A method for identifying paint using near-infrared hyperspectral images

A near-infrared hyperspectral and image recognition technology, which is applied in the field of identifying coatings using near-infrared hyperspectral images, can solve the problems of long-term, inability to quickly and reliably detect the quality consistency of coatings, and limited detection range. It takes time to achieve Short, non-destructive quality and consistency detection, enhanced absorption properties

Inactive Publication Date: 2017-12-05
CHINA UNIV OF MINING & TECH (BEIJING)
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method for identifying coatings using near-infrared hyperspectral remote sensing images to solve the technical problems that the detection of coating quality indicators takes a long time, the detection range is limited, and the quality consistency of coatings cannot be quickly and reliably detected during acceptance.

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
  • A method for identifying paint using near-infrared hyperspectral images
  • A method for identifying paint using near-infrared hyperspectral images
  • A method for identifying paint using near-infrared hyperspectral images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] Such as figure 2 Shown, the method for discriminating coating with near-infrared hyperspectral image of the present invention, specific following steps:

[0037] Step A1: Obtain near-infrared hyperspectral image information of the paint to be identified;

[0038] Step A101: performing image radiation correction and smoothing processing on the near-infrared hyperspectral image information;

[0039] Step A2: performing continuum removal processing on the near-infrared hyperspectral image information;

[0040] Step A3: Analyze the spectral characteristics of different quality paints of the same color under multiple color systems;

[0041] Step A4: Select characteristic bands according to spectral characteristics: any two of 1415nm, 1590nm, 1672nm, 1847nm, 1922nm, 2147nm, 2203nm, 2290nm and 2403nm;

[0042] Step A5: The formula for constructing the hyperspectral remote sensing ratio identification model of any two characteristic bands is as follows:

[0043]

[0044...

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 recognizing coating by means of near-infrared hyperspectral images. The method comprises the steps that near-infrared hyperspectral image information of a coating to be recognized is obtained; continuum removal treatment is performed on the near-infrared hyperspectral image information; spectral signatures of coatings of different qualities and the identical color under various color systems are analyzed; characteristic wave bands are selected according to the spectral signatures; hyperspectral remote sensing specific value recognition models of any two characteristic wave bands are constructed; distance testing is performed on each hyperspectral remote sensing specific value recognition model; the hyperspectral remote sensing specific value recognition model with the optimal coating quality recognition is screened out according to an inspection result. The method has the technical effects that coating quality detection can be efficiently and rapidly performed and the coating quality consistence can be rapidly and reliably detected during decoration inspection and acceptance.

Description

technical field [0001] The invention relates to a method for recognizing paint by using a near-infrared hyperspectral image. Background technique [0002] There are many types of coatings on the market, with different models and qualities. Coatings are mainly composed of bonding materials, pigments, fillers, thinners, etc., and are manufactured through certain processes. For example, the content of titanium dioxide (TiO2) may significantly affect the performance of coatings. The corresponding contrast ratio is an important indicator for coating testing. For paints of the same color but different brands or different qualities, they have very similar spectral characteristics in the visible light range, making it difficult for the naked eye to directly distinguish them. This provides the possibility for the coating products to be confused with real ones and shoddy. There are many detection indicators for coating quality, and it takes a long time to detect these indicators wit...

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): G01N21/359
CPCG01N21/359
Inventor 蒋金豹乔小军何汝艳
Owner CHINA UNIV OF MINING & TECH (BEIJING)
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