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

Clustering optimization method for mixed pigment information unmixing

An optimization method and pigment technology, applied in color/spectral characteristic measurement, instrument, character and pattern recognition, etc., can solve problems such as unstable convergence of unmixing results, solve unstable or even non-converging unmixing results, and improve accuracy Effect

Active Publication Date: 2020-04-14
XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the FastICA algorithm is sensitive to the initial value of the unmixing matrix, which may easily lead to unstable convergence of the unmixing results.

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
  • Clustering optimization method for mixed pigment information unmixing
  • Clustering optimization method for mixed pigment information unmixing
  • Clustering optimization method for mixed pigment information unmixing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] This embodiment provides a clustering optimization method for mixed pigment information unmixing, including the following steps:

[0041] Step 1, making a single pigment color block and mixed pigment color blocks with different concentration ratios;

[0042] Step 2, using the spectral reflectance acquisition system to obtain the reflective spectral information data of the pigment color block;

[0043] Step 3: Use the fuzzy C-means clustering algorithm (also known as FC-FastICA algorithm) to reduce the dimensionality of the spectral characteristics of a single pigment spectral information, and use the clustering results as the initial value of the unmixing matrix; substitute into the Newton iterative formula of the fast independent component analysis algorithm The unmixing matrix is ​​calculated, and the unmixing identification of the spectral information of the mixed pigment is completed.

[0044] In step one, the production process of the mineral pigment block is:

[0...

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 clustering optimization method for mixed pigment information unmixing. The clustering optimization method comprises the following steps: firstly, making a single pigment color block and mixed pigment color blocks with different concentration ratios; acquiring reflection spectrum information data of the pigment color block by using a spectral reflectivity acquisition system; performing spectral feature dimension reduction on single pigment spectral information by using a fuzzy C-means clustering algorithm, and taking a clustering result as the initial value of the unmixing matrix; substituting into the Newton iteration formula of a rapid independent component analysis algorithm to calculate the unmixing matrix to complete unmixing identification of the spectral information of the mixed pigment. According to the method, the unmixing precision can be improved, and the unmixing requirement of the mixed pigment is met.

Description

technical field [0001] The invention belongs to the field of digital image processing, and in particular relates to a cluster optimization method for unmixing mixed pigment information. Background technique [0002] In ancient murals, different pigments were mixed and used. The correct detection and identification of pigments is an important prerequisite for cultural relic restorers to restore murals, and it is also an important research content for digital virtual restoration of cultural relics. In recent years, most of the research on mural paints is aimed at the identification of single pigments, and less analysis is made on mixed pigments. Using reflectance spectroscopy to identify and analyze pigments can not only obtain accurate chromaticity information, but also has the advantages of non-destructive testing, which can avoid secondary damage to murals caused by traditional testing methods. It has become the first choice for many domestic and foreign researchers to cond...

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): G06K9/62G01N21/25
CPCG01N21/25G06F18/23Y02P90/30
Inventor 王慧琴杨蕾王可
Owner XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY
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

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