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

A Raman Spectral Image Unmixing Method Based on Non-negative Matrix Adjacency

A Raman spectroscopy, non-negative matrix technology, applied in the field of image processing, can solve problems such as unsatisfactory assumptions, and achieve the effect of improving noise resistance and stability

Active Publication Date: 2017-04-12
ZHEJIANG UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The limitation of this method is that there must be N-1 end members (N is the total number of end members), but in real high-mixed data sets, this assumption is not ideal

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 Raman Spectral Image Unmixing Method Based on Non-negative Matrix Adjacency
  • A Raman Spectral Image Unmixing Method Based on Non-negative Matrix Adjacency
  • A Raman Spectral Image Unmixing Method Based on Non-negative Matrix Adjacency

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Based on the rank 1-NMU algorithm, the invention proposes a non-negative matrix proximity algorithm for sparse graph relations.

[0033] The basic rank 1-NMU algorithm can be formulated as an optimization problem as shown in the following formula:

[0034]

[0035] in: is the F norm. matrix is the image data matrix, matrix u and matrix v are row vectors with length m and length n respectively.

[0036] Such as figure 1 As shown, the present invention is based on the Raman spectral image unmixing method that the non-negative matrix is ​​adjacent, comprises the following steps:

[0037] (1) Perform noise reduction and defluorescence processing on the Raman image to obtain processed image data.

[0038] (2) For the pixels in the image data, calculate the weight between the pixels according to the following formula:

[0039]

[0040] where: m i and m j are any two pixels in the image data, and σ is the kernel width of the thermal kernel function.

[0041] (...

Embodiment 2

[0065] Below we take the structural components of the tea plant cell wall as an example to describe the specific implementation of the method proposed by the present invention.

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 Raman spectral image unmixing method based on non-negative matrix proximity. The method aims at the absence of impure pixels in the Raman spectral image, and unknown ANC, ASC and endmembers in the Raman spectral unmixing. When the Raman spectral image satisfies the LMM model, by adding a variety of regularization factors such as sparseness to the non-negative matrix, the components of the mixed pixels and their corresponding abundances can be effectively obtained. Compared with other existing methods, the present invention has the following advantages: (1) the number of endmembers (constituent substances) is not required as prior knowledge; (2) an iterative strategy is adopted, and the obtained result has nothing to do with the number of endmembers; (3) The graph relationship and 1 / 2 norm are added to improve the noise resistance and stability of the algorithm.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a Raman spectral image unmixing method based on non-negative matrix proximity. Background technique [0002] Raman spectroscopy is a three-dimensional image, including ordinary two-dimensional plane image information and wavelength information. While imaging the spatial characteristics of the target, each spatial pixel is dispersed to form dozens or even hundreds of narrow bands for continuous spectral coverage. A Raman image is a three-dimensional Raman image composed of two-dimensional images corresponding to several wavelengths. [0003] Raman spectroscopy is widely used in industries such as cell engineering (detection of cell wall structural components) because of its unique spectral characteristics for different substances. However, most of the current Raman images are synthesized by mixing multiple different substances (endmembers). In order to analy...

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): G06T5/00
CPCG06V20/693G06V20/695G06V20/698
Inventor 邓水光徐亦飞李莹吴建尹建伟吴朝晖
Owner ZHEJIANG UNIV
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