CN109801235A - A kind of epipremnum aureum blade disease causes detection method and device - Google Patents
A kind of epipremnum aureum blade disease causes detection method and device Download PDFInfo
- Publication number
- CN109801235A CN109801235A CN201811624647.6A CN201811624647A CN109801235A CN 109801235 A CN109801235 A CN 109801235A CN 201811624647 A CN201811624647 A CN 201811624647A CN 109801235 A CN109801235 A CN 109801235A
- Authority
- CN
- China
- Prior art keywords
- image
- scab
- region
- epipremnum aureum
- leaf
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Abstract
The invention discloses a kind of epipremnum aureum blade disease causes detection method and device, for the automatic identification for realizing epipremnum aureum blade disease, the present invention selects single illness blade to classify and count, the blade with leaf spot and anthracnose is classified and counted simultaneously, the characteristics extraction of leaf color is carried out by RGB and YCbCr color space, judge whether leaf image to be measured scab occurs in scab image-region, and calculate the scab image-region range of scab image-region, substantially reduce the time manually protected and cost, real-time can be carried out to blade, periodically automatic observation and early warning, easily facilitate the intelligent management to plant.
Description
Technical field
This disclosure relates to plant disease reason detection field, and in particular to a kind of epipremnum aureum blade disease causes detection method and
Device.
Background technique
The disease causes that plant leaf blade occurs are varied, and predominantly leaf spot and the carbon bacterium disease two that epipremnum aureum blade is common
Kind.Leaf spot mainly causes damages to the blade of epipremnum aureum, will appear the fleck of many brown in the initial stage blade of morbidity, tight
Spot can be throughout entire blade in the case where weight.If timely found, only needs to remove disease leaf at the initial stage of morbidity, be used in combination
95% 500 times of liquid of ambam or 80% 1000 times of liquid of carbendazol wettable powder etc. are sprayed and can be prevented and treated.From current reality
From the point of view of situation is planted on border, the blade Defect inspection and solution of plant have the following deficiencies: 1, due to the disease initial stage of plant
Symptom is often to be difficult judgement, along with comprehensive sex knowledge that grower's shortage diagnoses flowers and plants plant disease, therefore
Pesticide spraying and fertilising are just often carried out when disease development tends to be serious in the management of the disease of plant, disease cannot be made to obtain
To timely and effectively controlling;2, busy life rhythm further makes whether people both went management kind plant without the time or without energy
It is invaded by disease, various control measures can not be also provided;Although 3, round pcr solves current plant mycosis substantially
Former identification, Defect inspection, genetic diversity and it is disease-resistant based on analyzing the problems such as, but due to the individualized medicine difference of grower,
And the Disease symptoms of some plants are often complexity, obscure multiplicity, plant expert uses the description of symptom fuzzy
The language description of property, cannot be described disease causes with the symbol of accurate quantification, cause grower can not be to plant disease
It judges soundly;4, the difficulty of PCR molecular detection technology is there is polymorphism, labeled a certain segment due to DNA
Specificity transformation may occur so that genome is unevenly distributed, significantly limit the accuracy of pcr gene positioning, and
And there is the problems such as experimental implementation is cumbersome, and detection time is long, at high cost during the experiment, with computer technology, computer
The disease causes detection of the development of image processing and artificial intelligence technology, automation has become a kind of trend.
Summary of the invention
The disclosure provides a kind of epipremnum aureum blade disease causes detection method and device, to realize the automatic of epipremnum aureum blade disease
Identification, the present invention select single illness blade to classify and count, while classifying to the blade with leaf spot and anthracnose
And statistics, the characteristics extraction of leaf color is carried out by RGB and YCbCr color space, is judged in scab image-region to be measured
Whether leaf image there is scab, and calculates the scab image-region range of scab image-region.
To achieve the goals above, according to the one side of the disclosure, a kind of epipremnum aureum blade disease causes detection method is provided,
It the described method comprises the following steps:
Step 1, leaf image to be measured is pre-processed to obtain denoising image;
Step 2, denoising image is subjected to image segmentation and obtains foreground image;
Step 3, scab image-region is highlighted by color space conversion foreground image;
Step 4, judge whether leaf image to be measured scab occurs in scab image-region;
Step 5, the scab image-region range of scab image-region is calculated.
Further, in step 1, the leaf image to be measured is the epipremnum aureum blade picture of line-scan digital camera shooting.
Further, in step 1, the method for being pre-processed to obtain denoising image to leaf image to be measured is, for
Pixel at the pixel position (i, j) of leaf image to be measured, the gray value of (i, j) are f (i, j), and smoothed out gray value is g
(i, j) passes through formulaThe pixel gray value progress of leaf image to be measured is smoothly gone
Make an uproar image g (i, j), wherein set of the A for the neighborhood point centered on (i, j), sum of the M for pixel in A, and x, y=0,1,
2,…,M-1。
Further, in step 2, will denoise the method that image progress image segmentation obtains foreground image is,
If denoising image is g (i, j), θ (x, y) is two-dimentional smooth function ∫R∫Rθ (x, y) dxdy=1;
The direction x and the partial derivative in the direction y is asked to have respectively smooth function θ (x, y): x Directional partial derivativeY Directional partial derivativeFor arbitrary function g (i, j) ∈ R2, R2For 2 dimension spaces
Image, by two small echo φ1(x, y) and φ2(x, y) there are two components:
Gradient vector are as follows:Wherein: S is scale coefficient, and S is defaulted as 1;WithAlong x respectively in image, the partial derivative in the direction y, wavelet transformation is in scale 2jMould and argument point
Not are as follows:
The mould W of wavelet transformation2jG (x, y) is proportional to gradient vectorMould, the argument A of wavelet transformation2jg
(x, y) is gradient vectorWith the angle of horizontal direction, the as edge of image segmentation, gradient vector is foundMould local maximum point and carry out image segmentation and obtain foreground image;In each scale 2j, small echo change
The maximum value of the mould changed is defined as mould W2jFor g (x, y) in the local maximum point along gradient direction, (g* θ) (x, y) is g (i, j)
Orthogonal θ (x, y).
Further, in step 3, the method for scab image-region being highlighted by color space conversion foreground image
For,
Step 3.1, foreground image is transformed into YCbCr space, space change type from rgb space are as follows:Wherein, R, G, B are respectively the red, green, blue three of pixel
The color value in a channel, Y are brightness, i.e. grayscale value, and brightness is established through RGB input signal, and method is to believe RGB
Number specific part be superimposed together, difference of the Cb between RGB input signal blue portion and rgb signal brightness value, Cr is
Difference between RGB input signal RED sector and rgb signal brightness value;
Step 3.2, since Cr and Cb have the normal distribution characteristic relative to Y respectively, normal state point is used in YCbCr space
The method of cloth parameter evaluation highlights scab image-region in foreground image, normal distyribution function expression formula are as follows:
Wherein, μxWith
μyIt is the mean value of x and y in smooth function θ (x, y), σ respectivelyxAnd σyIt is the sample standard deviation of x and y respectively, finds out foreground image Cr
Mean value xμWith variance xσ, the mean value y of CbμWith variance yσ, obtain F distribution are as follows:
I.e. as the Cr of the pixel region in foreground image, when Cb meets the distribution in the section of mean value and standard deviation, i.e.,
The F (x, y) that Cr and Cb is constituted meets the region of F distribution, as scab image-region.
Further, in step 4, judge whether leaf image to be measured the method for scab occurs in scab image-region
For,
Due to the scab image-region presentation of the epipremnum aureum blade of suffering from the lesions such as leaf spot and anthracnose show white, black,
Grey, i.e., in rgb space, R, G, B three-component are approximately equal, according to the difference of lesion situation, the color of scab image-region
Brightness is different, according to the constraint of the Y channel components in YCbCr color space, the color property of scab image-region be it is following about
Beam condition, R ± α=G ± α=B ± α, L1≤Y≤L2, it is 10~50 integer, L that α, which takes range,1It is 70, L2For 150, α, L1,L2
It is the actual count data of epipremnum aureum blade lesion, meets constraint condition and then judge that scab occurs in epipremnum aureum blade.
Further, in steps of 5, the scab image-region range method for calculating scab image-region is, according to scab
The rgb value for the sample point that the color property of image-region is chosen in scab image-region, which is averaged, obtains average color, this average
Color is defined with RGB column vector m, and z is enabled to indicate any pixel vectors in rgb space, if the distance between z and m be less than it is specified
Threshold value T, threshold value T=100, then z is similar to m, and the Euclidean distance D (z, m) between z and m is,mR,mG,mBRespectively R, G and B component of vector m, zR,
zG,zBRespectively R, G and B component of vector z;The track of D (z, m)≤T point is the scab image-region range that radius is T.
The present invention also provides a kind of epipremnum aureum blade disease causes detection device, described device includes: memory, processor
And the computer program that can be run in the memory and on the processor is stored, the processor executes the meter
Calculation machine program operates in the unit of following device:
Image pre-processing unit obtains denoising image for being pre-processed to leaf image to be measured;
Foreground segmentation unit obtains foreground image for that will denoise image progress image segmentation;
Scab highlights unit, for highlighting scab image-region by color space conversion foreground image;
Scab judging unit, for judging whether leaf image to be measured scab occurs in scab image-region;
Scab range calculation unit, for calculating the scab image-region range of scab image-region.
The disclosure has the beneficial effect that the present invention provides a kind of epipremnum aureum blade disease causes detection method and device, significantly
The time manually protected and cost are reduced, real-time, periodically automatic observation and early warning can be carried out to blade, is easily facilitated
To the intelligent management of plant.
Detailed description of the invention
By the way that the embodiment in conjunction with shown by attached drawing is described in detail, above-mentioned and other features of the disclosure will
More obvious, identical reference label indicates the same or similar element in disclosure attached drawing, it should be apparent that, it is described below
Attached drawing be only some embodiments of the present disclosure, for those of ordinary skill in the art, do not making the creative labor
Under the premise of, it is also possible to obtain other drawings based on these drawings, in the accompanying drawings:
Fig. 1 show a kind of flow chart of epipremnum aureum blade disease causes detection method;
Fig. 2 is shown with leaf spot blade schematic diagram;
Fig. 3 is shown with anthracnose variegated leaf piece schematic diagram;
Fig. 4 show the blade schematic diagram with leaf spot and anthracnose;
Fig. 5 show a kind of epipremnum aureum blade disease causes detection device figure.
Specific embodiment
It is carried out below with reference to technical effect of the embodiment and attached drawing to the design of the disclosure, specific structure and generation clear
Chu, complete description, to be completely understood by the purpose, scheme and effect of the disclosure.It should be noted that the case where not conflicting
Under, the features in the embodiments and the embodiments of the present application can be combined with each other.
As shown in Figure 1 for according to a kind of flow chart of epipremnum aureum blade disease causes detection method of the disclosure, below with reference to
Fig. 1 illustrates a kind of epipremnum aureum blade disease causes detection method according to embodiment of the present disclosure.
The disclosure proposes a kind of epipremnum aureum blade disease causes detection method, specifically includes the following steps:
Step 1, leaf image to be measured is pre-processed to obtain denoising image;
Step 2, denoising image is subjected to image segmentation and obtains foreground image;
Step 3, scab image-region is highlighted by color space conversion foreground image;
Step 4, judge whether leaf image to be measured scab occurs in scab image-region;
Step 5, the scab image-region range of scab image-region is calculated.
Further, in step 1, the leaf image to be measured is the epipremnum aureum blade picture of line-scan digital camera shooting.
Further, in step 1, the method for being pre-processed to obtain denoising image to leaf image to be measured is, for
Pixel at the pixel position (i, j) of leaf image to be measured, the gray value of (i, j) are f (i, j), and smoothed out gray value is g
(i, j) passes through formulaThe pixel gray value progress of leaf image to be measured is smoothly gone
Make an uproar image g (i, j), wherein set of the A for the neighborhood point centered on (i, j), sum of the M for pixel in A, and x, y=0,1,
2,…,M-1。
Further, in step 2, will denoise the method that image progress image segmentation obtains foreground image is,
If denoising image is g (i, j), θ (x, y) is two-dimentional smooth function ∫R∫Rθ (x, y) dxdy=1;
The direction x and the partial derivative in the direction y is asked to have respectively smooth function θ (x, y): x Directional partial derivativeY Directional partial derivativeFor arbitrary function g (i, j) ∈ R2, R2For 2 dimension spaces
Image, by two small echo φ1(x, y) and φ2(x, y) there are two components:
Gradient vector are as follows:Wherein: S is scale coefficient, and S is defaulted as 1;WithAlong x respectively in image, the partial derivative in the direction y, wavelet transformation is in scale 2jMould and argument point
Not are as follows:
The mould W of wavelet transformation2jG (x, y) is proportional to gradient vectorMould, the argument of wavelet transformationIt is gradient vectorWith the angle of horizontal direction, the as edge of image segmentation, gradient vector is foundMould local maximum point and carry out image segmentation and obtain foreground image;In each scale 2j, small echo change
The maximum value of the mould changed is defined as mouldIn the local maximum point along gradient direction, x, y=0,1,2 ..., M-1.
Further, in step 3, the method for scab image-region being highlighted by color space conversion foreground image
For,
Step 3.1, foreground image is transformed into YCbCr space, space change type from rgb space are as follows:Wherein, R, G, B are respectively the red, green, blue three of pixel
The color value in a channel, Y are brightness, i.e. grayscale value, and brightness is established through RGB input signal, and method is to believe RGB
Number specific part be superimposed together, difference of the Cb between RGB input signal blue portion and rgb signal brightness value, Cr is
Difference between RGB input signal RED sector and rgb signal brightness value;
Step 3.2, since Cr and Cb have the normal distribution characteristic relative to Y respectively, normal state point is used in YCbCr space
The method of cloth parameter evaluation highlights scab image-region in foreground image, normal distyribution function expression formula are as follows:
Wherein, μxWith
μyIt is the mean value of x and y in smooth function θ (x, y), σ respectivelyxAnd σyIt is the sample standard deviation of x and y respectively, finds out foreground image Cr
Mean value xμWith variance xσ, the mean value y of CbμWith variance yσ, obtain F distribution are as follows:
I.e. as the Cr of the pixel region in foreground image, when Cb meets the distribution in the section of mean value and standard deviation, i.e.,
The F (x, y) that Cr and Cb is constituted meets the region of F distribution, as scab image-region.
Further, in step 4, judge whether leaf image to be measured the method for scab occurs in scab image-region
For,
See shown in Fig. 2, Fig. 3 and Fig. 4, the scab image-region of the epipremnum aureum blade due to suffering from the lesions such as leaf spot and anthracnose
Presentation shows white, black, grey, i.e., in rgb space, R, G, B three-component are approximately equal, according to the difference of lesion situation,
The colour brightness of scab image-region is different, according to the constraint of the Y channel components in YCbCr color space, scab image-region
Color property be following constraint condition, R ± α=G ± α=B ± α, L1≤Y≤L2, it is 10~50 integer, L that α, which takes range,1For
70, L2For 150, α, L1,L2It is the actual count data of epipremnum aureum blade lesion, meets constraint condition and then judge that epipremnum aureum blade goes out
Existing scab.
Further, in steps of 5, the scab image-region range method for calculating scab image-region is, according to scab
The rgb value for the sample point that the color property of image-region is chosen in scab image-region, which is averaged, obtains average color, this average
Color is defined with RGB column vector m, and z is enabled to indicate any pixel vectors in rgb space, if the distance between z and m be less than it is specified
Threshold value T, threshold value T=100, then z is similar to m, and the Euclidean distance D (z, m) between z and m is D (z, m)=[(zR-mR)2+
(zG-mG)2+(zB-mB)2]1/2, mR,mG,mBRespectively R, G and B component of vector m, zR,zG,zBRespectively R, G and B of vector z
Component;The track of D (z, m)≤T point is the scab image-region range that radius is T.
A kind of embodiment 1 of the disclosure chooses the leaf of epipremnum aureum suffered from leaf spot and anthracnose respectively as shown in Figures 2 and 3
Piece is tested, and since blade is different to the absorption of light with the different piece of background, the leaf image uneven illumination of acquisition is even,
Certain parts of performance are dark, and certain parts are bright, this will affect the correct segmentation of target object, so before removing background,
The even elimination of uneven illumination first is carried out to leaf image.This experiment uses the even technology for eliminating of uneven illumination of wavelet transformation, by stretching
Contracting shift operations carry out multi-scale refinement to signal, are finally reached at high frequency treatment subdivision and low frequency and segment, reach background and target
The segmentation of blade.Then noise processed is carried out to gained blade, the timing filter for choosing 10 × 10 carries out median filtering;By mould
Block slides in the picture, and module centers are overlapped with pixel a certain in image;The gray scale of corresponding pixel under read module
Value, and according to being ranked up from small to large, it finally assigns median to the center pixel for template, can thus make surrounding
Pixel grey scale difference tend to 0, to eliminate isolated noise point.In order to preferably obtain scab cutting object, we are using adaptive
Fuzzy threshold segmentation method is answered to divide leaf spot lesion, by the morphological feature of gained blade, color characteristic and texture feature information are carried out
It extracts, different characteristics is had to calculate the area in scab region according to different period scabs, these information summaries are obtained
The classifier of degree of disease.This experimental result provides reliable foundation to detect that epipremnum aureum blade is suffered from for anthracnose blade, changes
The ventilated environment of kind plant keeps the wet of basin soil, to increase the resistance of plant.If symptom is in hair initial stage, can
To add 80% 500 times of liquid sprinklings of anthrax good fortune U.S. wettable powder in water, pass through primary sprinkling in timing every 10 days, continuous 2-
3 times.
A kind of embodiment 2 of the disclosure, chooses as shown in Figure 4 while the blade with leaf spot and anthracnose carries out in fact
It tests, which is broadly divided into five big steps and carries out, and first step categorizing system first pre-processes the blade of camera acquisition, eliminates
Due to the picture noise that environmental factor generates, when the pixel value of pixel is maximum or minimum in Neighborhood Filtering window
When, then pixel each in Neighborhood Filtering window is subjected to arrangement from big to small, chooses the pixel value in middle position as neighborhood
The pixel value of filter window handles leaf image;The epipremnum aureum leaf image handled well is carried out image by second step
Segmentation, highlights scab image-region by color space conversion, and then weed out pixel access overlap-add region and background area,
The region comprising scab blade is left, then enhances scab region using the Y channel components in YCbCr color space;Third step
The scab image-region progress pixel characteristic value extraction obtained using image segmentation, including form, color, texture and gradient are straight
Square figure feature respectively obtains classification data to different scab features;After 4th step extracts different types of scab characteristic,
Data different types of in same feature are demarcated with function curve, determining in the division curvilinear function of comprehensive different characteristic should
The total characteristic in scab region;The mode that final step needs to define scab region illness provides sorted different scab characteristics
It according to symptom described in model and is inputted, the provincial characteristics data that can directly extract scab next time and model data is facilitated to compare
Determine illness.To prevent epipremnum aureum blade to suffer from leaf spot, light filling operation can be carried out to epipremnum aureum according to timing, if leaf spot is more tight
When weight, suitable streptomysin can be added in watering, the symptom of leaf spot can be effectively improved, which is the inspection of epipremnum aureum disease
Important evidence is provided with solution.
A kind of epipremnum aureum blade disease causes detection device that embodiment of the disclosure provides, is illustrated in figure 5 the disclosure
A kind of epipremnum aureum blade disease causes detection device figure, a kind of epipremnum aureum blade disease causes detection device of the embodiment include: place
The computer program managing device, memory and storage in the memory and can running on the processor, the processing
Device realizes the step in a kind of above-mentioned epipremnum aureum blade disease causes detection device embodiment when executing the computer program.
Described device includes: memory, processor and storage in the memory and can transport on the processor
Capable computer program, the processor execute the computer program and operate in the unit of following device:
Image pre-processing unit obtains denoising image for being pre-processed to leaf image to be measured;
Foreground segmentation unit obtains foreground image for that will denoise image progress image segmentation;
Scab highlights unit, for highlighting scab image-region by color space conversion foreground image;
Scab judging unit, for judging whether leaf image to be measured scab occurs in scab image-region;
Scab range calculation unit, for calculating the scab image-region range of scab image-region.
A kind of epipremnum aureum blade disease causes detection device can run on desktop PC, notebook, palm electricity
Brain and cloud server etc. calculate in equipment.A kind of epipremnum aureum blade disease causes detection device, the device that can be run can wrap
It includes, but is not limited only to, processor, memory.It will be understood by those skilled in the art that the example is only a kind of epipremnum aureum blade
The example of disease causes detection device does not constitute the restriction to a kind of epipremnum aureum blade disease causes detection device, may include
Components more more or fewer than example perhaps combine certain components or different components, such as a kind of epipremnum aureum blade disease
Evil reason detection device can also include input-output equipment, network access equipment, bus etc..
Alleged processor can be central processing unit (Central Processing Unit, CPU), can also be it
His general processor, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng the processor is a kind of control centre of epipremnum aureum blade disease causes detection device running gear, is connect using various
Mouthful and connection entirely a kind of epipremnum aureum blade disease causes detection device can running gear various pieces.
The memory can be used for storing the computer program and/or module, and the processor is by operation or executes
Computer program in the memory and/or module are stored, and calls the data being stored in memory, described in realization
A kind of various functions of epipremnum aureum blade disease causes detection device.The memory can mainly include storing program area and storage number
According to area, wherein storing program area can application program needed for storage program area, at least one function (for example sound plays function
Energy, image player function etc.) etc.;Storage data area can store according to mobile phone use created data (such as audio data,
Phone directory etc.) etc..In addition, memory may include high-speed random access memory, it can also include nonvolatile memory, example
Such as hard disk, memory, plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure
Digital, SD) card, flash card (Flash Card), at least one disk memory, flush memory device or other volatibility are solid
State memory device.
Although the description of the disclosure is quite detailed and especially several embodiments are described, it is not
Any of these details or embodiment or any specific embodiments are intended to be limited to, but should be considered as is by reference to appended
A possibility that claim provides broad sense in view of the prior art for these claims explanation, to effectively cover the disclosure
Preset range.In addition, the disclosure is described with inventor's foreseeable embodiment above, its purpose is to be provided with
Description, and those equivalent modifications that the disclosure can be still represented to the unsubstantiality change of the disclosure still unforeseen at present.
Claims (7)
1. a kind of epipremnum aureum blade disease causes detection method, which is characterized in that the described method comprises the following steps:
Step 1, leaf image to be measured is pre-processed to obtain denoising image;
Step 2, denoising image is subjected to image segmentation and obtains foreground image;
Step 3, scab image-region is highlighted by color space conversion foreground image;
Step 4, judge whether leaf image to be measured scab occurs in scab image-region;
Step 5, the scab image-region range of scab image-region is calculated.
2. a kind of epipremnum aureum blade disease causes detection method according to claim 1, which is characterized in that in step 1, right
The method that leaf image to be measured is pre-processed to obtain denoising image is, for the pixel position (i, j) of leaf image to be measured
The pixel at place, the gray value of (i, j) are f (i, j), and smoothed out gray value is g (i, j), pass through formulaThe pixel gray value of leaf image to be measured is carried out smoothly obtaining denoising image g (i, j),
In, A is the set of the neighborhood point centered on (i, j), and M is the sum of pixel in A, x, y=0,1,2 ..., M-1.
3. a kind of epipremnum aureum blade disease causes detection method according to claim 1, which is characterized in that in step 2, will
Denoising image carries out the method that image segmentation obtains foreground image,
If denoising image is g (i, j), θ (x, y) is two-dimentional smooth function ∫R∫Rθ (x, y) dxdy=1;
The direction x and the partial derivative in the direction y is asked to have respectively smooth function θ (x, y): x Directional partial derivativey
Directional partial derivativeFor arbitrary function g (i, j) ∈ R2, R2For the image of 2 dimension spaces, by two small echos
φ1(x, y) and φ2(x, y) there are two components:
Gradient vector are as follows:Wherein: S is scale coefficient, and S is defaulted as 1;WithAlong x respectively in image, the partial derivative in the direction y, wavelet transformation is in scale 2jMould and argument be respectively as follows:
The mould of wavelet transformationIt is proportional to gradient vectorMould, the argument of wavelet transformation
It is gradient vectorWith the angle of horizontal direction, the as edge of image segmentation, gradient vector is foundMould local maximum point and carry out image segmentation and obtain foreground image;In each scale 2j, small echo change
The maximum value of the mould changed is defined as mouldIn the local maximum point along gradient direction.
4. a kind of epipremnum aureum blade disease causes detection method according to claim 1, which is characterized in that in step 3, lead to
Crossing the method that color space conversion foreground image highlights scab image-region is,
Step 3.1, foreground image is transformed into YCbCr space, space change type from rgb space are as follows:Wherein, R, G, B are respectively the red, green, blue three of pixel
The color value in a channel, Y are brightness, i.e. grayscale value, and brightness is established through RGB input signal, and method is to believe RGB
Number specific part be superimposed together, difference of the Cb between RGB input signal blue portion and rgb signal brightness value, Cr is
Difference between RGB input signal RED sector and rgb signal brightness value;
Step 3.2, since Cr and Cb have the normal distribution characteristic relative to Y respectively, joined in YCbCr space using normal distribution
The method of assessment is counted to highlight scab image-region in foreground image, normal distyribution function expression formula are as follows:
Wherein, μxAnd μyPoint
It is not the mean value of x and y in smooth function θ (x, y), σxAnd σyIt is the sample standard deviation of x and y respectively, finds out the equal of foreground image Cr
Value xμWith variance xσ, the mean value y of CbμWith variance yσ, obtain F distribution are as follows:
I.e. as the Cr of the pixel region in foreground image, when Cb meets the distribution in the section of mean value and standard deviation, i.e. Cr and
The F (x, y) that Cb is constituted meets the region of F distribution, as scab image-region.
5. a kind of epipremnum aureum blade disease causes detection method according to claim 1, which is characterized in that in step 4,
The method that scab image-region judges whether leaf image to be measured scab occurs is that the color property of scab image-region is following
Constraint condition, R ± α=G ± α=B ± α, L1≤Y≤L2, it is 10~50 integer, L that α, which takes range,1It is 70, L2It is 150, meets
Constraint condition then judges that scab occurs in epipremnum aureum blade.
6. a kind of epipremnum aureum blade disease causes detection method according to claim 1, which is characterized in that in steps of 5, meter
The scab image-region range method for calculating scab image-region is, according to the color property of scab image-region in scab image district
The rgb value for the sample point that domain is chosen averages and obtains average color, and this average color is defined with RGB column vector m, enables the z indicate RGB
Any pixel vectors in space, if the distance between z and m are less than specified threshold value T, threshold value T=100, then z is similar to m, z
Euclidean distance D (z, m) between m is D (z, m)=[(zR-mR)2+(zG-mG)2+(zB-mB)2]1/2, mR,mG,mBRespectively to
Measure R, G and B component of m, zR,zG,zBRespectively R, G and B component of vector z;The track of D (z, m)≤T point is that radius is T
Scab image-region range.
7. a kind of epipremnum aureum blade disease causes detection device, which is characterized in that described device include: memory, processor and
The computer program that can be run in the memory and on the processor is stored, the processor executes the computer
Program operates in the unit of following device:
Image pre-processing unit obtains denoising image for being pre-processed to leaf image to be measured;
Foreground segmentation unit obtains foreground image for that will denoise image progress image segmentation;
Scab highlights unit, for highlighting scab image-region by color space conversion foreground image;
Scab judging unit, for judging whether leaf image to be measured scab occurs in scab image-region;
Scab range calculation unit, for calculating the scab image-region range of scab image-region.
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 true CN109801235A (en) | 2019-05-24 |
CN109801235B 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) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112413449A (en) * | 2020-11-13 | 2021-02-26 | 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 (10)
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 |
CN102063708A (en) * | 2011-01-06 | 2011-05-18 | 西安电子科技大学 | Image denoising method based on Treelet and non-local means |
US20140036054A1 (en) * | 2012-03-28 | 2014-02-06 | George Zouridakis | Methods and Software for Screening and Diagnosing Skin Lesions and Plant Diseases |
CN103808265A (en) * | 2014-02-28 | 2014-05-21 | 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 |
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 |
CN104463173A (en) * | 2014-12-12 | 2015-03-25 | 西京学院 | Crop disease recognition method based on probability density ratio |
CN105654445A (en) * | 2016-01-28 | 2016-06-08 | 东南大学 | Mobile phone image denoising method based on wavelet transform edge detection |
CN106682571A (en) * | 2016-11-08 | 2017-05-17 | 中国民航大学 | Skin color segmentation and wavelet transformation-based face detection method |
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 (10)
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 |
CN102063708A (en) * | 2011-01-06 | 2011-05-18 | 西安电子科技大学 | Image denoising method based on Treelet and non-local means |
US20140036054A1 (en) * | 2012-03-28 | 2014-02-06 | George Zouridakis | 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 |
CN103808265A (en) * | 2014-02-28 | 2014-05-21 | 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 |
CN104463173A (en) * | 2014-12-12 | 2015-03-25 | 西京学院 | Crop disease recognition method based on probability density ratio |
CN105654445A (en) * | 2016-01-28 | 2016-06-08 | 东南大学 | Mobile phone image denoising method based on wavelet transform edge detection |
CN106682571A (en) * | 2016-11-08 | 2017-05-17 | 中国民航大学 | Skin color segmentation and wavelet transformation-based face detection method |
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 |
Non-Patent Citations (2)
Title |
---|
ZHU WENBO,ET AL: "LPPCO: A Novel Multimodal Medical Image Registration Using New Feature Descriptor Based on the Local Phase and Phase Congruency of Different Orientations", 《SPECIAL SECTION ON NEW TRENDS IN BRAIN SIGNAL PROCESSING AND ANALYSIS》 * |
陈占良等: "基于图像处理的叶斑病分级方法的研究", 《农机化研究》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112413449A (en) * | 2020-11-13 | 2021-02-26 | 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 |
Also Published As
Publication number | Publication date |
---|---|
CN109801235B (en) | 2023-03-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Barbedo | A novel algorithm for semi-automatic segmentation of plant leaf disease symptoms using digital image processing | |
Mizushima et al. | An image segmentation method for apple sorting and grading using support vector machine and Otsu’s method | |
US8331642B2 (en) | Method and device for determining a contour and a center of an object | |
Celebi et al. | Lesion border detection in dermoscopy images | |
Sadeghi-Tehran et al. | Multi-feature machine learning model for automatic segmentation of green fractional vegetation cover for high-throughput field phenotyping | |
Sarrafzadeh et al. | Nucleus and cytoplasm segmentation in microscopic images using K-means clustering and region growing | |
CN109154978A (en) | System and method for detecting plant disease | |
CN109801235A (en) | A kind of epipremnum aureum blade disease causes detection method and device | |
Yang et al. | LS-SVM based image segmentation using color and texture information | |
CN110309781B (en) | House damage remote sensing identification method based on multi-scale spectrum texture self-adaptive fusion | |
Guo et al. | An improved Hough transform voting scheme utilizing surround suppression | |
Arbelaez et al. | Constrained image segmentation from hierarchical boundaries | |
Sun et al. | Recognition of green apples based on fuzzy set theory and manifold ranking algorithm | |
Gharge et al. | Image processing for soybean disease classification and severity estimation | |
JP2013111420A (en) | Image processing device, image processing method, and image processing program | |
CN109871900A (en) | The recognition positioning method of apple under a kind of complex background based on image procossing | |
CN109766818A (en) | Pupil center's localization method and system, computer equipment and readable storage medium storing program for executing | |
Apou et al. | Detection of lobular structures in normal breast tissue | |
Dong et al. | Detecting soft shadows in a single outdoor image: From local edge-based models to global constraints | |
CN111784764A (en) | Tea tender shoot identification and positioning algorithm | |
CN110705634B (en) | Heel model identification method and device and storage medium | |
Fan et al. | Estimating the aquatic-plant area on a pond surface using a hue-saturation-component combination and an improved Otsu method | |
Hu et al. | Computer vision based method for severity estimation of tea leaf blight in natural scene images | |
Sangworasil et al. | Automated screening of cervical cancer cell images | |
Sun et al. | Combining an information-maximization-based attention mechanism and illumination invariance theory for the recognition of green apples in natural scenes |
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 |