Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for constructing DCNN leaf blast classification model based on fusion features

A technology that combines features and construction methods, applied in the field of data processing, can solve problems such as small sample data, inability to build deep learning models, expensive hyperspectral instruments, etc., and achieve high accuracy

Pending Publication Date: 2022-02-25
SHENYANG AGRI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The reason may be that there are few sample data and it is impossible to build a deep learning model
[0031] In existing studies, researchers mostly use three-dimensional hyperspectral data for deep learning modeling. Although this modeling method can obtain high accuracy, in practical agricultural applications, it is still necessary to use expensive The hyperspectral instrument cannot really be popularized and applied

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for constructing DCNN leaf blast classification model based on fusion features
  • Method for constructing DCNN leaf blast classification model based on fusion features
  • Method for constructing DCNN leaf blast classification model based on fusion features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The present invention will be further described below in conjunction with specific examples, but the present invention is not limited by the examples.

[0062] A method for building a DCNN leaf blast classification model based on fusion features, comprising the following steps:

[0063] S1. Use the obtained data of different disease levels of rice leaf blast as a sample;

[0064] S2. Obtain the best leaf blast grading features:

[0065] By using the determination coefficient isopotential map to screen the vegetation index with better correlation with the disease grade;

[0066] Using SPA and RF algorithms to extract spectral feature bands;

[0067] Texture features (TFs) and their fusion features are adopted.

[0068] S3. Build rice leaf blast classification model:

[0069] The grade data described in step S1 are all one-dimensional data, and the number of input feature numbers is used as network input respectively;

[0070] At the same time, the number of channels...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a method for constructing a DCNN leaf blast classification model based on fusion features. The method comprises the following steps: S1, taking obtained different disease grade data of rice leaf blast as samples; s2, obtaining an optimal leaf blast classification feature; s3, constructing a rice leaf blast classification model; and S4, carrying out a training test on the rice leaf blast classification model in the step S3. On the premise of keeping the design concept of the ResNet network, the rice leaf blast classification model is established by adjusting the network depth and structure of the ResNet network and adding the BatchNorm layer and the Dropout layer, so that a scientific and theoretical basis is expected to be provided for rice leaf blast disease detection.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to a method for constructing a DCNN leaf blast classification model based on fusion features. Background technique [0002] Crop diseases and insect pests have caused huge losses to agricultural production. According to the statistics of the Food and Agriculture Organization of the United Nations, worldwide, the annual grain production reduction caused by disease and insect pests accounts for about 25% of the total grain production, of which the production reduction caused by diseases is 14%. , the yield reduction caused by pests is 10%. [0003] In China, the annual direct food loss due to the outbreak and damage of pests and diseases is about 30% of the total output, which has caused a huge impact on the domestic economy. However, nowadays, crop disease monitoring mainly relies on field surveys and field sampling by plant protection personnel. Although these traditional ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06V10/44G06V10/80G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08G01N21/88G01N21/84
CPCG06N3/08G01N21/8851G01N2021/8883G01N2021/8466G06N3/045G06F18/241G06F18/253
Inventor 许童羽冯帅于丰华赵冬雪周云成金忠煜刘子扬
Owner SHENYANG AGRI UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com