CN109859167A - The appraisal procedure and device of cucumber downy mildew severity - Google Patents
The appraisal procedure and device of cucumber downy mildew severity Download PDFInfo
- Publication number
- CN109859167A CN109859167A CN201811623559.4A CN201811623559A CN109859167A CN 109859167 A CN109859167 A CN 109859167A CN 201811623559 A CN201811623559 A CN 201811623559A CN 109859167 A CN109859167 A CN 109859167A
- Authority
- CN
- China
- Prior art keywords
- layer
- downy mildew
- cucumber
- severity
- mildew severity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Image Analysis (AREA)
Abstract
The embodiment of the present invention provides the appraisal procedure and device of a kind of cucumber downy mildew severity, belongs to technical field of crop cultivation.This method comprises: obtaining collected cucumber leaves image to be assessed under natural environment；Using stochastic gradient descent method, and the neuralnetwork estimating model based on downy mildew severity, the cucumber downy mildew severity of cucumber leaves image is assessed.Method provided in an embodiment of the present invention, by using stochastic gradient descent method, and the neuralnetwork estimating model based on downy mildew severity, the cucumber downy mildew severity of cucumber leaves image is assessed.Due to that can estimate degree of disease automatically, to high degree of automation and recognition efficiency is high, manual intervention bring subjective impact can be effectively reduced, reduce the application cost and complexity of diagnosis process, the accuracy and real-time of disease screening can be effectively improved, also the correlative study for cucumber disease diagnosis provides reliable and accurate data basis.
Description
Technical field
The present embodiments relate to technical field of crop cultivation more particularly to a kind of assessments of cucumber downy mildew severity
Method and device.
Background technique
Greenhouse cucumber causes disease due to various reasons in planting process, in turn results in yield reduction and quality decline.
Downy mildew is one of disease relatively conventional in greenhouse cucumber disease.The Accurate Diagnosis of disease is divided into two aspects, and one is disease
Evil type identification, one be degree of disease estimation.The accurate acquisition of disease severity is grower's scientific prevention and cure disease
Precondition, for reduce Pesticide use amount, promoted economic benefit be of great significance.Traditional degree of disease evaluation method
Grower's experience is mainly leaned on, is not only taken time and effort, but also subjectivity is higher.In the related art, computer is usually utilized
Vision carries out Cucumber Disease Recognition in Greenhouse.Specifically, using cucumber leaves RGB image, color, texture and the shape of scab are obtained
Feature establishes diagnostic model by machine learning method, to realize the diagnosis of disease.These methods are merely able to the kind to disease
Class is identified, but cannot assess the severity of disease.Therefore, now it is badly in need of a kind of effective cucumber downy mildew severity
Appraisal procedure.
Summary of the invention
To solve the above-mentioned problems, the embodiment of the present invention provides one kind and overcomes the above problem or at least be partially solved
State the appraisal procedure and device of the cucumber downy mildew severity of the chamber crop context aware of problem.
According to a first aspect of the embodiments of the present invention, a kind of appraisal procedure of cucumber downy mildew severity is provided, comprising:
Obtain collected cucumber leaves image to be assessed under natural environment；
Using stochastic gradient descent method, and the neuralnetwork estimating model based on downy mildew severity, to cucumber leaves figure
The cucumber downy mildew severity of picture is assessed.
Method provided in an embodiment of the present invention, by obtaining collected cucumber leaves figure to be assessed under natural environment
Picture, using stochastic gradient descent method, and the neuralnetwork estimating model based on downy mildew severity, to the Huang of cucumber leaves image
Melon downy mildew severity is assessed.Due to that can estimate degree of disease automatically, thus high degree of automation and recognition efficiency height, energy
Manual intervention bring subjective impact is enough effectively reduced, the application cost and complexity of diagnosis process is reduced, can effectively improve
The accuracy and real-time of disease screening, also the correlative study for cucumber disease diagnosis provides reliable and accurate data base
Plinth.
According to a second aspect of the embodiments of the present invention, a kind of assessment device of cucumber downy mildew severity is provided, comprising:
Module is obtained, for obtaining collected cucumber leaves image to be assessed under natural environment；
Evaluation module, for using stochastic gradient descent method, and the neuralnetwork estimating model based on downy mildew severity,
The cucumber downy mildew severity of cucumber leaves image is assessed.
According to a third aspect of the embodiments of the present invention, a kind of electronic equipment is provided, comprising:
At least one processor；And
At least one processor being connect with processor communication, in which:
Memory is stored with the program instruction that can be executed by processor, and the instruction of processor caller is able to carry out first party
The assessment side of cucumber downy mildew severity provided by any possible implementation in the various possible implementations in face
Method.
According to the fourth aspect of the invention, a kind of non-transient computer readable storage medium, non-transient computer are provided
Readable storage medium storing program for executing stores computer instruction, and computer instruction makes the various possible implementations of computer execution first aspect
In cucumber downy mildew severity provided by any possible implementation appraisal procedure.
It should be understood that above general description and following detailed description be it is exemplary and explanatory, can not
Limit the embodiment of the present invention.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of flow diagram of the appraisal procedure of cucumber downy mildew severity provided in an embodiment of the present invention；
Fig. 2 is a kind of structural representation of the neuralnetwork estimating model of downy mildew severity provided in an embodiment of the present invention
Figure；
Fig. 3 is a kind of structural schematic diagram of the assessment device of cucumber downy mildew severity provided in an embodiment of the present invention；
Fig. 4 is the block diagram of a kind of electronic equipment provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Greenhouse cucumber causes disease due to various reasons in planting process, in turn results in yield reduction and quality decline.
Downy mildew is one of disease relatively conventional in greenhouse cucumber disease.The Accurate Diagnosis of disease is divided into two aspects, and one is disease
Evil type identification, one be degree of disease estimation.The accurate acquisition of disease severity is grower's scientific prevention and cure disease
Precondition, for reduce Pesticide use amount, promoted economic benefit be of great significance.Traditional degree of disease evaluation method
Grower's experience is mainly leaned on, is not only taken time and effort, but also subjectivity is higher.In the related art, computer is usually utilized
Vision carries out Cucumber Disease Recognition in Greenhouse.Specifically, using cucumber leaves RGB image, color, texture and the shape of scab are obtained
Feature establishes diagnostic model by machine learning method, to realize the diagnosis of disease.These methods are merely able to the kind to disease
Class is identified, but cannot assess the severity of disease.Therefore, now it is badly in need of a kind of effective cucumber downy mildew severity
Appraisal procedure.
There is a small amount of research to construct appraising model using shallow-layer machine learning method for degree of disease, although there is certain effect
Fruit, but need to carry out early period scab segmentation and artificial setting characteristics of image, due under natural environment by complex background and
The accuracy rate of the influence of illumination, segmentation is difficult to ensure, these methods is caused to be difficult to expand use in a natural environment.Convolutional Neural
Network is the unsupervised learning method with self-learning capability, it is considered to be image recognition one of the most effective ways at present.Volume
Product neural network is achieved in agriculture field and is widely applied, its clear superiority in image recognition is that we provide one
Kind thinking.Therefore, the greenhouse cucumber downy mildew severity quantitative estimation method based on convolutional neural networks is studied, can be cucumber
Disease Precise Diagnosis provides support.
Based on above description, presently, there are aiming at the problem that, the embodiment of the invention provides a kind of cucumber downy mildew is serious
The appraisal procedure of degree.Referring to Fig. 1, this method comprises:
101, collected cucumber leaves image to be assessed under natural environment is obtained.
102, using stochastic gradient descent method, and the neuralnetwork estimating model based on downy mildew severity, to cucumber leaf
The cucumber downy mildew severity of picture is assessed.
Method provided in an embodiment of the present invention, by obtaining collected cucumber leaves figure to be assessed under natural environment
Picture, using stochastic gradient descent method, and the neuralnetwork estimating model based on downy mildew severity, to the Huang of cucumber leaves image
Melon downy mildew severity is assessed.Due to that can estimate degree of disease automatically, thus high degree of automation and recognition efficiency height, energy
Manual intervention bring subjective impact is enough effectively reduced, the application cost and complexity of diagnosis process is reduced, can effectively improve
The accuracy and real-time of disease screening, also the correlative study for cucumber disease diagnosis provides reliable and accurate data base
Plinth.
Content based on the above embodiment, as a kind of alternative embodiment, in the neural network based on downy mildew severity
Appraising model, before assessing the cucumber downy mildew severity of cucumber leaves image, further includes: to being acquired under natural environment
To the sample image of cucumber downy mildew blade pre-processed, and construct to obtain original number based on pretreated sample image
According to collection；The degree of disease value of the sample image and sample image concentrated based on initial data carries out original neural network model
Training, obtains the neuralnetwork estimating model of downy mildew severity.Wherein, original neural network model can be convolutional Neural net
Network model, the present invention is not especially limit this.
Content based on the above embodiment, as a kind of alternative embodiment, about to cucumber collected under natural environment
The sample image of downy mildew blade carries out pretreated mode, and the present invention is not especially limit this, including but unlimited
In: sample image of the resolution ratio lower than preset threshold is rejected from collected sample image；Reject the back of each sample image
Scape pattern, and each sample image is adjusted to pre-set dimension size.
Specifically, in the case where getting greenhouse after collected sample image, the lower image of quality can be first weeded out,
Such as resolution ratio or the lower image of clarity.Furthermore it is also possible to sample image be normalized, also i.e. by sample graph
As being adjusted to identical color space, identical size, such as 128 × 128 pixels, the embodiment of the present invention are not made this specifically
It limits.It should be noted that the size of sample label image is bigger, then it is higher to calculate cost.In addition to this it is possible to reject surplus
Under sample image background patterns, to reduce information unrelated in image.
Content based on the above embodiment is being based on raw data set, to original nerve net as a kind of alternative embodiment
Network model is trained, before obtaining the neuralnetwork estimating model of downy mildew severity, further includes: according to default processing side
Formula, the sample image concentrated to initial data is handled, and to expand raw data set, default processing mode is at least wrapped
Any one in following three kinds of modes is included, three kinds of modes are respectively color jitter, flip horizontal and flip vertical below.
Specifically, color jitter, overturning both horizontally and vertically can be carried out to sample image, with 90 °, 180 °, 270 °
It carries out the mode such as rotating and carries out data enhancing, to expand sample.It should be noted that exptended sample image master here
If in order to improve the estimation effect of subsequent network model.In network model training process, front is got and this step
Expanding obtained sample image in rapid can be used as the training set of training, and training set can be divided into two parts according to function,
Respectively training set and test set.And it should be divided according to suitable ratio when being divided to data set, it is ensured that every class
The data volume relative equilibrium of data set.
Content based on the above embodiment, as a kind of alternative embodiment, the neuralnetwork estimating mould of downy mildew severity
Type includes input layer, 5 convolutional layers, 4 pond layers, 4 batches of standardization layers, 2 full articulamentums and output layer.Certainly, may be used also
To include Dropout layers, Dropout layers can be placed on before 2 full articulamentums, and the embodiment of the present invention does not limit this specifically
It is fixed.
Content based on the above embodiment, as a kind of alternative embodiment, input layer and first convolutional layer and first
Standardization layer connection is criticized, first convolutional layer and first batch of standardization layer are connect with first pond layer, first pond layer
It is connect with second convolutional layer and second batch of standardization layer, second convolutional layer and second batch of standardize layer and second pond
Change layer connection, second pond layer is connect with third convolutional layer and third batch standardization layer, third convolutional layer and third
A batch of standardization layer is connect with third pond layer, and third pond layer connects with the 4th convolutional layer and the 4th batch of standardization layer
It connects, the 4th convolutional layer and the 4th batch of standardization layer are connect with the 4th pond layer, the 4th pond layer and the 5th convolution
Layer connection, the 5th convolutional layer are successively connect with 2 full articulamentums and output layer.Wherein, the connection relationship between each layer can join
Examine Fig. 2.
Specifically, the input size of the model is 128 × 128 pixels, and convolution kernel size is 5 × 5 in convolutional layer, convolution
Convolution kernel number can be respectively 32,64,128,256 and 512 in layer, every to pass through a convolution operation, and network can be mentioned effectively
The feature in image is taken, the characteristic pattern of corresponding number is generated.Pond layer carries out average pond using 2 × 2 convolution kernel, realizes special
Levy the down-sampled of figure.The weight parameter in network structure can be substantially reduced by 4 pond layers, reduces and calculates cost.Finally
It is 2 full articulamentums after one convolutional layer, all characteristic pattern vector quantizations are indicated whole image with one-dimensional vector by full articulamentum
Feature.Dropout layers are increased before full articulamentum, by neural network unit according to certain probability temporarily from network
It abandons, to prevent over-fitting, improves model recognition accuracy.It is finally that a regressionLayer returns layer.
Wherein, the size of convolution operation output characteristic pattern, which can be used for following formula, indicates:
Wi+1=(Wi-F+2P)/S+1
In above-mentioned formula, WiIndicate the picture size of input, F indicates the size of convolution kernel, and P and S respectively represent filling
Pixel and step-length.For a convolution operation, input/output relation can be used following formula to indicate:
In above-mentioned formula, l indicates that layer index, i indicate that input feature vector index of the picture, k indicate output feature index of the picture,
It indicates using ith feature figure on l-1 layer as input.Indicate the output of l layers of upper k-th of characteristic pattern.In addition, W is indicated
Convolution weight tensor, b indicate that offset parameter, f () indicate activation primitive.
The result received is carried out size reduction processing by pond layer, specifically refers to following formula:
Wherein, down () is down-sampled function, and F is desampling fir filter size, and S is down-sampled step-length.
Content based on the above embodiment, the embodiment of the invention also provides a kind of assessment of cucumber downy mildew severity dresses
It sets, which is used to execute the appraisal procedure of the cucumber downy mildew severity provided in above method embodiment.It, should referring to Fig. 3
Device includes: to obtain module 301 and evaluation module 302；Wherein,
Module 301 is obtained, for obtaining collected cucumber leaves image to be assessed under natural environment；
Evaluation module 302, for using stochastic gradient descent method, and the neuralnetwork estimating mould based on downy mildew severity
Type assesses the cucumber downy mildew severity of cucumber leaves image.
Content based on the above embodiment, as a kind of alternative embodiment, the device further include:
Preprocessing module is located in advance for the sample image to cucumber downy mildew blade collected under natural environment
Reason, and construct to obtain raw data set based on pretreated sample image；
Training module, the degree of disease value of sample image and sample image for being concentrated based on initial data, to original
Neural network model is trained, and obtains the neuralnetwork estimating model of downy mildew severity.
Content based on the above embodiment, as a kind of alternative embodiment, preprocessing module is used for from collected sample
The sample image that resolution ratio is lower than preset threshold is rejected in image；The background patterns of each sample image are rejected, and will be per the same
This Image Adjusting is at pre-set dimension size.
Content based on the above embodiment, as a kind of alternative embodiment, the device further include:
Enlargement module, for according to default processing mode, the sample image concentrated to initial data to be handled, to original
Beginning data set is expanded, and presets processing mode including at least any one in following three kinds of modes, three kinds of modes are divided below
It Wei not color jitter, flip horizontal and flip vertical.
Content based on the above embodiment, as a kind of alternative embodiment, the neuralnetwork estimating mould of downy mildew severity
Type includes input layer, 5 convolutional layers, 4 pond layers, 4 batches of standardization layers, 2 full articulamentums and output layer.
Content based on the above embodiment, as a kind of alternative embodiment, input layer and first convolutional layer and first
Standardization layer connection is criticized, first convolutional layer and first batch of standardization layer are connect with first pond layer, first pond layer
It is connect with second convolutional layer and second batch of standardization layer, second convolutional layer and second batch of standardize layer and second pond
Change layer connection, second pond layer is connect with third convolutional layer and third batch standardization layer, third convolutional layer and third
A batch of standardization layer is connect with third pond layer, and third pond layer connects with the 4th convolutional layer and the 4th batch of standardization layer
It connects, the 4th convolutional layer and the 4th batch of standardization layer are connect with the 4th pond layer, the 4th pond layer and the 5th convolution
Layer connection, the 5th convolutional layer are successively connect with 2 full articulamentums and output layer.
Device provided in an embodiment of the present invention, by obtaining collected cucumber leaves figure to be assessed under natural environment
Picture, using stochastic gradient descent method, and the neuralnetwork estimating model based on downy mildew severity, to the Huang of cucumber leaves image
Melon downy mildew severity is assessed.Due to that can estimate degree of disease automatically, thus high degree of automation and recognition efficiency height, energy
Manual intervention bring subjective impact is enough effectively reduced, the application cost and complexity of diagnosis process is reduced, can effectively improve
The accuracy and real-time of disease screening, also the correlative study for cucumber disease diagnosis provides reliable and accurate data base
Plinth.
Fig. 4 illustrates the entity structure schematic diagram of a kind of electronic equipment, as shown in figure 4, the electronic equipment may include: place
Manage device (processor) 410, communication interface (Communications Interface) 420,430 He of memory (memory)
Communication bus 440, wherein processor 410, communication interface 420, memory 430 complete mutual lead to by communication bus 440
Letter.Processor 410 can call the logical order in memory 430, to execute following method: obtaining and collect under natural environment
Cucumber leaves image to be assessed；Using stochastic gradient descent method, and the neuralnetwork estimating mould based on downy mildew severity
Type assesses the cucumber downy mildew severity of cucumber leaves image.It should be noted that electronic equipment in actual implementation
Form can perhaps the PC such as tablet computer or the tablet computer can acquire data and can have the function of Decision Control for PC
Deng the present invention is not especially limit this.
In addition, the logical order in above-mentioned memory 430 can be realized by way of SFU software functional unit and conduct
Independent product when selling or using, can store in a computer readable storage medium.Based on this understanding, originally
Substantially the part of the part that contributes to existing technology or the technical solution can be in other words for the technical solution of invention
The form of software product embodies, which is stored in a storage medium, including some instructions to
So that a computer equipment (can be personal computer, electronic equipment or the network equipment etc.) executes each reality of the present invention
Apply all or part of the steps of a method.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (ROM,
Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic or disk etc. it is various
It can store the medium of program code.
The embodiment of the present invention also provides a kind of non-transient computer readable storage medium, is stored thereon with computer program,
The computer program is implemented to carry out the various embodiments described above offer method when being executed by processor, for example, obtain nature
Collected cucumber leaves image to be assessed under environment；Using stochastic gradient descent method, and the mind based on downy mildew severity
Through network appraising model, the cucumber downy mildew severity of cucumber leaves image is assessed.
The apparatus embodiments described above are merely exemplary, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (9)
1. a kind of appraisal procedure of cucumber downy mildew severity characterized by comprising
Obtain collected cucumber leaves image to be assessed under natural environment；
Using stochastic gradient descent method, and the neuralnetwork estimating model based on downy mildew severity, to the cucumber leaves figure
The cucumber downy mildew severity of picture is assessed.
2. the method according to claim 1, wherein the neuralnetwork estimating mould based on downy mildew severity
Type, before assessing the cucumber downy mildew severity of the cucumber leaves image, further includes:
The sample image of cucumber downy mildew blade collected under natural environment is pre-processed, and is based on pretreated sample
This picture construction obtains raw data set；
The degree of disease value of the sample image and the sample image concentrated based on the initial data, to original neural network mould
Type is trained, and obtains the neuralnetwork estimating model of the downy mildew severity.
3. according to the method described in claim 2, it is characterized in that, described to cucumber downy mildew leaf collected under natural environment
The sample image of piece is pre-processed, comprising:
The sample image that resolution ratio is lower than preset threshold is rejected from collected sample image；
The background patterns of each sample image are rejected, and each sample image is adjusted to pre-set dimension size.
4. according to the method described in claim 2, it is characterized in that, described be based on the raw data set, to original nerve net
Network model is trained, before obtaining the neuralnetwork estimating model of the downy mildew severity, further includes:
According to default processing mode, the sample image concentrated to the initial data is handled, to the raw data set
Expanded, the default processing mode includes at least any one in following three kinds of modes, following three kinds of modes point
It Wei not color jitter, flip horizontal and flip vertical.
5. the method according to claim 1, wherein the neuralnetwork estimating model packet of the downy mildew severity
Include input layer, 5 convolutional layers, 4 pond layers, 4 batches of standardization layers, 2 full articulamentums and output layer.
6. according to the method described in claim 5, it is characterized in that, the input layer and first convolutional layer and first batch of rule
The connection of generalized layer, first convolutional layer and the first batch of standardization layer are connect with first pond layer, and described first
A pond layer is connect with second convolutional layer and second batch of standardization layer, second convolutional layer and the second batch of rule
Generalized layer is connect with second pond layer, and second pond layer connects with third convolutional layer and third batch standardization layer
It connects, the third convolutional layer and the third batch standardization layer are connect with third pond layer, third pond layer
Connect with batch standardization layer of the 4th convolutional layer and the 4th, the 4th convolutional layer and the 4th batch of standardization layer and
The connection of 4th pond layer, the 4th pond layer are connect with the 5th convolutional layer, the 5th convolutional layer successively with institute
State 2 full articulamentums and output layer connection.
7. a kind of assessment device of cucumber downy mildew severity characterized by comprising
Module is obtained, for obtaining collected cucumber leaves image to be assessed under natural environment；
Evaluation module, for using stochastic gradient descent method, and the neuralnetwork estimating model based on downy mildew severity, to institute
The cucumber downy mildew severity for stating cucumber leaves image is assessed.
8. a kind of electronic equipment characterized by comprising
At least one processor；And
At least one processor being connect with the processor communication, in which:
The memory is stored with the program instruction that can be executed by the processor, and the processor calls described program to instruct energy
Enough methods executed as described in claim 1 to 6 is any.
9. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer instruction is stored up, the computer instruction makes the computer execute the method as described in claim 1 to 6 is any.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811623559.4A CN109859167A (en) | 2018-12-28 | 2018-12-28 | The appraisal procedure and device of cucumber downy mildew severity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811623559.4A CN109859167A (en) | 2018-12-28 | 2018-12-28 | The appraisal procedure and device of cucumber downy mildew severity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109859167A true CN109859167A (en) | 2019-06-07 |
Family
ID=66892910
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811623559.4A Pending CN109859167A (en) | 2018-12-28 | 2018-12-28 | The appraisal procedure and device of cucumber downy mildew severity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109859167A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112699941A (en) * | 2020-12-31 | 2021-04-23 | 浙江科技学院 | Plant disease severity image classification method and device, computer equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107784305A (en) * | 2017-09-29 | 2018-03-09 | 中国农业科学院农业环境与可持续发展研究所 | Facilities vegetable disease recognition method and device based on convolutional neural networks |
| CN108319988A (en) * | 2017-01-18 | 2018-07-24 | 华南理工大学 | A kind of accelerated method of deep neural network for handwritten Kanji recognition |
| CN108764039A (en) * | 2018-04-24 | 2018-11-06 | 中国科学院遥感与数字地球研究所 | Building extracting method, medium and the computing device of neural network, remote sensing image |
-
2018
- 2018-12-28 CN CN201811623559.4A patent/CN109859167A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108319988A (en) * | 2017-01-18 | 2018-07-24 | 华南理工大学 | A kind of accelerated method of deep neural network for handwritten Kanji recognition |
| CN107784305A (en) * | 2017-09-29 | 2018-03-09 | 中国农业科学院农业环境与可持续发展研究所 | Facilities vegetable disease recognition method and device based on convolutional neural networks |
| CN108764039A (en) * | 2018-04-24 | 2018-11-06 | 中国科学院遥感与数字地球研究所 | Building extracting method, medium and the computing device of neural network, remote sensing image |
Non-Patent Citations (4)
| Title |
|---|
| GUAN WANG等: "Automatic Image-Based Plant Disease Severity Estimation Using Deep Learning", 《COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE》 * |
| 刘瑾蓉等: "基于卷积神经网络的银杏叶片患病程度识别", 《中国农业科技导报》 * |
| 叶海建等: "基于Android的自然背景下黄瓜霜霉病定量诊断系统", 《农业机械学报》 * |
| 尹晔等: "基于迁移学习的甜菜褐斑病识别方法", 《计算机工程与设计》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112699941A (en) * | 2020-12-31 | 2021-04-23 | 浙江科技学院 | Plant disease severity image classification method and device, computer equipment and storage medium |
| CN112699941B (en) * | 2020-12-31 | 2023-02-14 | 浙江科技学院 | Plant disease severity image classification method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110148120B (en) | Intelligent disease identification method and system based on CNN and transfer learning | |
| CN109241903A (en) | Sample data cleaning method, device, computer equipment and storage medium | |
| CN110163813B (en) | Image rain removing method and device, readable storage medium and terminal equipment | |
| CN108717524B (en) | Gesture recognition system based on double-camera mobile phone and artificial intelligence system | |
| CN109740721B (en) | Wheat ear counting method and device | |
| CN109117857B (en) | Biological attribute identification method, device and equipment | |
| CN107545249A (en) | A kind of population ages' recognition methods and device | |
| CN109583297A (en) | Retina OCT volume data identification method and device | |
| CN108319894A (en) | Fruit recognition methods based on deep learning and device | |
| CN109446889A (en) | Object tracking method and device based on twin matching network | |
| CN109670509A (en) | Winter wheat seedling stage growing way parameter evaluation method and system based on convolutional neural networks | |
| CN110197474B (en) | Image processing method and device and training method of neural network model | |
| CN110458109A (en) | A kind of tealeaves disease recognition system and working method based on image recognition technology | |
| CN109815846A (en) | Image processing method, device, storage medium and electronic device | |
| CN109344738A (en) | The recognition methods of crop diseases and pest crop smothering and device | |
| CN110197116B (en) | Human behavior recognition method, device and computer readable storage medium | |
| CN114005029A (en) | Improved yolov5 network-based fingered citron pest and disease identification method and system | |
| CN104063686A (en) | System and method for performing interactive diagnosis on crop leaf segment disease images | |
| Adedoja et al. | Intelligent mobile plant disease diagnostic system using NASNet-mobile deep learning | |
| CN110378305A (en) | Tealeaves disease recognition method, equipment, storage medium and device | |
| CN109063720A (en) | Handwritten word training sample acquisition methods, device, computer equipment and storage medium | |
| CN112861718A (en) | Lightweight feature fusion crowd counting method and system | |
| CN110543848A (en) | Driver action recognition method and device based on three-dimensional convolutional neural network | |
| CN114445268A (en) | Garment style migration method and system based on deep learning | |
| CN110428374A (en) | A kind of small size pest automatic testing method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190607 |
|
| RJ01 | Rejection of invention patent application after publication |