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

Fresh jujube wormhole detection method based on hyperspectral image convolutional neural network

A convolutional neural network, hyperspectral image technology, applied in neural learning methods, biological neural network models, image enhancement, etc., to achieve the effect of efficient recognition and improved detection accuracy

Active Publication Date: 2021-08-06
马翔
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of this, the purpose of the present invention is to address the deficiencies in the prior art, to provide a method for detecting insect eyes in fresh jujube based on hyperspectral image convolutional neural network, and to solve the problems caused by the surface color of fresh jujube in the existing computer vision detection process of fresh jujube. The problem of misjudgment caused by disturbances such as blocks, spots, fruit stems, etc.

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
  • Fresh jujube wormhole detection method based on hyperspectral image convolutional neural network
  • Fresh jujube wormhole detection method based on hyperspectral image convolutional neural network
  • Fresh jujube wormhole detection method based on hyperspectral image convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] A hyperspectral image convolutional neural network-based detection method for fresh jujube insect eyes, using a convolutional neural network model that can be used for detection of fresh jujube insect eyes, the construction method of the convolutional neural network model that can be used for fresh jujube eye detection includes: The steps are as follows: S1, collecting sample hyperspectral image data; S2, extracting the optimal characteristic wavelength; S3, data preprocessing; S4, using the training sample set to train the convolutional neural network model; S5, using the model to classify and verify the data set.

Embodiment 2

[0052] The difference between this embodiment and Embodiment 1 is that: S1 collecting sample hyperspectral image data includes the following steps: S1.1, select 100 normal fresh jujubes and 100 worm-eyed fresh jujubes as samples; S1.2, set hyperspectral The exposure time of the image acquisition equipment, the speed of the mobile platform, and the length of the scanning line are used to shoot the sample; S1.3, the original hyperspectral image collected is corrected by the black and white plate, and the correction equation is as in formula (1):

[0053]

[0054] The image of the whiteboard is W (the reflectivity is 99%), and the image of the collected blackboard file is D (the reflectivity is close to 0%). The original image I is corrected, and R is the corrected hyperspectral image.

Embodiment 3

[0056] The difference between this embodiment and Example 1 is that the extraction of the optimal characteristic wavelength in S2 is based on the spectral characteristics of the fresh jujube worm eye, and a fast extraction algorithm for the optimal characteristic wavelength based on the particle swarm optimization algorithm is proposed, which specifically includes the following steps: S2. 1. Extract the mean value of 3*3 pixel hyperspectral data from the full-spectrum fresh jujube insect eye area from the sample set to form a matrix A

[0057]

[0058] And the average value of 3*3 pixel hyperspectral data in the normal area of ​​​​fresh jujube constitutes a matrix C

[0059]

[0060] where a nm is the mean value of the hyperspectral data of the m-band worm-eye area of ​​the n-th sample, c nm is the mean value of the hyperspectral data in the normal region of the m-th band of the n-th sample;

[0061] S2.2, design the particle swarm optimization algorithm fitness functi...

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 fresh jujube wormhole detection method based on a hyperspectral image convolutional neural network, and the method employs a convolutional neural network model which can be used for the detection of fresh jujube wormholes for detection, and the construction method of the convolutional neural network model comprises the following steps: S1, collecting the data of a hyperspectral image of a sample; S2, extracting an optimal characteristic wavelength; S3, performing data preprocessing; S4, training a convolutional neural network model by using the training sample set; and S5, performing classification verification on the data set by using the model. According to the fresh jujube wormhole detection method based on the hyperspectral image convolutional neural network, the detection of the fresh jujube wormhole can be realized without manual intervention by processing the hyperspectral image data under the selected characteristic wavelength, the detection precision of the network model on the fresh jujube wormhole is improved. The method solves the problem of misjudgment caused by interference of color blocks, spots, fruit stems and the like on the surfaces of the fresh jujubes in the existing computer vision detection process of the fresh jujubes, and has the characteristics of simplicity, feasibility and high recognition efficiency.

Description

technical field [0001] The invention relates to the technical field of machine vision, in particular to a method for detecting insect eyes in fresh dates based on a hyperspectral image convolutional neural network. Background technique [0002] During the growth process of fresh jujube, it will be eroded by various insect pests, resulting in the appearance of insect eyes and internal damage on the surface of fresh jujube, which seriously affects storage and sales. Traditional sorting methods are mostly manual, with low efficiency and poor accuracy, and cannot meet the needs of large-scale storage and sales. Therefore, it is urgent to develop a fast, efficient and non-destructive detection method. Currently, computer vision is used to detect insect eyes in fresh jujube, which is easily interfered by color blocks, spots, fruit stems, etc. on the entire surface of fresh jujube, and has the problem of low accuracy. [0003] In the prior art, the main methods for detecting worm...

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): G06T7/00G06T7/136G06T7/11G06N3/00G06N3/04G06N3/08
CPCG06T7/0002G06T7/136G06T7/11G06N3/006G06N3/08G06T2207/20081G06T2207/20104G06N3/048G06N3/045
Inventor 马翔施健周芳媛
Owner 马翔
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