Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

An online recognition method of seed cotton mulch film based on hyperspectral imaging and deep learning

A hyperspectral imaging and deep learning technology, applied in the field of online identification of seed cotton mulch film, can solve problems such as seed cotton mixed with mulch film, affecting textile quality and textile dyeing quality, etc., to reduce the impact of noise and ensure the effect of multi-channel input advantages

Active Publication Date: 2020-07-28
NANJING FORESTRY UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

As a major cotton-producing province in my country, Xinjiang has widely used plastic film mulching technology in cotton planting, and cotton picking production is highly mechanized. During the mechanical picking process, seed cotton is mixed with a large amount of plastic film. If it is not cleaned thoroughly, it will follow the processing link. Into the lint, it will definitely affect the quality of the textile and the dyeing quality of the textile

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
  • An online recognition method of seed cotton mulch film based on hyperspectral imaging and deep learning
  • An online recognition method of seed cotton mulch film based on hyperspectral imaging and deep learning
  • An online recognition method of seed cotton mulch film based on hyperspectral imaging and deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] Below in conjunction with specific examples, further illustrate the present invention, the examples are implemented under the premise of the technical solutions of the present invention, it should be understood that these examples are only used to illustrate the present invention and are not intended to limit the scope of the present invention.

[0042] The online recognition method of seed cotton mulch film based on hyperspectral imaging and deep learning of the present invention uses a hyperspectral imager to obtain the reflection spectrum image of seed cotton mulch film, and constructs a deep learning network composed of a stacked weighted autoencoder and an extreme learning machine optimized by particle swarm optimization. Spectral image online recognition, the steps of the method are as follows:

[0043](1) Use the SWIR series hyperspectral imager of Finnish SPECIM company to obtain the reflection spectrum image of the seed cotton mulch film at 1000nm-2500nm, 5.6nm ...

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 an on-line identification method of seed cotton mulch based on hyperspectral imaging and deep learning. The hyperspectral imager is used to obtain the reflection spectrum image of seed cotton mulch, and a deep learning network composed of a stacking weight autoencoder and a particle swarm optimized extreme learning machine is constructed. For online recognition of hyperspectral images, the present invention uses a network composed of stacked weighted autoencoders and extreme learning machines in deep learning to classify hyperspectral images of seed cotton mulch, and introduces a weighting mechanism in each layer of autoencoders to ensure multiple The channel input advantage reduces the impact of noise; the weights and biases of the extreme learning machine are randomly determined, which is prone to overfitting. The particle swarm optimization algorithm is used to optimize the weights and biases of the extreme learning machine to ensure the recognition speed At the same time, the classification accuracy is improved. The deep learning network composed of stacked weighted autoencoder and extreme learning machine can be used for online recognition of seed cotton mulch.

Description

technical field [0001] The invention belongs to the technical field of foreign fiber identification of seed cotton, and in particular relates to an online identification method of mulch film of seed cotton based on hyperspectral imaging and deep learning. Background technique [0002] my country is a big country of cotton production and consumption, and cotton processing and weaving play an important role in the national economy. As a major cotton-producing province in my country, Xinjiang has widely used plastic film mulching technology in cotton planting, and cotton picking production is highly mechanized. During the mechanical picking process, seed cotton is mixed with a large amount of plastic film. If it is not cleaned thoroughly, it will follow the processing link. If it enters the lint, it will definitely affect the quality of the textile and the dyeing quality of the textile. At present, the mulch fragments contained in machine-picked cotton have become the fundament...

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): G06K9/00G06K9/62G06N3/00G06N3/04G06N3/08
CPCG06N3/08G06N3/006G06V20/13G06N3/044G06N3/045G06F18/2411G06F18/214
Inventor 倪超张雄李振业
Owner NANJING FORESTRY 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
Eureka Blog
Learn More
PatSnap group products