CN106022467A - Crop disease detection system based on neural network - Google Patents
Crop disease detection system based on neural network Download PDFInfo
- Publication number
- CN106022467A CN106022467A CN201610324908.7A CN201610324908A CN106022467A CN 106022467 A CN106022467 A CN 106022467A CN 201610324908 A CN201610324908 A CN 201610324908A CN 106022467 A CN106022467 A CN 106022467A
- Authority
- CN
- China
- Prior art keywords
- neural network
- disease
- media
- network module
- picture
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
- G06N3/065—Analogue means
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Neurology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Processing (AREA)
Abstract
The invention provides a crop disease detection system based on a neural network and relates to the field of artificial intelligence. The system comprises a network module, a neural network module, a CPU master control module and a database and the like. The network module is connected with a user terminal, and is used for receiving data of the user terminal or sending data to the terminal. The neural network module is a software program or a hardware system comprising a convolution neural network. The CPU master control module is used for analyzing the output of the neural network module, querying the database and sending the result to the user terminal. The database is used for recording disease information and treatment method of each crop. With the neural network module being combined, the crop disease detection system overcomes the defect that a feature matching algorithm is not fully considered, has good generalization ability and improves predication accuracy.
Description
Technical field
The present invention relates to field of artificial intelligence, particularly relate to a kind of disease of agricultural plants detecting system based on neutral net.
Background technology
Grain is most important for the life of people, but often uses a lot of disease before grain produces, and owing to the average schooling of peasant is relatively low, when disease occur in crops, is often at a loss or at will processes, and the yield causing grain is the highest.
Nowadays along with the rise of artificial intelligence neural networks so that machine oneself is abstract, study features is possibly realized.Therefore, artificial intelligence disease of agricultural plants detection be scheme be present demand.
Summary of the invention
In order to solve this problem, the present invention proposes a kind of disease of agricultural plants detecting system based on neutral net, has convenient and swift, recognition rate higher characteristic.
The technical scheme is that
A kind of disease of agricultural plants detecting system based on neutral net,
This system mainly comprises mixed-media network modules mixed-media, neural network module, CPU module and data base.
Wherein mixed-media network modules mixed-media is mainly used in carrying out network with user terminal and is connected, and receives the picture of user's shooting and the result finally inquired is sent to user terminal；
Neural network module comprises a convolutional neural networks, and first it be iterated training with the picture of the various crops various disease comprised in data base, to obtain the neural network model of a convergence.
CPU module is mainly used in controlling mixed-media network modules mixed-media, obtains the data that user terminal transmits, passes it to neural network module, then the output of neural network module is resolved, identifying these crops and disease type, then inquiry data base obtains processing method, is pushed to user terminal.
Lane database bread contains picture and the processing method of the various disease of various crops, the novel crop of convenient interpolation and New Type of Diseases information.
Further, this system directly i.e. be can determine that disease of agricultural plants type by mixed-media network modules mixed-media reception corps diseases picture and informed processing method.
Further, neural network module is internal is convolutional neural networks, can identify the local feature of picture, and training speed is fast, and accuracy rate is high.
Further, the picture of substantial amounts of crops and disease information should be comprised in data base, in order to neural metwork training.
The present invention combines neural network model, overcomes Feature Correspondence Algorithm and considers the most full shortcoming, have good generalization ability, improves the accuracy of prediction.By novel artificial intelligence technology, facilitate the process of disease of agricultural plants, improve crop yield.
Accompanying drawing explanation
Fig. 1 is disease of agricultural plants detecting system composition frame chart；
Fig. 2 is disease of agricultural plants detecting system workflow diagram.
Detailed description of the invention
Below present disclosure is carried out more detailed elaboration:
The composition frame chart of native system is as shown in Figure 1: comprise mixed-media network modules mixed-media, neural network module, CPU module and data base.
Wherein CPU module is mainly used in controlling other modules, and data base is used for depositing sample and process information.CPU module read-write database information, when neural metwork training, by picture and the disease information input neural network of data base.After neural network module is formed, CPU analyzes the output information of neural network module, then inquires about data base, will send information to mixed-media network modules mixed-media and be pushed to user.
Neural network module is a convolutional neural networks trained, and has the strongest generalization ability, it is possible to judge its kind and disease information according to input crops picture.Being trained by the picture sample of substantial amounts of disease of agricultural plants information, final accuracy obtains target and is formed.
Mixed-media network modules mixed-media is for receiving the picture of user and to user's pushed information.
The workflow diagram of native system is as shown in Figure 2: first user is by the picture of the terminal taking corps diseases such as mobile phone, is delivered to mixed-media network modules mixed-media.Pictorial information in mixed-media network modules mixed-media is passed to neural network module by CPU, and neural network module produces kind and the disease information of crops by analysis.Disease information and processing mode, according to these information inquiries data base, are sent to mixed-media network modules mixed-media and pass to user by CPU.
Claims (4)
1. a disease of agricultural plants detecting system based on neutral net, it is characterised in that this system mainly comprises mixed-media network modules mixed-media, neural network module, CPU module and data base；
Wherein mixed-media network modules mixed-media is mainly used in carrying out network with user terminal and is connected, and receives the picture of user's shooting and the result finally inquired is sent to user terminal；
Neural network module comprises a convolutional neural networks, and first it be iterated training with the picture of the various crops various disease comprised in data base, to obtain the neural network model of a convergence；
CPU module is mainly used in controlling mixed-media network modules mixed-media, obtains the data that user terminal transmits, passes it to neural network module, then the output of neural network module is resolved, identifying these crops and disease type, then inquiry data base obtains processing method, is pushed to user terminal；
Lane database bread contains picture and the processing method of the various disease of various crops, the novel crop of convenient interpolation and New Type of Diseases information.
2. according to a kind of based on neutral net the disease of agricultural plants detecting system described in claims 1, it is characterised in that:
This system directly receives corps diseases picture by mixed-media network modules mixed-media and i.e. can determine that disease of agricultural plants type and inform processing method.
3. according to a kind of based on neutral net the disease of agricultural plants detecting system described in claims 1, it is characterised in that:
Neural network module is internal is convolutional neural networks, can identify the local feature of picture.
4. according to a kind of based on neutral net the disease of agricultural plants detecting system described in claims 1, it is characterised in that:
Comprise so that the crops of neural metwork training and the picture of disease information in data base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610324908.7A CN106022467A (en) | 2016-05-17 | 2016-05-17 | Crop disease detection system based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610324908.7A CN106022467A (en) | 2016-05-17 | 2016-05-17 | Crop disease detection system based on neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106022467A true CN106022467A (en) | 2016-10-12 |
Family
ID=57098084
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610324908.7A Pending CN106022467A (en) | 2016-05-17 | 2016-05-17 | Crop disease detection system based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106022467A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682704A (en) * | 2017-01-20 | 2017-05-17 | 中国科学院合肥物质科学研究院 | Method of disease image identification based on hybrid convolutional neural network fused with context information |
| CN107330887A (en) * | 2017-07-11 | 2017-11-07 | 重庆邮电大学 | A kind of crop pest control scheme commending system based on deep learning |
| CN107392091A (en) * | 2017-06-09 | 2017-11-24 | 河北威远生物化工有限公司 | A kind of agriculture artificial intelligence makees object detecting method, mobile terminal and computer-readable medium |
| CN107742290A (en) * | 2017-10-18 | 2018-02-27 | 成都东谷利农农业科技有限公司 | Plant disease identifies method for early warning and device |
| CN108509608A (en) * | 2018-03-30 | 2018-09-07 | 重庆市农业科学院 | Interactive Management System of Crop Production andIts based on WEB and its method |
| CN109522858A (en) * | 2018-11-26 | 2019-03-26 | Oppo广东移动通信有限公司 | Plant disease detection method, device and terminal device |
| CN109922361A (en) * | 2019-03-29 | 2019-06-21 | 深圳海青联合技术有限公司 | A kind of artificial intelligence box |
| WO2020047739A1 (en) * | 2018-09-04 | 2020-03-12 | 安徽中科智能感知大数据产业技术研究院有限责任公司 | Method for predicting severe wheat disease on the basis of multiple time-series attribute element depth features |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI245205B (en) * | 2001-09-11 | 2005-12-11 | I-Chang Jou | Fake withdrawing prevention and early warning monitoring system for ATM based on neural network |
| CN102759528A (en) * | 2012-07-09 | 2012-10-31 | 陕西科技大学 | Method for detecting diseases of crop leaves |
| CN104598908A (en) * | 2014-09-26 | 2015-05-06 | 浙江理工大学 | Method for recognizing diseases of crop leaves |
| CN104899255A (en) * | 2015-05-15 | 2015-09-09 | 浙江大学 | Image database establishing method suitable for training deep convolution neural network |
-
2016
- 2016-05-17 CN CN201610324908.7A patent/CN106022467A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI245205B (en) * | 2001-09-11 | 2005-12-11 | I-Chang Jou | Fake withdrawing prevention and early warning monitoring system for ATM based on neural network |
| CN102759528A (en) * | 2012-07-09 | 2012-10-31 | 陕西科技大学 | Method for detecting diseases of crop leaves |
| CN104598908A (en) * | 2014-09-26 | 2015-05-06 | 浙江理工大学 | Method for recognizing diseases of crop leaves |
| CN104899255A (en) * | 2015-05-15 | 2015-09-09 | 浙江大学 | Image database establishing method suitable for training deep convolution neural network |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106682704A (en) * | 2017-01-20 | 2017-05-17 | 中国科学院合肥物质科学研究院 | Method of disease image identification based on hybrid convolutional neural network fused with context information |
| CN107392091A (en) * | 2017-06-09 | 2017-11-24 | 河北威远生物化工有限公司 | A kind of agriculture artificial intelligence makees object detecting method, mobile terminal and computer-readable medium |
| CN107392091B (en) * | 2017-06-09 | 2020-10-16 | 河北威远生物化工有限公司 | Agricultural artificial intelligence crop detection method, mobile terminal and computer readable medium |
| CN107330887A (en) * | 2017-07-11 | 2017-11-07 | 重庆邮电大学 | A kind of crop pest control scheme commending system based on deep learning |
| CN107742290A (en) * | 2017-10-18 | 2018-02-27 | 成都东谷利农农业科技有限公司 | Plant disease identifies method for early warning and device |
| CN108509608A (en) * | 2018-03-30 | 2018-09-07 | 重庆市农业科学院 | Interactive Management System of Crop Production andIts based on WEB and its method |
| CN108509608B (en) * | 2018-03-30 | 2021-06-22 | 重庆市农业科学院 | WEB-based interactive crop production management system and method thereof |
| WO2020047739A1 (en) * | 2018-09-04 | 2020-03-12 | 安徽中科智能感知大数据产业技术研究院有限责任公司 | Method for predicting severe wheat disease on the basis of multiple time-series attribute element depth features |
| CN109522858A (en) * | 2018-11-26 | 2019-03-26 | Oppo广东移动通信有限公司 | Plant disease detection method, device and terminal device |
| CN109922361A (en) * | 2019-03-29 | 2019-06-21 | 深圳海青联合技术有限公司 | A kind of artificial intelligence box |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106022467A (en) | Crop disease detection system based on neural network | |
| US10460231B2 (en) | Method and apparatus of neural network based image signal processor | |
| WO2016041442A1 (en) | Data processing method and device | |
| CN110148120A (en) | A kind of disease intelligent identification Method and system based on CNN and transfer learning | |
| CN104063686B (en) | Crop leaf diseases image interactive diagnostic system and method | |
| CN111767849A (en) | Crop pest and disease identification method and device and storage medium | |
| CN110345610B (en) | Control method and device of air conditioner and air conditioning equipment | |
| WO2021104124A1 (en) | Method, apparatus and system for determining confinement pen information, and storage medium | |
| KR102526846B1 (en) | Fruit tree disease Classification System AND METHOD Using Generative Adversarial Networks | |
| CN110610125A (en) | Ox face identification method, device, equipment and storage medium based on neural network | |
| WO2020232942A1 (en) | Method for constructing farmland image-based convolutional neural network model, and system thereof | |
| CN110827273A (en) | Tea disease detection method based on regional convolution neural network | |
| Singh et al. | CottonLeafNet: cotton plant leaf disease detection using deep neural networks | |
| Hua et al. | A review of target recognition technology for fruit picking robots: from digital image processing to deep learning | |
| Parvez et al. | IoT in agriculture | |
| CN111242183A (en) | Image identification and classification method and device based on attention mechanism | |
| Pramudhita et al. | Strawberry Plant Diseases Classification Using CNN Based on MobileNetV3-Large and EfficientNet-B0 Architecture | |
| Rahaman et al. | A deep learning based smartphone application for detecting mango diseases and pesticide suggestions | |
| Zheng et al. | Fruit tree disease recognition based on convolutional neural networks | |
| CN113344009B (en) | Light and small network self-adaptive tomato disease feature extraction method | |
| Li et al. | Cattle face recognition under partial occlusion | |
| CN114296443A (en) | Unmanned modular combine harvester | |
| Morchid et al. | Intelligent detection for sustainable agriculture: A review of IoT-based embedded systems, cloud platforms, DL, and ML for plant disease detection | |
| US20220051154A1 (en) | Method and apparatus for measuring plant trichomes | |
| Nalli et al. | Performance Analysis of Pre-Trained Deep Learning Architectures for Classification of Corn Leaf Diseases |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161012 |