High spectral image waveband selection method based on global optimal clustering

A hyperspectral image, global optimal technology, applied in the field of image processing, can solve the problem of reducing the effect of dimensionality reduction, uncertainty, etc., to achieve high classification accuracy, reduce the probability of being selected, and reduce the solution space.

Active Publication Date: 2017-09-29
NORTHWESTERN POLYTECHNICAL UNIV
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method proposes a clustering method for band selection, but its shortcomings are: first, it is an uncertain method, although it can reduce the difference between the bands within the cluster, it cannot measure how far the difference is reduced. secondly, in the presence of noise bands, due to the large difference between noise bands and other bands, it is easier to be classified into a single-band cluster, making noise bands easier to be selected, thus reducing the The effect of dimensionality reduction

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
  • High spectral image waveband selection method based on global optimal clustering
  • High spectral image waveband selection method based on global optimal clustering
  • High spectral image waveband selection method based on global optimal clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The present invention will be further described below in conjunction with the accompanying drawings and embodiments, and the present invention includes but not limited to the following embodiments.

[0015] Such as figure 1 As shown, a hyperspectral image band selection method based on global optimal clustering of the present invention, its implementation steps are as follows:

[0016] Step 1: Normalization processing, that is, according to p n =(p o -M 2 ) / (M 1 -M 2 ) to normalize the hyperspectral image, where, p n is the pixel value of the normalized image, p o is the pixel value of the original hyperspectral image, M 1 is the maximum value of the pixel value in the original hyperspectral image, M 2 is the minimum value of the pixel value in the original hyperspectral image;

[0017] Step 2: According to the physical meaning of the hyperspectral image, that is, adjacent bands have greater similarity, and the bands in a cluster should be continuous. According...

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 provides a high spectral image waveband selection method based on global optimal clustering. The method comprises steps that a ratio of difference between clusters and difference in clusters is taken as a to-be-optimized target function, a bisection method and a dynamic programming method are utilized to acquire the global optimal clustering result, through minimizing a wave band linearity reconstruction error, representative high spectral image waveband selection can be lastly accomplished. The method is advantaged in that high spectral image waveband selection is carried out, selection probability of noise wave bands can be reduced, and higher classification precision can be acquired.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a hyperspectral image band selection method based on global optimal clustering. Background technique [0002] Hyperspectral images contain rich spectral information, and can still have a good recognition effect when the ground objects have only slight differences. However, for hyperspectral images, a large amount of spectral information often brings redundancy of information and excessive calculation. Band selection, as a dimensionality reduction method for hyperspectral images, has been widely used in recent years. Document "A. -Usó Martinez-Uso, F. Pla, J.M. Sotoca and P. -Sevilla, "Clustering-Based Hyperspectral Band Selection Using Information Measures," in IEEETransactions on Geoscience and Remote Sensing, pp.4158-4171.2007."A clustering-based band selection method is proposed, through the method of hierarchical clustering, Based on some metrics of...

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): G06K9/62
CPCG06F18/23G06F18/2411
Inventor 王琦李学龙张发弘
Owner NORTHWESTERN POLYTECHNICAL 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