Method for identifying plant leaf diseases by using GPCNNs and ELM

A technology for plant leaves and diseases, applied in the computer field, can solve the problems of extracting robust classification features, irregularities, complexities, etc., and achieve the effects of improving efficiency, reliability, and speeding up convergence.

Pending Publication Date: 2019-09-10
TIANJIN UNIV OF SCI & TECH +1
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the complex and irregular color, shape and texture of diseased leaf images, it is difficult to extract robust classification features from diseased leaf images for disease identification

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 identifying plant leaf diseases by using GPCNNs and ELM
  • Method for identifying plant leaf diseases by using GPCNNs and ELM
  • Method for identifying plant leaf diseases by using GPCNNs and ELM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0087] The feasibility and accuracy of the present invention are verified by experiments.

[0088] A database of apple diseased leaf images was constructed, including 400 diseased leaf images of 4 common diseases, namely Figure 7-1 variegated leaves, Figure 7-2 Brown spots (Brown spots), Figure 7-3 mosaic and Figure 7-4 Rust, 100 leaf images per class. All leaf images were collected from the Yangling Agricultural High-tech Industry Demonstration Zone in Shaanxi, and then shot with a Canon A640 digital camera with a resolution of 1200×1600. There are 100 leaf images in JPEG format for each disease, with obvious symptoms, different sizes, different directions, different illuminance, and a single background. The k-means clustering algorithm was used to segment diseased leaf images. Figure 7 Some original diseased leaf images and corresponding segmented color lesion images are shown.

[0089] CNNs models often require a large-scale image set to train their parameters, a...

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 plant leaf diseases by using GPCNNs and ELMs, which comprises the following three stages of learning multi-scale pyramid convergent features by using GPCNN, fusing extracted hierarchical features, and performing disease identification and classification. The method has the characteristics that (1) a global convergence layer is adopted to replace a full-connection layer, so that the network convergence speed is increased, and the network performance is improved; (2) compared with a traditional disease recognition method based on feature extraction, the method has the advantages that GPCNNs are utilized to automatically learn reliable features from the diseased leaf images, manual diseased leaf feature extraction is replaced, and reliability and efficiency are improved; and (3) compared with a traditional crop disease identification method based on deep learning, an ELM classifier is used for replacing a convolutional neural network (CNNs)to classify disease types, so that the identification performance is improved.

Description

technical field [0001] The invention relates to the field of computer technology, and more specifically relates to a method for identifying plant leaf diseases by using GPCNNs and ELM. Background technique [0002] At present, the traditional main method of detecting and diagnosing plant leaf diseases is to observe fruit trees with the naked eye through experts and farmers' professional technical level and years of experience, which is labor-intensive and time-consuming, and requires experts and farmers to continuously monitor the growth of fruits in the field. It is often easy to miss the best timing for prevention and treatment. With the development of machine learning, pattern recognition, image processing and image classification, many identification methods and technologies of plant diseases have been proposed and applied to automatic detection and identification of apple diseases. Sindhuja[2] established a fast, Effective and reliable health monitoring sensors. Altho...

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): G06K9/46G06K9/62G06N3/04
CPCG06V10/462G06N3/045G06F18/241
Inventor 张传雷任雪飞李建荣武大硕刘璞张善文
Owner TIANJIN UNIV OF SCI & TECH
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