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

Hyperspectral image band noise removing method

A hyperspectral image and stripe noise technology, applied in the field of image processing, can solve problems such as easy to be smoothed and blurred images, and achieve the effect of improving image quality and not losing edges and details

Inactive Publication Date: 2014-12-03
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF2 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0017] The purpose of the present invention is to provide a hyperspectral image strip noise denoising method to solve the problem that the image details and edges are easily smoothed and the image becomes blurred by the existing denoising methods in the process of image denoising

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
  • Hyperspectral image band noise removing method
  • Hyperspectral image band noise removing method
  • Hyperspectral image band noise removing method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Embodiments of the invention are described in detail below, but the invention can be practiced in many different ways as defined and covered by the claims.

[0035] In the hyperspectral image denoising method in the prior art, the correlation between the bands of the hyperspectral image is not fully utilized, the information on the spectral dimension is not fully utilized and mined, and the wavelet transform cannot effectively describe the singularity of the curve. , the present invention proposes a new denoising method based on the second-generation curvelet transform and spectral dimension information weighting. characteristics to achieve the purpose of effectively removing band noise in hyperspectral images.

[0036] Because the hyperspectral image has obvious inter-spectral correlation, the closer the image bands are, the closer the high-frequency coefficient amplitude of its Curvelet transform is. The high-frequency coefficients are used to denoise the bands with ...

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 relates to a hyperspectral image band noise removing method which comprises the steps that 1. an image to be processed and two reference images are selected, wherein the noise of the two reference images is lower than the noise of the image to be processed, and the two reference images are placed on the two sides of the band of the image to be processed in the band range respectively; 2. the image to be processed and the reference images are subjected to Curvelet forward transformation, multi-scale multi-direction Curvelet transformation coefficients are obtained, and the Curvelet transformation coefficients comprise high-frequency coefficients and low-frequency coefficients; 3. the high-frequency coefficients of the two reference images are subjected to weighting processing, then first coefficients are obtained, and the first coefficients are used for replacing the high-frequency coefficients of the image to be processed; and 4. the Curvelet transformation coefficients obtained by replacing of the image to be processed are subjected to Curvelet inverse transformation, and accordingly noise removing images are obtained. The method is used for noise removing, edges and details are not lost during image noise removing, and image quality is improved.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a hyperspectral image band noise denoising method. Background technique [0002] Optical remote sensing images are usually polluted by noise during the acquisition and transmission process, which is not conducive to the accurate identification of image targets. Therefore, it is necessary to study the denoising technology of hyperspectral images. Traditional image noise removal or suppression methods can be divided into frequency domain filtering methods and spatial domain smoothing methods, the disadvantage of which is that a large amount of image information is lost. Wavelet transform is widely used in one-dimensional signal and two-dimensional signal denoising because of its ability to analyze signals in time and frequency domains, such as translation invariant wavelet denoising, matching pursuit denoising based on projection principle, and multi-dimensional signal denoising. W...

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
IPC IPC(8): G06T5/00
Inventor 宋冬梅刘斌马毅吴远龙崔建勇单新建沈晨任广波陈寿长邵红梅任鹏
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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