A deep learning-based image recognition method for leaf diseases of medicinal plants

A technology of medicinal plants and deep learning, applied in neural learning methods, image enhancement, image data processing, etc., can solve the problems of small amount of sample data, low recognition accuracy, and large number of convolution kernel parameters

Active Publication Date: 2022-07-08
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The background technology is shooting and sampling under laboratory conditions, and due to the small amount of sample data, it is easy to lead to low model generalization ability
[0009] The second method adopts the basic structure of CNN, which is easy to lead to overfitting, and the number of convolution kernel parameters is too large, so the training efficiency is low; in addition, the training samples are all taken from the laboratory environment, and for pictures with complex backgrounds taken in the field, the recognition low accuracy

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
  • A deep learning-based image recognition method for leaf diseases of medicinal plants
  • A deep learning-based image recognition method for leaf diseases of medicinal plants
  • A deep learning-based image recognition method for leaf diseases of medicinal plants

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] Please refer to figure 1 , figure 2 , image 3 and Figure 4 , an embodiment of the present invention provides a deep learning-based image recognition method for leaf diseases of medicinal plants, comprising the following steps:

[0045] S1. Collect several images of leaf diseases of medicinal plants, and rename each image in the form of plant name + disease name;

[0046] S2, performing enhancement processing on the renamed image of leaf diseases of medicinal plants;

[0047] S3, image data preprocessing, and uniformly adjust the size of the images of leaf diseases of medicinal plants after each enhancement processing to 299x299;

[0048] S4. Train the deep CNN model. The deep CNN model includes the convolution pooling network in series, the Inception-I network, the average pooling network, the Dropout layer and the Softmax layer. The last two convolution layers of the convolution pooling network in series are Depthwise separable convolutional layers, including ran...

Embodiment 2

[0064] For step S1 in Example 1, images of leaf diseases of medicinal plants are collected by a digital camera, and there are 500 images of leaf diseases of medicinal plants in total.

Embodiment 3

[0066] For step S2 in Embodiment 1, the enhancement processing on the leaf disease image includes image rotation, mirror symmetry, brightness adjustment and PCA jitter.

[0067] In this embodiment, image rotation refers to rotating all pixels of the image by an angle of 0-360 degrees around the center of the image; mirror symmetry refers to using the mid-perpendicular line in the image as the axis, and exchanging all the pixels in the image is horizontal symmetry . Set the coordinates of any point P in the image to be (x0, y0), and the coordinates after rotating θ degrees counterclockwise are (x, y), then the calculation formula of the polar coordinates before and after the rotation is as follows:

[0068] x0=γcosα, y0=γsinα

[0069] x=γcos(α+θ), y=γsin(α+θ)

[0070] Where γ represents the polar diameter of point P; α represents the polar angle of point P.

[0071] In this embodiment, the brightness adjustment refers to adjusting the sharpness value, brightness value and co...

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 identifying images of leaf diseases of medicinal plants based on deep learning, and relates to the technical field of protection of leaf diseases of medicinal plants. The method includes collecting several images of leaf diseases of medicinal plants; The image is enhanced; the size of each enhanced image of leaf diseases of medicinal plants is uniformly adjusted to 299x299; the deep CNN model is trained, and the deep CNN model includes convolution pooling network in series, Inception‑I network, average pooling network, Dropout layer and Softmax layer, the last two convolutional layers of the convolutional pooling network in series are depthwise separable convolutional layers, and the Inception‑I network includes a random pooling layer; The leaf disease images of each medicinal plant are identified, and the identification result is the type of disease on the leaf of each medicinal plant, and the leaf disease of each medicinal plant is classified based on the identification result. The identification method can effectively assist planters in diagnosing diseases and improve diagnosis efficiency.

Description

technical field [0001] The invention relates to the technical field of medicinal plant leaf disease protection, in particular to a deep learning-based image recognition method for medicinal plant leaf diseases. Background technique [0002] During the growth of medicinal plants, there are many opportunities for leaves to come into contact with pathogens, and they are also greatly affected by external environmental conditions. According to the statistics of popular science literature, there are 394 kinds of diseases in 61 kinds of medicinal plants, among which 220 kinds of leaf diseases, accounting for 58.1%. The common types of leaf diseases are downy mildew, white rust, powdery mildew, rust, leaf spot, leaf blight and so on. [0003] In order to minimize the impact of pests and diseases on the growth process of medicinal plants, pests and diseases should be detected as early as possible, so that appropriate treatment methods can be selected at the right time to prevent the...

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 Patents(China)
IPC IPC(8): G06V20/10G06V10/32G06V10/764G06V10/82G06K9/62G06N3/04G06N3/08G06T3/60G06T5/00
CPCG06N3/084G06T3/60G06T5/007G06V20/00G06V10/32G06N3/045G06F18/2431G06F18/2415G06F18/241
Inventor 刘勇国李巧勤杨尚明蔡茁李杨何家欢
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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