Pest Image Recognition Method Based on Bayesian Width Residual Neural Network

A neural network and image recognition technology, applied in neural learning methods, biological neural network models, image analysis, etc., can solve problems such as degradation, gradient explosion, and gradient disappearance, achieve high accuracy, improve accuracy, and eliminate salt and pepper noise Effect

Active Publication Date: 2021-06-04
JILIN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problems existing in the existing deep learning network, such as gradient disappearance or gradient explosion, degradation phenomenon, and overfitting and other problems

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
  • Pest Image Recognition Method Based on Bayesian Width Residual Neural Network
  • Pest Image Recognition Method Based on Bayesian Width Residual Neural Network
  • Pest Image Recognition Method Based on Bayesian Width Residual Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] Step 1: Preprocessing the pest image recognition training data set, converting the color pest image into a grayscale image, reducing the influence of the background on the image. Use Rich-Edge to perform edge detection on the grayscale image of pests. Normalize the scale of the image on the data set, and uniformly process it into an image with a size of 224*224. Set aside known samples {X i ,Y i} to calculate the probability distribution.

[0025] (1) Use the psychological formula: Gray=0.299*R+0.587*G+0.114*B to perform grayscale processing on the color image of the pest, and convert the RGB image into a grayscale image.

[0026] (2) Add some salt and pepper noise to the input image f 1 (x, y).

[0027] (3) Use the median filter to remove the salt and pepper noise on the image in (2), use the sliding window method to detect the image, and obtain the output image f 2 (x,y).

[0028] (4) Use the Sobel edge detection algorithm to detect the pest image f 1(x, y) fo...

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 pest image recognition method based on a Bayesian width residual neural network. The method comprises the following steps: step 1, preprocessing the pest image recognition training data set, using a rich edge detection algorithm (Rich-Edge) Pest edge detection is performed on the grayscale image. Step 2. Construct a Bayesian Wide-Residual Network (BWResNet). Step 3: Input the pest edge image obtained in Step 1 into the BWResNet constructed in Step 2. Use the pest edge image training set obtained in step 1 to obtain the total error function of BWResNet. Step 4: Use the error function obtained in Step 3 to train the network. Here we propose the block-conjugate (Block‑cg) algorithm to train the network. Step 5. Update hyperparameters according to the optimized network in step 4. Step 6: Repeat steps 4 and 5 to obtain the final network, and the classification accuracy rate obtained after inputting the verification set of pest images into the network is higher.

Description

technical field [0001] The present invention involves the use of Bayesian methods, residual neural networks, and pest image recognition. Background technique [0002] Plant diseases and insect pests are one of the three natural disasters, and they are also the main problems faced by China's agricultural development. There are many kinds of pests with high similarity in shape, and it is difficult to efficiently and accurately identify them with the naked eye. With the rapid development of computer vision technology and theory, image classification technology has been applied to many aspects. In agriculture, we can also use image classification technology to classify plant pests. This technology has the advantages of high efficiency, speed, and high accuracy compared with traditional human-eye recognition. [0003] In recent years, this image classification technology for pest image recognition has been widely researched and applied. The research method mainly involves 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): G06T7/00G06T5/00G06T7/13G06N3/04G06N3/08
CPCG06N3/08G06T5/009G06T7/0002G06T7/13G06T2207/20192G06T2207/30188G06T2207/20081G06T2207/20032G06N3/045
Inventor 王生生赵慧颖
Owner JILIN UNIV
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