CN109801235B - Method and device for detecting disease cause of epipremnum aureum leaves - Google Patents
Method and device for detecting disease cause of epipremnum aureum leaves Download PDFInfo
- Publication number
- CN109801235B CN109801235B CN201811624647.6A CN201811624647A CN109801235B CN 109801235 B CN109801235 B CN 109801235B CN 201811624647 A CN201811624647 A CN 201811624647A CN 109801235 B CN109801235 B CN 109801235B
- Authority
- CN
- China
- Prior art keywords
- image
- leaf
- scab
- image area
- foreground
- 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
Images
Abstract
The invention discloses a method and a device for detecting the cause of a green bonnie leaf disease, which are used for realizing the automatic identification of the green bonnie leaf disease, select single diseased leaves for classification and statistics, classify and count the leaves with leaf spot and anthracnose at the same time, extract the characteristic values of leaf colors through RGB and YCbCr color spaces, judge whether a diseased spot appears in a leaf image to be detected in a diseased spot image area, and calculate the diseased spot image area range of the diseased spot image area, thereby greatly reducing the time and cost of manual protection, being capable of carrying out real-time automatic observation and early warning on the leaves, and being more convenient for the intelligent management of plants.
Description
Technical Field
The disclosure relates to the field of plant disease cause detection, in particular to a method and a device for detecting a disease cause of a scindapsus aureus leaf.
Background
The disease causes of plant leaves are various, and common epipremnum aureum leaves mainly comprise two types of leaf spot and carbon bacterial disease. Leaf blotch is a major hazard to the leaves of scindapsus aureus, and many small brown spots appear in the early stage of the disease, and in severe cases, the spots are spread over the entire leaf. If timely discovery is carried out, the disease can be prevented and cured only by removing diseased leaves at the early stage of disease attack and spraying 95% of amobam 500 times liquid or 80% of carbendazim 1000 times liquid and the like. From the current practical planting situation, the following defects exist in the detection and solution measures of the leaf diseases of the plants: 1. because the initial symptoms of the plant diseases are often difficult to judge and the grower lacks comprehensive knowledge on the disease diagnosis of the flowers and plants, the pesticide is sprayed and fertilized when the disease development tends to be serious in the management of the plant diseases, so that the diseases cannot be effectively controlled in time; 2. the increasingly busy pace of life makes people not only have no time and no energy to manage whether plants are attacked by diseases, but also fail to provide various prevention and control measures; 3. although the PCR technology basically solves the problems of plant fungal pathogen identification, disease detection, genetic diversity, disease resistance based analysis and the like at present, plant experts describe symptoms by fuzzy language and cannot describe disease causes by using accurate and quantitative symbols due to the fact that the individual knowledge difference of growers and the disease symptoms of some plants are complex and fuzzy and diverse, so that the growers cannot correctly judge plant diseases; 4. the difficulty of the PCR molecular detection technology lies in that because DNA has polymorphism, a certain marked segment may have specificity transformation to make the distribution of genome uneven, thus greatly limiting the accuracy of PCR gene positioning, and the problems of complicated experimental operation, long detection time, high cost and the like exist in the experimental process.
Disclosure of Invention
The invention provides a method and a device for detecting the cause of a green bonnie leaf disease, which aim to realize the automatic identification of the green bonnie leaf disease.
In order to achieve the above object, according to an aspect of the present disclosure, there is provided a method for detecting a cause of a disease of a scindapsus aureus leaf, the method comprising the steps of:
step 1, preprocessing an image of a blade to be detected to obtain a de-noised image;
step 2, carrying out image segmentation on the denoised image to obtain a foreground image;
step 3, converting the foreground image through a color space to highlight a scab image area;
step 4, judging whether the leaf image to be detected has scabs in the scab image area;
and 5, calculating the range of the lesion image area.
Further, in step 1, the blade image to be measured is a scindapsus aureus blade picture shot by the line camera.
Further, in step 1, the method for preprocessing the blade image to be detected to obtain the denoised image includes that for the pixel at the pixel point position (i, j) of the blade image to be detected, the gray value of (i, j) is f (i, j), the smoothed gray value is g (i, j), and the method is implemented by using a formula
Smoothing the gray value of the pixel points of the blade image to be detected to obtain a de-noised image g (i, j), wherein A is a set of neighborhood points with (i, j) as the center, M is the total number of the pixel points in A, and x, y =0,1,2, \ 8230;, M-1.
Further, in step 2, the method of performing image segmentation on the denoised image to obtain the foreground image comprises,
let the denoised image be g (i, j), θ (x, y) be the two-dimensional smoothing function ^ integral R ∫ R θ(x,y)dxdy＝1；
The partial derivatives in the x-direction and y-direction for the smoothing function θ (x, y), respectively, have: partial derivative in x direction
Partial derivative in the y-direction->
For any function g (i, j) ∈ R 2 ，R 2 Is an image of 2-dimensional space and is composed of two wavelets phi 1 (x, y) and phi 2 (x, y) has two components:
the gradient vector is:
wherein: s is a scale coefficient, and S is defaulted to 1;
and &>
Partial derivatives in the x, y direction in the image, respectively, wavelet transform at scale 2 j The mode and the argument of (a) are respectively: />
Modulus W of wavelet transform 2j g (x, y) is proportional to the gradient vector
Modulus of (1), argument A of wavelet transform 2j g (x, y) is a gradient vector @>
The included angle between the horizontal direction and the horizontal direction is the edge of image segmentation, and a gradient vector is searched
Performing image segmentation on the local maximum point of the model to obtain a foreground image; at each scale 2 j The maximum of the modulus of the wavelet transform is defined as modulus W 2j g (x, y) is at a local maximum point along the gradient direction, (g x θ) (x, y) is g (i, j) orthogonal to θ (x, y).
Further, in step 3, the method for converting the foreground image through the color space to highlight the lesion image area is that,
step 3.1, converting the foreground image from an RGB space to a YCbCr space, wherein the space conversion formula is as follows:
r, G and B are color values of red, green and blue channels of the pixel point respectively, Y is brightness, namely gray level value, the brightness is established through RGB input signals, the method is to superpose specific parts of the RGB signals together, cb is the difference between the blue part of the RGB input signals and the brightness value of the RGB signals, and Cr is the red part of the RGB input signals and the RGB signalsA difference between the luminance values;
step 3.2, because Cr and Cb respectively have normal distribution characteristics relative to Y, a lesion image area in the foreground image is highlighted by using a normal distribution parameter evaluation method in a YCbCr space, and the normal distribution function expression is as follows:
that is, when Cr and Cb in the pixel region in the foreground image satisfy the distribution in the interval of the mean value and the standard deviation, that is, the region where F (x, y) composed of Cr and Cb satisfies the F distribution is the lesion image region.
Furthermore, in step 4, the method for judging whether the leaf image to be measured has the scab in the scab image area is that,
the scab image area of the scindapsus aureus leaf with the pathological changes such as leaf spot and anthracnose appears white, black and gray, namely R, G and B components are approximately equal in RGB space, the color brightness of the scab image area is different according to the pathological changes, and the color characteristic of the scab image area is the following constraint condition according to the constraint of Y channel component in YCbCr color space, wherein R +/-alpha = G +/-alpha = B +/-alpha, and L is 1 ≤Y≤L 2 Alpha is an integer ranging from 10 to 50, L 1 Is 70,L 2 Is 150, alpha, L 1 ,L 2 The data are the actual statistical data of the pathological changes of the scindapsus aureus leaves, and the scindapsus aureus leaves are judged to have the pathological changes if the constraint conditions are met.
Further, in step 5, a lesion image of the lesion image area is calculatedThe area range method comprises the steps of obtaining an average color by averaging RGB values of sample points selected in a scab image area according to color features of the scab image area, wherein the average color is defined by an RGB column vector m, z represents any pixel vector in an RGB space, if the distance between z and m is smaller than a specified threshold value T, and the threshold value T =100, z is similar to m, and the Euclidean distance D (z, m) between z and m is as follows,
m R ,m G ,m B r, G and B components of the vector m, respectively, z R ,z G ,z B R, G, and B components of vector z, respectively; the locus of the points with the radius of D (z, m) less than or equal to T is the range of the lesion image area with the radius of T.
The invention also provides a device for detecting the disease cause of the epipremnum aureum leaves, which comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to run in units of:
the image preprocessing unit is used for preprocessing the blade image to be detected to obtain a de-noised image;
the foreground segmentation unit is used for carrying out image segmentation on the denoised image to obtain a foreground image;
the scab highlighting unit is used for highlighting a scab image area through converting the foreground image by a color space;
the scab judging unit is used for judging whether the leaf image to be detected has scabs in the scab image area;
and the lesion area calculating unit is used for calculating the lesion image area range of the lesion image area.
The beneficial effect of this disclosure does: the invention provides a method and a device for detecting the disease cause of epipremnum aureum leaves, which greatly reduce the time and cost of manual protection, can automatically observe and early warn the leaves in real time and periodically and is more convenient for the intelligent management of plants.
Drawings
The foregoing and other features of the present disclosure will become more apparent from the detailed description of the embodiments shown in conjunction with the drawings in which like reference characters designate the same or similar elements throughout the several views, and it is apparent that the drawings in the following description are merely some examples of the present disclosure and that other drawings may be derived therefrom by those skilled in the art without the benefit of any inventive faculty, and in which:
FIG. 1 is a flow chart of a method for detecting the cause of a disease in a scindapsus aureus leaf;
FIG. 2 is a schematic view of a leaf suffering from leaf blight;
FIG. 3 is a schematic view of a leaf blade with anthrax plaques;
FIG. 4 is a schematic representation of a leaf blade with leaf spot and anthracnose;
FIG. 5 is a diagram of a detecting device for detecting the cause of a disease of a scindapsus aureus leaf.
Detailed Description
The conception, the specific structure and the technical effects produced by the present disclosure will be clearly and completely described in conjunction with the embodiments and the attached drawings, so that the purposes, the schemes and the effects of the present disclosure can be fully understood. It should be noted that, in the present application, the embodiments and features of the embodiments may be combined with each other without conflict.
Fig. 1 is a flow chart of a method for detecting the cause of the epipremnum aureum leaf disease according to the present disclosure, and a method for detecting the cause of the epipremnum aureum leaf disease according to an embodiment of the present disclosure is described below with reference to fig. 1.
The invention provides a method for detecting the cause of a disease of scindapsus aureus leaf, which specifically comprises the following steps:
step 1, preprocessing an image of a blade to be detected to obtain a de-noised image;
step 2, carrying out image segmentation on the denoised image to obtain a foreground image;
step 3, converting the foreground image through a color space to highlight a scab image area;
step 4, judging whether the leaf image to be detected has scabs in the scab image area;
and 5, calculating the range of the lesion image area.
Further, in step 1, the blade image to be measured is a scindapsus aureus blade picture shot by the line camera.
Further, in step 1, the method for preprocessing the blade image to be detected to obtain the denoised image includes that for the pixel at the pixel point position (i, j) of the blade image to be detected, the gray value of (i, j) is f (i, j), the smoothed gray value is g (i, j), and the method is implemented by using a formula
Smoothing the gray value of the pixel points of the blade image to be detected to obtain a de-noised image g (i, j), wherein A is a set of neighborhood points with (i, j) as the center, M is the total number of the pixel points in A, and x, y =0,1,2, \ 8230;, M-1.
Furthermore, in step 2, the method of performing image segmentation on the denoised image to obtain a foreground image is that,
let the denoised image be g (i, j), and θ (x, y) be the two-dimensional smooth function ^ integral R ∫ R θ(x,y)dxdy＝1；
The partial derivatives in the x-direction and y-direction for the smoothing function θ (x, y), respectively, have: partial derivative in x direction
Partial derivative in the y-direction->
For any function g (i, j) ∈ R 2 ，R 2 Is an image of 2-dimensional space and is composed of two wavelets phi 1 (x, y) and phi 2 (x, y) has two components:
the gradient vector is:
wherein: s is a scale coefficient, and S is defaulted to 1;
and &>
Partial derivatives in the x, y direction in the image, respectively, wavelet transform at scale 2 j The mode and the argument of (a) are respectively: />
Modulus W of wavelet transform 2j g (x, y) is proportional to the gradient vector
Modulus of (1), argument of wavelet transform
Is the gradient vector pick>
The included angle between the horizontal direction and the horizontal direction is the edge of image segmentation, and a gradient vector is searched
Performing image segmentation on the local maximum value point of the model to obtain a foreground image; at each scale 2 j The maximum of the modulus of the wavelet transform is defined as modulus->
At the local maximum point along the gradient direction, x, y =0,1,2, \ 8230;, M-1.
Further, in step 3, the method for converting the foreground image through the color space to highlight the lesion image area is that,
step 3.1, converting the foreground image from an RGB space to a YCbCr space, wherein the space conversion formula is as follows:
wherein, R, G, B are color values of red, green, blue three channels of the pixel respectively, Y is brightnessI.e., gray scale values, the luminance is established through the RGB input signals by superimposing specific portions of the RGB signals together, cb being the difference between the blue portion of the RGB input signals and the luminance values of the RGB signals, cr being the difference between the red portion of the RGB input signals and the luminance values of the RGB signals;
step 3.2, because Cr and Cb respectively have normal distribution characteristics relative to Y, a lesion image area in the foreground image is highlighted by using a normal distribution parameter evaluation method in a YCbCr space, and the normal distribution function expression is as follows:
that is, when Cr and Cb in the pixel region in the foreground image satisfy the distribution in the interval of the mean value and the standard deviation, that is, the region where F (x, y) composed of Cr and Cb satisfies the F distribution is the lesion image region.
Furthermore, in step 4, the method for judging whether the leaf image to be detected has the scab in the scab image area is that,
referring to fig. 2, 3 and 4, the lesion image area of the scindapsus aureus leaf with the lesion such as leaf spot disease and anthracnose appears white, black and gray, that is, the three components of R, G and B are approximately equal in RGB space, the color brightness of the lesion image area is different according to the lesion condition, and the color feature of the lesion image area is the following constraint condition according to the constraint of Y channel component in YCbCr color space, R ± α = G ± α = B ± α, L 1 ≤Y≤L 2 Alpha is an integer ranging from 10 to 50, L 1 Is 70，L 2 Is 150, alpha, L 1 ,L 2 The data are the actual statistical data of the pathological changes of the scindapsus aureus leaves, and the scindapsus aureus leaves are judged to have the pathological changes if the constraint conditions are met.
Further, in step 5, the range of the lesion image area is calculated by averaging RGB values of sample points selected from the lesion image area according to color features of the lesion image area to obtain an average color, the average color is defined by RGB column vector m, where z represents any pixel vector in RGB space, and if a distance between z and m is less than a specified threshold T, and the threshold T =100, z is similar to m, and an euclidean distance D (z, m) between z and m is D (z, m) = [ (z, m) = where D (z, m) = is R -m R ) 2 +(z G -m G ) 2 +(z B -m B ) 2 ] 1/2 ，m R ,m G ,m B R, G and B components of the vector m, respectively, z R ,z G ,z B R, G, and B components of vector z, respectively; the locus of the point with the radius of D (z, m) less than or equal to T is the range of the lesion image area with the radius of T.
In an embodiment 1 of the present disclosure, as shown in fig. 2 and fig. 3, the leaf of the scindapsus aureus and the leaf of the anthracnose are respectively selected for experiments, and because different parts of the leaf and the background absorb light differently, the illuminance of the obtained leaf image is uneven, some parts are dark, and some parts are bright, which may affect the correct segmentation of the target object, so that the uneven illuminance of the leaf image is eliminated before the background is removed. In the experiment, a wavelet transform illumination unevenness elimination technology is adopted, signals are subjected to multi-scale refinement through telescopic translation operation, and finally high-frequency subdivision and low-frequency subdivision are achieved, so that the segmentation of a background and a target blade is achieved. Then, carrying out noise processing on the obtained blade, and selecting a 10 multiplied by 10 timing filter to carry out median filtering; sliding the module in the image, and overlapping the center of the module with a certain pixel point in the image; and reading the gray values of the corresponding pixels under the module, sequencing the pixels from small to large, and finally giving the intermediate value to the central pixel of the template, so that the gray difference of the surrounding pixels tends to 0, and further eliminating isolated noise points. In order to obtain lesion segmentation objects better, a self-adaptive fuzzy threshold segmentation method is adopted to segment leaf lesions, morphological feature, color feature and texture feature information of the obtained leaves are extracted, the areas of lesion areas are calculated according to different characteristics of the lesions in different periods, and the information is summarized to obtain a classifier of lesion degrees. The experimental result provides reliable basis for detecting that the epipremnum aureum leaves are suffered from the anthracnose leaves, improves the ventilation environment of the plants, and keeps the moist of the pot soil so as to increase the resistance of the plants. If the disease state is in the early stage, 80% of thiram wettable powder 500 times liquid can be added into water for spraying, and the spraying is carried out once every 10 days at regular time and continuously for 2-3 times.
In an embodiment 2 of the present disclosure, as shown in fig. 4, a leaf with a leaf spot and an anthracnose is selected to perform an experiment, the experiment is mainly performed in five steps, a first step classification system first preprocesses the leaf collected by a camera to eliminate image noise generated due to environmental factors, when a pixel value of a pixel is a maximum value or a minimum value in a neighborhood filtering window, the pixels in the neighborhood filtering window are arranged from large to small, and a pixel value in a middle position is selected as a pixel value of the neighborhood filtering window to process a plant leaf image; secondly, performing image segmentation on the processed scindapsus aureus leaf image, highlighting a scab image area through color space conversion, further eliminating a pixel channel superposition area and a background area, leaving an area containing scab leaves, and then applying a Y channel component in a YCbCr color space to enhance the scab area; thirdly, extracting pixel characteristic values including morphology, color, texture and gradient histogram characteristics by using the scab image area obtained by image segmentation, and respectively obtaining classification data for different scab characteristics; after extracting the feature data of the lesion spots of different types, dividing the data of different types in the same feature by using a function curve, and determining the total feature of the lesion spot area by integrating the dividing curve functions of different features; and finally, symptoms of the classified different lesion feature data models are given and input in a mode of defining lesion regional symptoms, so that regional feature data of lesions can be directly extracted next time and compared with model data to determine the symptoms. In order to prevent the epipremnum aureum leaves from suffering from the leaf spot disease, the epipremnum aureum can be supplemented with light at regular time, if the leaf spot disease is serious, a proper amount of streptomycin can be added in watering, the symptom of the leaf spot disease can be effectively improved, and the experiment provides an important basis for the inspection and solution method of the epipremnum aureum disease.
An apparatus for detecting a disease cause of a epipremnum aureum leaf provided by an embodiment of the present disclosure is shown in fig. 5, and the apparatus for detecting a disease cause of a epipremnum aureum leaf of the present disclosure includes: the detection device comprises a processor, a memory and a computer program which is stored in the memory and can run on the processor, wherein the processor executes the computer program to realize the steps in the embodiment of the detection device for the disease cause of the epipremnum aureum leaf.
The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to operate in the units of:
the image preprocessing unit is used for preprocessing the blade image to be detected to obtain a de-noised image;
the foreground segmentation unit is used for carrying out image segmentation on the denoised image to obtain a foreground image;
the scab highlighting unit is used for highlighting a scab image area through converting the foreground image by a color space;
the scab judging unit is used for judging whether the leaf image to be detected has scabs in the scab image area;
and the lesion area calculation unit is used for calculating the lesion image area range of the lesion image area.
The scindapsus aureus leaf disease cause detection device can be operated in computing equipment such as desktop computers, notebooks, palm computers and cloud servers. The scindapsus aureus leaf disease cause detection device can be operated by devices including, but not limited to, a processor and a memory. Those skilled in the art will appreciate that the example is only an example of a detecting device for detecting the disease cause of the epipremnum aureum leaf, and does not constitute a limitation to the detecting device for detecting the disease cause of the epipremnum aureum leaf, and may include more or less components than the epipremnum aureum leaf, or combine some components, or different components, for example, the detecting device for detecting the disease cause of the epipremnum aureum leaf may further include an input-output device, a network access device, a bus, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general processor can be a microprocessor or the processor can be any conventional processor and the like, the processor is a control center of the operating device of the detecting device for detecting the disease cause of the epipremnum aureum, and various interfaces and lines are utilized to connect all parts of the operating device of the detecting device for detecting the disease cause of the epipremnum aureum.
The memory can be used for storing the computer program and/or the module, and the processor realizes various functions of the epipremnum aureum leaf disease cause detection device by running or executing the computer program and/or the module stored in the memory and calling the data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the cellular phone, and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
While the present disclosure has been described in considerable detail and with particular reference to a few illustrative embodiments thereof, it is not intended to be limited to any such details or embodiments or any particular embodiments, but it is to be construed as effectively covering the intended scope of the disclosure by providing a broad, potential interpretation of such claims in view of the prior art with reference to the appended claims. Furthermore, the foregoing description of the present disclosure has been presented in terms of embodiments foreseen by the inventors for purposes of providing a useful description, and enabling one of ordinary skill in the art to devise equivalent variations of the present disclosure that are not presently foreseen.
Claims (6)
1. A method for detecting the cause of a disease of a scindapsus aureus leaf is characterized by comprising the following steps:
step 1, preprocessing an image of a blade to be detected to obtain a de-noised image;
step 2, carrying out image segmentation on the denoised image to obtain a foreground image;
step 3, converting the foreground image through a color space to highlight a scab image area;
step 4, judging whether the leaf image to be detected has scabs in the scab image area;
step 5, calculating the range of the lesion image area;
in step 2, the method for obtaining the foreground image by performing image segmentation on the denoised image comprises the following steps,
let the denoised image be g (i, j), and θ (x, y) be the two-dimensional smooth function ^ integral R ∫ R θ(x,y)dxdy＝1；
The partial derivatives in the x-direction and y-direction for the smoothing function θ (x, y), respectively, have: partial derivative in x direction
Partial derivative in y direction->
For any function g (i, j) ∈ R 2 ，R 2 Is an image of 2-dimensional space and is composed of two wavelets phi 1 (x,y) and phi 2 (x, y) has two components: />
The gradient vector is:
wherein: s is a scale coefficient, and S is defaulted to 1; />
And
partial derivatives in the x, y directions in the image, respectively, wavelet transform at scale 2 j The mode and the argument of (a) are respectively:
modulus of wavelet transform
Proportional to the gradient vector->
Modulo of (4), amplitude and angle of wavelet transform>
Is a gradient vector>
The included angle between the horizontal direction and the horizontal direction is the edge of image segmentation, and a gradient vector is searched
Performing image segmentation on the local maximum point of the model to obtain a foreground image; at each scale 2 j Maximum of modulus of wavelet transformThe value is defined as modulo>
At the local maximum point along the gradient direction.
2. The method for detecting the cause of the disease of the epipremnum aureum leaf as claimed in claim 1, wherein in the step 1, the method for preprocessing the leaf image to be detected to obtain the de-noised image comprises the steps of obtaining the gray value f (i, j) of the pixel position (i, j) of the leaf image to be detected, obtaining the smoothed gray value g (i, j) of the pixel position (i, j), and calculating the gray value g (i, j) according to the formula
Smoothing the gray value of a pixel point of the blade image to be detected to obtain a de-noised image, wherein A is a set of neighborhood points with (i, j) as the center, M is the total number of the pixel points in A, and x, y =0,1,2, \ 8230;, M-1.
3. The method for detecting the cause of the epiphytic leaf disease of scindapsus aureus as claimed in claim 1, wherein in step 3, the method for transforming the foreground image into the image area highlighting the scab by the color space comprises,
step 3.1, converting the foreground image from an RGB space to a YCbCr space, wherein the space conversion formula is as follows:
r, G and B are color values of red, green and blue channels of a pixel point respectively, Y is brightness, namely a gray scale value, the brightness is established through RGB input signals, the method is to superpose specific parts of the RGB signals together, cb is the difference between the blue part of the RGB input signals and the brightness value of the RGB signals, and Cr is the difference between the red part of the RGB input signals and the brightness value of the RGB signals;
step 3.2, since Cr and Cb respectively have normal distribution characteristics relative to Y, a lesion image area in the foreground image is highlighted by using a normal distribution parameter evaluation method in a YCbCr space, and a normal distribution function expression is as follows:
that is, when Cr and Cb in the pixel region in the foreground image satisfy the distribution in the interval of the mean value and the standard deviation, that is, the region where F (x, y) composed of Cr and Cb satisfies the F distribution is the lesion image region.
4. The method for detecting the cause of the epipremnum aureum leaf disease as claimed in claim 1, wherein in the step 4, the method for judging whether the leaf image to be detected has the scab in the scab image area is that the color feature of the scab image area is the following constraint condition, R ± α = G ± α = B ± α, L ± α 1 ≤Y≤L 2 Alpha is an integer ranging from 10 to 50, L 1 Is 70,L 2 150, if the constraint condition is satisfied, judging that the scindapsus aureus leaf has scab.
5. The method for detecting the cause of the disease of scindapsus aureus leaf as claimed in claim 1, wherein in step 5, the range of the lesion image area is calculated by averaging the RGB values of the sample points selected from the color features of the lesion image area in the lesion image area to obtain an average color, the average color is defined by an RGB column vector m, z represents any pixel vector in the RGB space, if the distance between z and m is smaller than a specified threshold T, and the threshold T =100, z is similar to m, and the euclidean distance between z and m D (z, m) is D (z, m) = [ (z) is R -m R ) 2 +(z G -m G ) 2 +(z B -m B ) 2 ] 1/2 ，m R ,m G ,m B R, G and B components of the vector m, respectively, z R ,z G ,z B The R, G, and B components of vector z, respectively; the locus of the point with the radius of D (z, m) less than or equal to T is the range of the lesion image area with the radius of T.
6. A scindapsus aureus leaf disease cause detection device is characterized by comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the computer program to run in units of:
the image preprocessing unit is used for preprocessing the blade image to be detected to obtain a de-noised image;
the foreground segmentation unit is used for carrying out image segmentation on the denoised image to obtain a foreground image;
the scab highlighting unit is used for highlighting a scab image area through converting the foreground image by a color space;
the scab judging unit is used for judging whether the leaf image to be detected has scabs in the scab image area;
the scab range calculating unit is used for calculating the scab image area range of the scab image area;
the image segmentation of the denoised image to obtain a foreground image comprises the following steps:
let the denoised image be g (i, j), and θ (x, y) be the two-dimensional smooth function ^ integral R ∫ R θ(x,y)dxdy＝1；
The partial derivatives in the x-direction and y-direction for the smoothing function θ (x, y), respectively, have: partial derivative in x direction
Partial derivative in the y-direction->
For any function g (i, j) ∈ R 2 ，R 2 Is 2Image of dimensional space, consisting of two wavelets phi 1 (x, y) and phi 2 (x, y) has two components: />
The gradient vector is:
wherein: s is a scale coefficient, and the default S is 1; />
And
partial derivatives in the x, y direction in the image, respectively, wavelet transform at scale 2 j The mode and the argument of (a) are respectively:
modulus of wavelet transform
Proportional to the gradient vector->
Modulo of (4), amplitude and angle of wavelet transform>
Is the gradient vector pick>
The included angle between the horizontal direction and the horizontal direction is the edge of image segmentation, and a gradient vector is searched
Performing image segmentation on the local maximum point of the model to obtain a foreground image; at each oneDimension 2 j The maximum of the modulus of the wavelet transform is defined as modulus->
At the local maximum point along the gradient direction. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811624647.6A CN109801235B (en) | 2018-12-28 | 2018-12-28 | Method and device for detecting disease cause of epipremnum aureum leaves |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811624647.6A CN109801235B (en) | 2018-12-28 | 2018-12-28 | Method and device for detecting disease cause of epipremnum aureum leaves |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109801235A CN109801235A (en) | 2019-05-24 |
| CN109801235B true CN109801235B (en) | 2023-03-28 |
Family
ID=66557949
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811624647.6A Active CN109801235B (en) | 2018-12-28 | 2018-12-28 | Method and device for detecting disease cause of epipremnum aureum leaves |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109801235B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112413449B (en) * | 2020-11-13 | 2022-10-28 | 北国之光(深圳)科技有限公司 | Intelligent light distribution system and method for plant growth lamp |
| CN112801990A (en) * | 2021-02-03 | 2021-05-14 | 广东省科学院广州地理研究所 | Method for detecting rice blast of rice leaves |
| CN113269690A (en) * | 2021-05-27 | 2021-08-17 | 山东大学 | Method and system for detecting diseased region of blade |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5970164A (en) * | 1994-08-11 | 1999-10-19 | Sophisview Technologies, Ltd. | System and method for diagnosis of living tissue diseases |
| US6185320B1 (en) * | 1995-03-03 | 2001-02-06 | Arch Development Corporation | Method and system for detection of lesions in medical images |
| CN105654445A (en) * | 2016-01-28 | 2016-06-08 | 东南大学 | Mobile phone image denoising method based on wavelet transform edge detection |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102063708B (en) * | 2011-01-06 | 2012-06-27 | 西安电子科技大学 | Image denoising method based on Treelet and non-local means |
| NZ701369A (en) * | 2012-03-28 | 2016-09-30 | Univ Houston System | Methods and software for screening and diagnosing skin lesions and plant diseases |
| JP2015036929A (en) * | 2013-08-15 | 2015-02-23 | 三星電子株式会社Ｓａｍｓｕｎｇ Ｅｌｅｃｔｒｏｎｉｃｓ Ｃｏ．，Ｌｔｄ． | Image feature extraction device, image feature extraction method, image feature extraction program and image processing system |
| CN103808265B (en) * | 2014-02-28 | 2017-04-26 | 北京农业信息技术研究中心 | Method, device and system for measuring oilseed rape laminae and forms of sclerotium scabs synchronously |
| CN104463173B (en) * | 2014-12-12 | 2017-07-07 | 西京学院 | A kind of crop disease recognition methods based on probability density ratio |
| CN106682571B (en) * | 2016-11-08 | 2019-09-27 | 中国民航大学 | Method for detecting human face based on skin color segmentation and wavelet transformation |
| CN108596262A (en) * | 2018-04-28 | 2018-09-28 | 北京麦飞科技有限公司 | A kind of method and system carrying out plant disease spot classification based on computer vision |
-
2018
- 2018-12-28 CN CN201811624647.6A patent/CN109801235B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5970164A (en) * | 1994-08-11 | 1999-10-19 | Sophisview Technologies, Ltd. | System and method for diagnosis of living tissue diseases |
| US6185320B1 (en) * | 1995-03-03 | 2001-02-06 | Arch Development Corporation | Method and system for detection of lesions in medical images |
| CN105654445A (en) * | 2016-01-28 | 2016-06-08 | 东南大学 | Mobile phone image denoising method based on wavelet transform edge detection |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109801235A (en) | 2019-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Bakar et al. | Rice leaf blast disease detection using multi-level colour image thresholding | |
| EP3455782B1 (en) | System and method for detecting plant diseases | |
| CN109801235B (en) | Method and device for detecting disease cause of epipremnum aureum leaves | |
| Archana et al. | Automatic rice leaf disease segmentation using image processing techniques | |
| CN109447945B (en) | Quick counting method for basic wheat seedlings based on machine vision and graphic processing | |
| CN110120042B (en) | Crop image pest and disease damage area extraction method based on SLIC super-pixel and automatic threshold segmentation | |
| CN110415208B (en) | Self-adaptive target detection method and device, equipment and storage medium thereof | |
| CN107563384B (en) | Head and tail identification method of adhered pigs based on generalized Hough clustering | |
| CN107038704B (en) | Retina image exudation area segmentation method and device and computing equipment | |
| CN110223344B (en) | Infrared small target detection method based on morphology and visual attention mechanism | |
| Lv et al. | A segmentation method of red apple image | |
| Alegro et al. | Automating cell detection and classification in human brain fluorescent microscopy images using dictionary learning and sparse coding | |
| CN112257702A (en) | Crop disease identification method based on incremental learning | |
| CN105512612A (en) | SVM-based image classification method for capsule endoscope | |
| Sridhathan et al. | Plant infection detection using image processing | |
| CN111784764A (en) | Tea tender shoot identification and positioning algorithm | |
| CN113298777A (en) | Cotton leaf blight detection method and system based on color features and super-pixel clustering | |
| CN112215865A (en) | Automatic detection method for micro-droplets under fluorescence microscopic image | |
| CN115578660A (en) | Land block segmentation method based on remote sensing image | |
| CN110298835B (en) | Leather surface damage detection method, system and related device | |
| CN111105427A (en) | Lung image segmentation method and system based on connected region analysis | |
| CN114581658A (en) | Target detection method and device based on computer vision | |
| TWI498830B (en) | A method and system for license plate recognition under non-uniform illumination | |
| Zhang et al. | Cherry recognition in natural environment based on the vision of picking robot | |
| WO2024016632A1 (en) | Bright spot location method, bright spot location apparatus, electronic device and storage medium |
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 |