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

Image fusion method based on NSCT (Non Subsampled Contourlet Transform) and sparse representation

An image fusion and sparse representation technology, applied in the field of image fusion, can solve the problems of unfavorable extraction of useful information fusion, poor sparsity, etc.

Inactive Publication Date: 2013-03-13
NORTHWESTERN POLYTECHNICAL UNIV
View PDF2 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the shortage of low-frequency sub-band coefficients containing the main energy of the image after NSCT change in the prior art, which is not conducive to extracting useful information for fusion, the present invention provides an image fusion method based on NSCT and sparse representation. Poor low-frequency sub-band coefficient learning dictionary, using sparse representation to extract the common and unique coefficients of the source image to achieve the purpose of improving the sparsity of low-frequency sub-bands, and then adaptively adjust the weight fusion according to the activity level of the unique coefficients; for higher sparsity The high-frequency direction sub-band coefficients of the same scale are fused with the absolute value of the direction sub-band and the method of taking the maximum to capture the salient features in the source image, and finally improve the fusion effect

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
  • Image fusion method based on NSCT (Non Subsampled Contourlet Transform) and sparse representation
  • Image fusion method based on NSCT (Non Subsampled Contourlet Transform) and sparse representation
  • Image fusion method based on NSCT (Non Subsampled Contourlet Transform) and sparse representation

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0081] Example 1. Using sparse representation to improve the sparsity of NSCT low-frequency subbands and extract the unique and common features of the source image

[0082] 1 The dictionary learning steps in this example are as follows:

[0083] (1.1) Use NSCT to decompose infrared and visible light source images respectively, using "9-7" tower decomposition and "c-d" direction filter bank, and the number of directions taken by the high-frequency layer is 2 in turn 4 ,2 3 ,2 2 ,2 2 ;

[0084] (1.2) Initialize dictionary D∈R 64×256 ;

[0085] (1.3) For the low-frequency subband coefficients, the sliding window with a step size of 1 and a size of 8×8 extracts blocks from the upper left to the lower right, and then straightens the blocks and arranges them in sequence to form a matrix. The infrared low-frequency subband matrix is ​​recorded for V 1 ; Visible light low-frequency sub-band matrix is ​​denoted as V 2 ;

[0086] (1.4) Train a dictionary D with K-SVD algorith...

example 2

[0101] Example 2. The image fusion example of the present invention

[0102] Combine the method proposed by the invention with the traditional DWT-based image fusion method and the current NSCT-based image fusion method with superior performance 错误!未找到引用源。 And the image fusion method SOMP based on sparse representation 错误!未找到引用源。 and the JSR method 错误!未找到引用源。 Compare. The first two methods are transform-domain based methods, and the latter two are fusion methods based on sparse representations in the image domain. In the experiment, 240×320 and aligned infrared and visible light images were used. The wavelet type decomposed by DWT was 3rd-level db4 wavelet. The NSCT parameter setting and literature were wrong! No reference source was found. The same, that is, "9-7" tower decomposition and "c-d" direction filter bank, the number of directions taken by the high-frequency layer is 2 in turn 4 ,2 3 ,2 2 ,2 2 . The dictionary size of the sparse representation is all 64×256,...

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 an image fusion method based on NSCT (Non Subsampled Contourlet Transform) and sparse representation. According to the image fusion method, a learning dictionary is provided for the coefficients of a low-frequency sub-band lower in sparseness, and the common and special coefficients of a source image are extracted by virtue of spare representation, so that the purpose of improving the sparseness of the low-frequency sub-band can be realized; the weight fusion are horizontally adjusted in a self-adoption manner according to the movement of the special coefficient; and the coefficient of a high-frequency directional sub-band higher in sparseness is fused through absolute value of the directional sub-band with the same dimension by a maximizing method, thus the marked features of the source image can be captured, and as a result, the fusion effect is finally improved.

Description

technical field [0001] The invention relates to an image fusion method. Background technique [0002] In recent years, the Non-Subsampled Contourlet Transform (NSCT) based on Non-Subsampled Contourlet Transform (NSCT) has the image representation ability of translation invariance, multi-resolution, multi-direction and anisotropy, and can effectively overcome the inability of traditional wavelet transform to handle 2D Or higher Vitch heterogeneity problems, successfully used in the field of image fusion and achieved better fusion results. However, in the image fusion problem, we hope that the extracted image representation coefficients have excellent sparsity and feature retention, so that only a small number of coefficients need to be fused to obtain better fusion results. However, the low-frequency sub-band coefficients of the image obtained by NSCT transformation are very limited, that is, the low-frequency sub-band information of the image cannot be sparsely represented....

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): G06T5/50
Inventor 彭进业王珺何贵青阎昆夏召强冯晓毅蒋晓悦吴俊李会方谢红梅杨雨奇
Owner NORTHWESTERN POLYTECHNICAL 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