Hyperspectral model transfer method of citrus canker

A technology for citrus canker and model transfer, which is applied in the field of citrus canker hyperspectral model transfer, can solve the problems of being easily affected by meteorological factors and low accuracy, so as to improve universality, improve detection accuracy, and improve modeling efficiency. Effect

Inactive Publication Date: 2016-09-21
ZHEJIANG UNIV
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with the laboratory hyperspectral imaging platform, the quality of the hyperspectral image collecte

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
  • Hyperspectral model transfer method of citrus canker
  • Hyperspectral model transfer method of citrus canker
  • Hyperspectral model transfer method of citrus canker

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0029] A total of 106 samples were collected from 58 healthy citrus samples and 48 samples infected with canker in the green fruit stage. The laboratory hyperspectral imaging platform was applied respectively, mainly including CCD camera (C8484-05, Hamamatsu Photonics, Hamamatsu City, Japan), imaging spectrometer (ImSpector V10E, Spectral Imaging Ltd., Oulu, Finland), line light source (Fiber-Lite DC950 , Dolan Jenner Industries Inc., Boxborough, MA), electronically controlled mobile platform, camera obscura and computer, and a portable hyperspectral imager (SOC710VP, Surface Optics Corporation, San Diego, CA) to collect hyperspectral images.

[0030] Such as figure 1 As shown, the specific delivery process of the citrus canker hyperspectral model is as follows, including the following steps:

[0031] 1) Use the source machine M1 and the target machine M2 to collect hyperspectral images of citrus (106 samples); extract the average spectral reflectance of the region of interes...

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 relates to a hyperspectral model transfer method of citrus canker. The method includes acquiring hyperspectral images of citrus by using a source machine M1 and an object machine M2, getting a characteristic wave band of the hyperspectral images of M1 by using genetic partial least squares, and establishing a discrimination model of least squares support vector machine. The functional relation of the hyperspectral images acquired by two machines is established by using piecewise direct standardization, the standardized hyperspectral images of M2 is input into the discrimination model of least squares support vector machine, and the prediction set recognition rate of the model is increased from 26% before standardization to 97%. The method in the invention can be used for transferring hyperspectral model of citrus canker, is beneficial to establish the steady hyperspectral model of citrus canker, and can improve the detection precision of citrus canker.

Description

technical field [0001] The invention relates to the field of detection of citrus canker, in particular to a method for transmitting a hyperspectral model of citrus canker. Background technique [0002] Citrus canker (citrus canker) is a major quarantine disease that affects the development of the global citrus planting industry, mainly harming leaves and fruits. The germs spread through media such as rainwater and seedlings, and invade through the host's stomata, lenticels and wounds. Symptoms of diseased fruit and diseased leaves are similar. In the early stage of infection, the disease spots are small yellow or dark yellow spots; At present, most of the research is focused on the prevention and detection of this disease, while the removal of citrus fruits with canker lesions is mainly through manual sorting, which has high requirements for workers, low efficiency and poor accuracy. With the increasingly advanced image processing technology and the reduction of computer h...

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): G01N21/25
CPCG01N21/25G01N2021/1765
Inventor 岑海燕翁海勇何勇
Owner ZHEJIANG 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