CN111127423A - Rice pest and disease identification method based on CNN-BP neural network algorithm - Google Patents
Rice pest and disease identification method based on CNN-BP neural network algorithm Download PDFInfo
- Publication number
- CN111127423A CN111127423A CN201911335585.1A CN201911335585A CN111127423A CN 111127423 A CN111127423 A CN 111127423A CN 201911335585 A CN201911335585 A CN 201911335585A CN 111127423 A CN111127423 A CN 111127423A
- Authority
- CN
- China
- Prior art keywords
- cnn
- neural network
- layer
- model
- rice
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Image Analysis (AREA)
Abstract
The invention aims to provide a rice pest and disease identification method based on a CNN-BP neural network algorithm, and aims to construct a CNN-LeNet5 model, namely a network structure consisting of an input layer, a convolutional layer, a pooling layer, a fully-connected layer and an output layer. Firstly, gradually extracting features from the image, and finally extracting high-grade image features of rice plant diseases and insect pests. And after the feature extraction is completed, removing the last softmax classification layer of the network structure, and replacing the last softmax classification layer with a BP model. And the automatic identification of the rice disease and insect pest image is realized by combining the CNN automatic feature extraction and the BP neural network classification model.
Description
Technical Field
The invention relates to the field of rice disease and insect pest identification and classification, in particular to a rice disease and insect pest identification method based on a CNN-BP neural network algorithm.
Background
The rice is a widely planted grain crop in China, and the improvement of the yield and the quality of the rice is of great importance to the economic development of China. The traditional rice disease and insect pest investigation method mainly comprises the steps of artificially identifying and counting rice pests through lamp attraction, artificially investigating the pests in the field, and diagnosing diseases and insect pests in the field. The problems of heavy task, low efficiency, non-real-time property and the like in field investigation by means of manual identification, counting and diagnosis are solved. With the mature development of computer vision and image processing technology, the automatic identification and diagnosis of rice diseases and insect pests by using images becomes possible. The intelligent identification of the rice diseases and insect pests is a technical means for completing processing and explaining tasks by using an imaging system through a computer, and can realize segmentation of rice disease and insect pest images, extraction of characteristic values and automatic identification of the rice diseases and insect pests.
At present, researchers at home and abroad research a pest identification method, which is to establish a characteristic database for identification by searching characteristics such as texture, shape, color and the like of a pest image. For example, in 2008, Natalia Larios used local features to classify stone fly images; in 208, the livinbin uses a mode of combining color features, shape features and texture features with PCA to identify rice diseases and insect pests. However, the extracted texture, shape and color features belong to shallow features, and the features are easily influenced by rotation, translation and brightness degrees, so that the identification of the pest image is restricted.
Convolutional Neural Networks (CNN) are a type of feed-forward Neural network that includes convolution calculation and has a deep structure, and structurally mainly include modules such as an input layer, a Convolutional layer, a pooling layer, a nonlinear activation layer, and a full connection layer, and have a hierarchical learning mode, and parameter optimization is performed through a back propagation algorithm in a learning stage to adaptively learn an image shallow layer. The CNN has the characteristic of active feature learning, has strong expression capability and generalization capability, and can extract high-level image features by using the CNN. The CNN gradually extracts image features of each level from an original image through a multilayer convolutional network, and then gradually extracts high-level features from shallow features such as texture, color, shape and the like. Compared with shallow features, the high-level features extracted by the CNN have higher robustness and identifiability.
The BP (back propagation) neural network is a mathematical model established by simulating a biological brain nervous system, can effectively identify the nonlinear mapping relation between an input vector and an output vector of a complex system, and is particularly suitable for solving the problem that the output is influenced by more input factors and the influence relation is ambiguous. The BP neural network has strong generalization capability, nonlinear mapping capability and self-adaption capability, and can effectively classify and predict samples. However, the BP neural network has higher dependence on sample characteristics and higher recognition rate on the characteristics with high recognition. Therefore, rice pest and disease identification can be realized by combining the CNN and BP neural network algorithm.
Disclosure of Invention
To solve the above existing problems. The invention provides a rice disease and insect pest identification method based on a CNN-BP neural network algorithm, which utilizes the strong expression capability and generalization capability of the CNN, extracts the high-level image characteristics of a rice disease and insect pest image through the CNN, and combines the BP neural network algorithm to realize the task of automatically identifying the category of the rice disease and insect pest in the whole process. To achieve this object:
the invention provides a rice pest and disease identification method based on a CNN-BP neural network, which comprises the following steps of,
step 1: classifying the collected rice disease and insect pest images to establish a data set, and establishing rice disease and insect pest image categories, namely manually marking the categories for each rice disease and insect pest image, and preparing for subsequent training of a CNN network model and a BP neural network;
step 2: and constructing a CNN-LeNet5 model. The input layer structure is 512 x 3, the two convolution layers are 512 x 24 and 256 x 64, the maximum pooling mode is selected by the pooling layers, and the two fully-connected layers are 1 x 64 to 120 and 120 to 8;
and step 3: the CNN model is trained. Inputting training sample images and image types into a CNN model to enable a softmax layer to calculate loss errors, adjusting CNN convolutional layer template parameters by continuously reducing the errors, and training to obtain an optimal CNN model;
and 4, step 4: 8 high-level features of the training sample are extracted. Removing a softmax layer in the CNN model, inputting a training sample image into the trained CNN model, and outputting 8 high-level features of the training sample by the CNN model through a full-connection layer 120 × 8;
and 5: constructing a three-layer BP neural network model, taking 8 high-grade characteristics as network input, taking labels of 8 types of rice plant diseases and insect pests of cnaphalocrocis medinalis guenee adults, cnaphalocrocis medinalis guenee pupae, cnaphalocrocis medinalis guenee eggs, chilo suppressalis adults, chilo suppressalis larvae, chilo suppressalis pupae and chilo suppressalis eggs as network output, and setting the number of hidden layer nodes as 11 layers;
step 6: and training a BP neural network model. 8 high-level features of the training sample image are used for training a BP neural network model;
and 7: 8 high-level features of the test sample are extracted. Inputting the test sample image into the trained CNN model, wherein the CNN model outputs 8 high-level features of the test sample through a full-connection layer 120 x 8;
and 8: and outputting a classification result. And inputting 8 high-level features of the test sample into the trained BP neural network, and outputting a classification result of the test image.
As a further improvement of the present invention, in the fifth step, the function of the BP neural network is set as follows:
the transfer functions of the hidden layer and the output layer are respectively set as a 'logsig' function and a 'tangsig' function, the training function is a 'trainlm' function, and the learning function is a 'learngd' function.
As a further improvement of the invention, the calculation formula of softmax in the third step is as follows:
class S in which n numerical values representk,k∈(0,n]I denotes a certain class in k, giA value, P (S), representing the classificationk) Is the probability of that classification.
As a further improvement of the present invention, in the fifth step, a calculation formula of the hidden layer of the BP neural network is as follows:
m represents the number of hidden layer neuron nodes, n represents the number of input layer nodes, and l represents the number of output layer nodes.
The invention provides a rice disease and insect pest identification method based on a CNN-BP neural network algorithm, which is specifically designed as follows:
1. the invention utilizes CNN active characteristic learning, has the characteristics of strong characteristic expression capability and generalization capability, and utilizes CNN to extract advanced characteristics of rice plant disease and insect pest images. The CNN extracted features are stronger in robustness and generalization capability, and different types of images can be better represented.
2. A CNN-LeNet5 model for extracting rice pest and disease features is designed, the input layer structure is 512 x 3, the two layers of convolution layers are 512 x 24 and 256 x 64, the maximum pooling mode is selected for the pooling layers, and the two layers of full-connection layers are 1 x 64 to 120 and 120 to 8.
3. A BP neural network model for classifying rice diseases and insect pests is designed, the model is of a three-layer structure, the number of nodes of an input layer is 8, the number of nodes of a hidden layer is 11, the number of nodes of an output layer is 8, transfer functions of the hidden layer and the output layer are respectively set as a 'logsig' function and a 'tangsig' function, a training function is a 'train lm' function, and a learning function is a 'learngd' function.
4. The invention adopts BP neural network algorithm to replace softmax layer in CNN to realize the whole-process automation of mathematical classification algorithm model.
5. The CNN does not need to do complicated preprocessing work on the image in advance when extracting the image characteristics, and the CNN extracted characteristics can automatically overcome certain noise interference.
6. The CNN-BP neural network algorithm model greatly improves the accuracy of rice pest identification, improves the robustness in the identification process, and has significance in engineering application.
5. The CNN-BP neural network algorithm model provided by the invention can realize automatic identification of rice diseases and insect pests, and lays a solid core technology for subsequent intelligent agricultural technologies such as rice disease and insect pest management and the like.
Drawings
FIG. 1 is a flow chart of the overall algorithm principle of the present invention;
FIG. 2 is a CNN model structure employed in the present invention;
fig. 3 is a BP neural network model structure.
Detailed Description
The invention is described in further detail below with reference to the following detailed description and accompanying drawings:
the invention provides a rice disease and insect pest identification method based on a CNN-BP neural network algorithm, which utilizes the strong expression capability and generalization capability of the CNN, extracts the high-level image characteristics of a rice disease and insect pest image through the CNN, and combines the BP neural network algorithm to realize the task of automatically identifying the category of the rice disease and insect pest in the whole process.
The overall algorithm principle flow of the invention is shown in fig. 1.
Firstly, marking categories of collected rice disease and insect pest images and establishing a database. And then dividing the original data in the established data set into a training sample image and a testing sample image, wherein the training sample image is used for training a CNN model and a BP model, and the testing sample image is used for testing the effectiveness of the algorithm model. The training samples need to train a complete CNN model, and because the whole CNN algorithm process needs to be participated by a loss function layer, the characteristics obtained by convolution of the convolution template parameters can be optimal under the effect of loss function reduction, the CNN network needs to be trained by the training samples at first.
And after the preparation of the data set is completed, a CNN network is created, the CNN-LeNet5 model is constructed by the network, the input layer structure is 512 x 3, the two convolution layers have structures of 512 x 24 and 256 x 64, the maximum pooling mode is selected by the pooling layer, and the two fully-connected layers are 1 x 64 to 120 and 120 to 8. The network model structure of CNN-LeNet5 is shown in FIG. 2.
And (5) completing the pre-training of the CNN model by using the constructed CNN-LeNet5 model structure. Training the sample image to enable the softmax layer to calculate loss errors, then continuously reducing the errors so as to continuously adjust template parameters of the CNN convolutional layer, and training the convolutional template with the optimal feature extraction. Because the features extracted by the convolutional layer can be identified by the network better by continuously reducing the error in the softmax layer, the smaller the error is, the more effective and robust the extracted features are, the better the subsequent identification is, wherein the calculation formula of softmax is as follows:
class S in which n numerical values representk,k∈(0,n]I denotes a certain class in k, giA value, P (S), representing the classificationk) Is the probability of that classification.
And then inputting the training sample into the trained CNN model again, extracting 8 high-level features from the full-connection layer 120 x 8, inputting the 8 high-level features into a BP neural network to train the BP model, wherein the BP model has a structure shown in figure 3, and the trained BP neural network is used as a rice disease and pest classifier.
And removing the last loss function softmax layer in the trained CNN model, and replacing the last layer with the trained BP model to obtain the CNN-BP model.
And finally, inputting a test sample image into the trained CNN-BP model, outputting a classification result, and optimizing to obtain an algorithm model with the accuracy rate of 94.58% in rice pest identification.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, but any modifications or equivalent variations made according to the technical spirit of the present invention are within the scope of the present invention as claimed.
Claims (4)
1. A rice disease and insect pest identification method based on a CNN-BP neural network algorithm comprises the following specific steps,
step 1: classifying the collected rice disease and insect pest images to establish a data set, and establishing rice disease and insect pest image categories, namely manually marking the categories for each rice disease and insect pest image, and preparing for subsequent training of a CNN network model and a BP neural network;
step 2: constructing a CNN-LeNet5 model, wherein the input layer structure is 512 x 3, the two layers of convolution layers are 512 x 24 and 256 x 64, the maximum pooling mode is selected for the pooling layers, and the two layers of full-connection layers are 1 x 64 to 120 and 120 to 8;
and step 3: training a CNN model, inputting training sample images and image types into the CNN model to enable a softmax layer to calculate loss errors, adjusting CNN convolutional layer template parameters by continuously reducing the errors, and training to obtain an optimal CNN model;
and 4, step 4: extracting 8 high-level features of the training sample, removing a softmax layer in the CNN model, inputting the training sample image into the trained CNN model, and outputting the 8 high-level features of the training sample by the CNN model through a full-connection layer 120 x 8;
and 5: constructing a three-layer BP neural network model, taking 8 high-grade characteristics as network input, taking labels of 8 types of rice plant diseases and insect pests of cnaphalocrocis medinalis guenee adults, cnaphalocrocis medinalis guenee pupae, cnaphalocrocis medinalis guenee eggs, chilo suppressalis adults, chilo suppressalis larvae, chilo suppressalis pupae and chilo suppressalis eggs as network output, and setting the number of hidden layer nodes as 11 layers;
step 6: training a BP neural network model, and using 8 high-level features of a training sample image to train the BP neural network model;
and 7: extracting 8 high-level features of the test sample, inputting the image of the test sample into a trained CNN model, and outputting the 8 high-level features of the test sample by the CNN model through a full-connection layer 120 x 8;
and 8: and outputting a classification result, inputting 8 high-level features of the test sample into the trained BP neural network, and outputting the classification result of the test image.
2. The CNN-BP neural network algorithm rice pest identification method according to claim 1, characterized in that: the calculation formula of softmax in the third step is as follows:
class S in which n numerical values representk,k∈(0,n]I denotes a certain class in k, giA value, P (S), representing the classificationk) Is the probability of that classification.
3. The CNN-BP neural network algorithm rice pest identification method according to claim 1, characterized in that: in the fifth step, transfer functions of a hidden layer and an output layer of the BP neural network model are respectively set as a 'logsig' function and a 'tangsig' function, the training function is a 'trainlm' function, and the learning function is a 'learngd' function.
4. The CNN-BP neural network algorithm rice pest identification method according to claim 1, characterized in that: the number algorithm formula of the hidden layer nodes of the BP neural network model in the step five is as follows:
m represents the number of hidden layer neuron nodes, n represents the number of input layer nodes, and l represents the number of output layer nodes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911335585.1A CN111127423B (en) | 2019-12-23 | 2019-12-23 | Rice pest and disease identification method based on CNN-BP neural network algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911335585.1A CN111127423B (en) | 2019-12-23 | 2019-12-23 | Rice pest and disease identification method based on CNN-BP neural network algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111127423A true CN111127423A (en) | 2020-05-08 |
CN111127423B CN111127423B (en) | 2023-04-07 |
Family
ID=70501135
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911335585.1A Active CN111127423B (en) | 2019-12-23 | 2019-12-23 | Rice pest and disease identification method based on CNN-BP neural network algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111127423B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111814532A (en) * | 2020-05-09 | 2020-10-23 | 五邑大学 | Detection and spraying method for bacterial leaf blight of rice, control device and unmanned aerial vehicle |
CN112036470A (en) * | 2020-08-28 | 2020-12-04 | 扬州大学 | Cloud transmission-based multi-sensor fusion cucumber bemisia tabaci identification method |
CN112507770A (en) * | 2020-08-13 | 2021-03-16 | 华南农业大学 | Rice disease and insect pest identification method and system |
CN113822417A (en) * | 2021-09-22 | 2021-12-21 | 中国电建集团成都勘测设计研究院有限公司 | Transformer fault type diagnosis method combining two machine learning methods |
CN115797789A (en) * | 2023-02-20 | 2023-03-14 | 成都东方天呈智能科技有限公司 | Cascade detector-based rice pest monitoring system and method and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106971160A (en) * | 2017-03-23 | 2017-07-21 | 西京学院 | Winter jujube disease recognition method based on depth convolutional neural networks and disease geo-radar image |
CN107578089A (en) * | 2017-09-13 | 2018-01-12 | 中国水稻研究所 | A kind of crops lamp lures the automatic identification and method of counting for observing and predicting insect |
CN109558787A (en) * | 2018-09-28 | 2019-04-02 | 浙江农林大学 | A kind of Bamboo insect pests recognition methods based on convolutional neural networks model |
CN110148120A (en) * | 2019-05-09 | 2019-08-20 | 四川省农业科学院农业信息与农村经济研究所 | A kind of disease intelligent identification Method and system based on CNN and transfer learning |
CN110378435A (en) * | 2019-07-25 | 2019-10-25 | 安徽工业大学 | A method of the Apple Leaves disease recognition based on convolutional neural networks |
-
2019
- 2019-12-23 CN CN201911335585.1A patent/CN111127423B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106971160A (en) * | 2017-03-23 | 2017-07-21 | 西京学院 | Winter jujube disease recognition method based on depth convolutional neural networks and disease geo-radar image |
CN107578089A (en) * | 2017-09-13 | 2018-01-12 | 中国水稻研究所 | A kind of crops lamp lures the automatic identification and method of counting for observing and predicting insect |
CN109558787A (en) * | 2018-09-28 | 2019-04-02 | 浙江农林大学 | A kind of Bamboo insect pests recognition methods based on convolutional neural networks model |
CN110148120A (en) * | 2019-05-09 | 2019-08-20 | 四川省农业科学院农业信息与农村经济研究所 | A kind of disease intelligent identification Method and system based on CNN and transfer learning |
CN110378435A (en) * | 2019-07-25 | 2019-10-25 | 安徽工业大学 | A method of the Apple Leaves disease recognition based on convolutional neural networks |
Non-Patent Citations (2)
Title |
---|
张建华等: "基于改进VGG卷积神经网络的棉花病害识别模型", 《中国农业大学学报》 * |
邱靖等: "基于卷积神经网络的水稻病害图像识别研究", 《云南农业大学学报(自然科学)》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111814532A (en) * | 2020-05-09 | 2020-10-23 | 五邑大学 | Detection and spraying method for bacterial leaf blight of rice, control device and unmanned aerial vehicle |
CN112507770A (en) * | 2020-08-13 | 2021-03-16 | 华南农业大学 | Rice disease and insect pest identification method and system |
CN112036470A (en) * | 2020-08-28 | 2020-12-04 | 扬州大学 | Cloud transmission-based multi-sensor fusion cucumber bemisia tabaci identification method |
CN113822417A (en) * | 2021-09-22 | 2021-12-21 | 中国电建集团成都勘测设计研究院有限公司 | Transformer fault type diagnosis method combining two machine learning methods |
CN115797789A (en) * | 2023-02-20 | 2023-03-14 | 成都东方天呈智能科技有限公司 | Cascade detector-based rice pest monitoring system and method and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN111127423B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111127423B (en) | Rice pest and disease identification method based on CNN-BP neural network algorithm | |
Zhou et al. | Evaluation of fish feeding intensity in aquaculture using a convolutional neural network and machine vision | |
WO2022160771A1 (en) | Method for classifying hyperspectral images on basis of adaptive multi-scale feature extraction model | |
AU2020102885A4 (en) | Disease recognition method of winter jujube based on deep convolutional neural network and disease image | |
CN108734208B (en) | Multi-source heterogeneous data fusion system based on multi-mode deep migration learning mechanism | |
CN106971152B (en) | Method for detecting bird nest in power transmission line based on aerial images | |
CN110457982B (en) | Crop disease image identification method based on feature migration learning | |
CN109325495B (en) | Crop image segmentation system and method based on deep neural network modeling | |
CN107862694A (en) | A kind of hand-foot-and-mouth disease detecting system based on deep learning | |
CN104217214A (en) | Configurable convolutional neural network based red green blue-distance (RGB-D) figure behavior identification method | |
CN107563389A (en) | A kind of corps diseases recognition methods based on deep learning | |
CN111652247A (en) | Diptera insect identification method based on deep convolutional neural network | |
Chen et al. | Agricultural remote sensing image cultivated land extraction technology based on deep learning | |
CN112749675A (en) | Potato disease identification method based on convolutional neural network | |
CN111626969B (en) | Corn disease image processing method based on attention mechanism | |
Rai et al. | Classification of diseased cotton leaves and plants using improved deep convolutional neural network | |
CN113221913A (en) | Agriculture and forestry disease and pest fine-grained identification method and device based on Gaussian probability decision-level fusion | |
CN109102019A (en) | Image classification method based on HP-Net convolutional neural networks | |
CN111160428A (en) | Automatic vegetable identification method based on CNN-SVM algorithm | |
CN111144464B (en) | Fruit automatic identification method based on CNN-Kmeans algorithm | |
CN114511849B (en) | Grape thinning identification method based on graph attention network | |
Balakrishna et al. | Tomato Leaf Disease Detection Using Deep Learning: A CNN Approach | |
An | Xception network for weather image recognition based on transfer learning | |
CN115565168A (en) | Sugarcane disease identification method based on attention system residual error capsule network | |
CN108846327A (en) | A kind of intelligent distinguishing system and method for mole and melanoma |
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 |