution graph and the initial image to obtain an initial pixel point distribution graph;
s16, marking red at the corresponding position in the initial image by using the initial pixel point distribution map to obtain a disease marking image;
s2 structure of color feature
S21, taking the color of the initial pixel point obtained in the step S15 as a basis for counting the color moment of the wheat scab incidence, and counting the color moment of the wheat scab incidence of the single plant by using a calculation formula of first moment, second moment and third moment, wherein the calculation formula of the first moment, the second moment and the third moment is as follows:
calculation formula of first moment:
calculation formula of second moment:
the formula for calculating the third moment:
s22, constructing a plurality of intermediate color parameters according to the combination relationship among the color components in the color spaces HSV, RGB and Lab;
s23, recording the color moments and the intermediate color parameters as evaluation color parameters, and calculating the correlation coefficient of each evaluation color parameter by using a correlation function corr ();
s24, judging the significance level of the correlation coefficient of each evaluation color parameter;
s25, selecting an evaluation color parameter with a correlation coefficient significance level reaching 0.01 as a correlation color parameter, and taking the correlation color parameter as a data source of a wheat scab color feature cloud model;
s3, generating a wheat gibberella color feature cloud model which is described by three digital features of expected Ex, entropy En and super-entropy He
S31, drawing frequency distribution curves corresponding to different wheat ear disease rate grades by using the related color parameters;
s32, solving peak points in each frequency distribution curve, and taking x values corresponding to the obtained peak points as expected Ex of the cloud model to be generated;
s33, calculating entropy En and super-entropy He according to formulas;
s4, establishing a comprehensive evaluation model
S41, calculating the values of Ex-0.67En and Ex +0.67En according to the digital characteristics corresponding to the relevant color parameters;
s42, respectively constructing an evaluation model according to the grades of different wheat ear diseases rates by using intervals [ Ex-0.67En, Ex +0.67En ];
s5 analysis of evaluation model
S51, evaluating the ear disease rate of wheat at a certain grade, and judging an interval [ Ex-0.67En, Ex +0.67En ] corresponding to each relevant color parameter in the grade as a relevant color parameter evaluation interval, wherein if the relevant color parameter evaluation intervals corresponding to all relevant parameters in the grade are intersected at the same time, the grade infinitely approaching the ear disease rate of wheat at a higher grade is defined in the current grade; otherwise, it may not be classified into the current level.
2. The method for determining the wheat scab damage level based on the cloud model as claimed in claim 1, wherein the denoising method in the step S11 is median filtering denoising.
3. The method for determining wheat scab damage level according to claim 1, wherein said R, G, B scale values in RGB color space represent chromaticity coordinates (R, G, B) satisfying R + G + B =1, and the calculation formulas are: r = R/(R + G + B); g = G/(R + G + B); b = B/(R + G + B).
4. The method for judging the wheat scab damage level based on the cloud model as claimed in claim 1, wherein the evaluation color parameters with the significance level of the correlation coefficient reaching 0.01 are h-mean, s-mean, h-std and s-std.
5. The method for determining the level of wheat scab damage based on the cloud model as claimed in claim 1, wherein said frequency distribution curve is plotted using a hist () function in a python library.
6. The method for judging the grade of wheat scab damage based on the cloud model as claimed in claim 1, wherein the grade of the wheat scab damage rate comprises: the first-level ear disease rate is 20-25%, the second-level ear disease rate is 45-50%, and the third-level ear disease rate is 70-75%.
7. The method for determining the level of wheat scab damage based on the cloud model as claimed in claim 1, wherein said peak point is a local maximum of a frequency distribution curve.
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 CN109187552A (en) | 2019-01-11 |
CN109187552B true 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) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN110089297B (en) * | 2019-05-18 | 2021-11-26 | 安徽大学 | Method and device for diagnosing severity of disease condition of wheat scab in field environment |
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 |
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 |
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 |
CN110736750B (en) * | 2019-10-28 | 2022-03-04 | 安徽大学 | Wheat scab detection method based on multi-angle field high-definition imaging |
Citations (3)
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 |
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 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9336584B2 (en) * | 2014-06-30 | 2016-05-10 | Trimble Navigation Limited | Active imaging systems for plant growth monitoring |
-
2018
- 2018-08-30 CN CN201810999005.8A patent/CN109187552B/en active Active
Patent Citations (3)
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 |
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 |
---|
关于果林中果害虫图像特征高效分类识别仿真;程鲁玉等;《计算机仿真》;20180215;第35卷(第02期);第425-428页 * |
基于图像分析技术的小麦叶面积指数智能估算;杨天东 等;《农业网络信息》;20170526(第05期);第86-89页 * |
Also Published As
Publication number | Publication date |
---|---|
CN109187552A (en) | 2019-01-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109187552B (en) | Wheat scab damage grade determination method based on cloud model | |
CN110309781B (en) | House damage remote sensing identification method based on multi-scale spectrum texture self-adaptive fusion | |
CN107356515B (en) | Method and system for determining fluorescence intensity of fluorescence image | |
Siraj et al. | Digital image classification for Malaysian blooming flower | |
JP5567448B2 (en) | Image area dividing apparatus, image area dividing method, and image area dividing program | |
CN112464942B (en) | Computer vision-based overlapped tobacco leaf intelligent grading method | |
CN108563979B (en) | Method for judging rice blast disease conditions based on aerial farmland images | |
CN109145848B (en) | Wheat ear counting method | |
US20120213440A1 (en) | Systems and Methods for Automatically Identifying Shadows in Images | |
CN109409389B (en) | Multi-feature-fused object-oriented change detection method | |
CN105320970B (en) | A kind of potato disease diagnostic device, diagnostic system and diagnostic method | |
CN111259925B (en) | K-means clustering and width mutation algorithm-based field wheat spike counting method | |
CN103793709A (en) | Cell recognition method and device, and urine analyzer | |
CN117575953B (en) | Detail enhancement method for high-resolution forestry remote sensing image | |
CN103500343A (en) | Hyperspectral image classification method based on MNF (Minimum Noise Fraction) transform in combination with extended attribute filtering | |
CN112396619A (en) | Small particle segmentation method based on semantic segmentation and internally complex composition | |
CN108364011A (en) | PolSAR image multi-stage characteristics extract and unsupervised segmentation method | |
CN111046838A (en) | Method and device for identifying wetland remote sensing information | |
CN113111969B (en) | Hyperspectral image classification method based on mixed measurement | |
Kent et al. | Early symptom detection of basal stem rot disease in oil palm trees using a deep learning approach on UAV images | |
CN113283538A (en) | Insect classification and counting method based on convolutional neural network | |
CN107657246A (en) | A kind of remote sensing image building detection method based on multi-scale filtering building index | |
CN111340761B (en) | Remote sensing image change detection method based on fractal attribute and decision fusion | |
CN111062954A (en) | Infrared image segmentation method, device and equipment based on difference information statistics | |
CN103366376B (en) | A kind of image characteristic extracting method based on neighborhood dimensional variation |
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 |