Maize leaf disease identification method based on convolutional neural network model GoogleNet

A convolutional neural network and disease identification technology, applied in the field of image recognition, can solve the problems of low identification accuracy of disease types and many network model parameters, and achieve the effect of improving identification accuracy and loss

Inactive Publication Date: 2018-04-20
NORTHEAST AGRICULTURAL UNIVERSITY
View PDF2 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the shortcomings of more network model parameters and low accuracy of disease type identification in the...

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
  • Maize leaf disease identification method based on convolutional neural network model GoogleNet
  • Maize leaf disease identification method based on convolutional neural network model GoogleNet
  • Maize leaf disease identification method based on convolutional neural network model GoogleNet

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0017] Specific implementation mode one: as figure 1 As shown, the corn leaf disease identification method based on the convolutional neural network model GoogleNet includes the following steps:

[0018] Step 1: Collect the corn leaf image data set, expand the collected corn leaf image data set, and then preprocess the image data set; the preprocessed image data set is divided into a training set and a test set;

[0019] Step 2: Input the training set and test set preprocessed in step 1 into the convolutional neural network model GoogleNet, use the first classifier for training and testing, adjust the parameters of the convolutional neural network model GoogleNet, and obtain an optimized convolutional neural network Network model GoogleNet (optimal top-1 accuracy and minimum model loss);

[0020] Step 3: Input the test set processed in step 1 into the optimized convolutional neural network model GoogleNet obtained in step 2 to complete the identification of corn leaf diseases...

specific Embodiment approach 2

[0022] Embodiment 2: The difference between this embodiment and Embodiment 1 is that the specific process of expanding the collected corn leaf image data set in the step 1 is as follows:

[0023] Rotate the images in the corn leaf image dataset by 90°, 180°, and 270° (each image is rotated by 90°, 180°, and 270°, and one image becomes four images after rotation), and the The rotated image is mirrored, and the center of the mirrored image is divided according to the same size; the rotated, mirrored and segmented images are converted into grayscale images in turn (the corn leaf image data set processed by the above steps Part of the image is converted to grayscale).

[0024] Other steps and parameters are the same as those in Embodiment 1.

specific Embodiment approach 3

[0025] Embodiment 3: The difference between this embodiment and Embodiment 1 or 2 is that: the specific process of preprocessing the image data set in the step 1 is:

[0026] Use the Python language to normalize the image name, format and size in the input data set based on OpenCv, and mark the normalized image categories. The image categories include 8 leaf disease categories and 1 healthy leaf category. , 8 leaf disease categories are large spot, small spot, rust, brown spot, round spot, Curvularia leaf spot, gray spot and dwarf mosaic.

[0027] Other steps and parameters are the same as those in Embodiment 1 or Embodiment 2.

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 provides a maize leaf disease identification method, in particular to a maize leaf disease identification method based on a convolutional neural network model GoogleNet. The invention aims at solving the defects that the existing maize leaf disease identification technology is more in network model parameters and low in disease type identification accuracy. The maize leaf disease identification method comprises the following steps: 1, collecting a maize leaf image data set, expanding the collected maize leaf image data set, and then pre-processing image data set, wherein the pre-processed image data set is divided into a training set and a test set; 2, inputting the training set and the test set into the convolutional neural network model GoogleNet, and training and testing by using a first classifier so as to obtain an optimized convolutional neural network model GoogleNet; 3, inputting the test set into the optimized convolutional neural network model GoogleNet so as tocomplete the identification of types of maize leaf diseases. The maize leaf disease identification method is applied to the technical field of image identification.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a corn leaf disease recognition method based on a convolutional neural network model GoogleNet. Background technique [0002] Corn is an important food crop and feed crop in my country. In recent years, due to changes in cultivation system, variation of pathogenic bacteria species, and unsound plant health care measures, corn diseases have occurred and the degree of damage has increased year by year, and the types have also increased year by year. Common corn leaf diseases include: large spot disease, small spot disease , rust, round spot, Curvularia leaf spot, dwarf mosaic, etc. The current disease classification and identification work in our country is mainly done by a small number of plant protection experts and agricultural technicians. However, there are many types of diseases, and each plant protection expert can only identify some of the diseases. [0003] In ...

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
IPC IPC(8): G06T7/00G06T7/10G06T3/60G06K9/46G01N21/88G06N3/04
CPCG06T3/60G06T7/0002G06T7/10G01N21/8851G06T2207/20084G06T2207/30188G01N2021/8466G01N2021/8887G06V10/40G06N3/045
Inventor 张喜海乔岳孟繁锋张明明许绥佳李想赵语杭范成国宋伟先许永花
Owner NORTHEAST AGRICULTURAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap