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

Potato disease identification method based on convolutional neural network

A convolutional neural network and disease identification technology, which is applied in the field of potato disease identification based on convolutional neural network, can solve the problems of complex models, time-consuming manual detection, labor-intensive identification accuracy, etc., and achieve good identification effect, high accuracy, and The effect of extending the range of application

Pending Publication Date: 2021-05-04
YUNNAN AGRICULTURAL UNIVERSITY
View PDF15 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to solve the above-mentioned problems in the prior art, the present invention provides a potato disease recognition method based on convolutional neural network, aiming to solve the problems of time-consuming and laborious traditional manual detection, low recognition accuracy and complex models of existing machine vision methods.

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
  • Potato disease identification method based on convolutional neural network
  • Potato disease identification method based on convolutional neural network
  • Potato disease identification method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0025] see figure 1 , a potato disease identification method based on a convolutional neural network, comprising the following steps:

[0026] Step 1: Use a digital camera or video camera to collect images of potato leaf diseases in the potato field, and then label the images by disease category to obtain a potato disease dataset with sample labels;

[0027] The original potato disease data set described in step 1 includes a certain number of common potato diseases such as late blight, early blight, and anthracnose.

[0028] see figure 2 ,

[0029] Step 2: Perform data augmentation operations on the original disease dataset with sample labels obtained in Step 1, and perform image data augmentation on each image in the original dataset through random inversion, angle transformation, and other operations;

[0030] 1) Classify the potato disease dat...

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 potato disease identification method based on a convolutional neural network. The method comprises the steps of constructing a potato disease data set for the training of the convolutional neural network (CNN) through employing an image enhancement method, carrying out preprocessing of a collected potato disease image through employing a median filtering method, an image standardization method and the like, and finally, constructing a disease identification classifier based on the convolutional neural network by using the potato disease and insect pest data set, and loading pre-training model parameters by using a transfer learning algorithm to carry out model training. The method can quickly and accurately realize the identification of various common diseases of potatoes.

Description

technical field [0001] The invention relates to the technical field of disease and insect pest identification, in particular to a potato disease identification method based on a convolutional neural network. Background technique [0002] my country is the largest producer of potatoes in the world, and the potato planting area and output account for about 1 / 4 of the world. In recent years, with the increase of people's demand for coarse grains and the improvement of potato processing technology, the scale and area of ​​potato planting have continued to expand. Potato diseases have also increased year by year, becoming one of the main factors limiting the high and high yield of potatoes, and seriously affecting the development of the potato industry. In order to reduce the impact of potato diseases on potato yield, timely and accurate judgment of the disease type is undoubtedly the key. At present, the detection of potato diseases is mainly judged by manual visual inspection...

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): G06K9/00G06K9/40G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/188G06V10/30G06N3/047G06N3/045G06F18/214
Inventor 杨琳琳徐振南胡益嘉王杨王建坤赵旭东
Owner YUNNAN AGRICULTURAL UNIVERSITY
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