Supplementation mechanism and PCNN-based NSCT domain image fusion method

An image fusion, image technology, applied in image enhancement, image analysis, image data processing and other directions, can solve problems such as image distortion

Active Publication Date: 2017-09-22
NORTHWESTERN POLYTECHNICAL UNIV +1
View PDF4 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the deficiencies of image distortion in existing NSCT domain image fusion method

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
  • Supplementation mechanism and PCNN-based NSCT domain image fusion method
  • Supplementation mechanism and PCNN-based NSCT domain image fusion method
  • Supplementation mechanism and PCNN-based NSCT domain image fusion method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0071] refer to Figure 1-4 . The present invention is based on supplementary mechanism and the NSCT domain image fusion method of PCNN concrete steps are as follows:

[0072] The hardware environment used for implementation is: the experimental environment is CPU Intel Core i5-5200U@2.20GHz, memory is 4GB, and MATLAB R2014a is used for programming. The present invention adopts 4 groups of infrared images of “UN Camp” image set (320×240), “Octec” image set (640×480), “Quad” image set (256×256) and “Seascape” image set (256×256) with visible light image set.

[0073] Step 1: Perform NSCT decomposition on the registered images A and B to be fused to obtain their respective NSCT coefficients and in is the NSCT high-frequency subband coefficient of the k-th direction at the j-th scale of the A image, L A is the NSCT low-frequency coefficient of image A, is the NSCT high-frequency subband coefficient of the k-th direction at the j-th scale of the B image, L B is the NSC...

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 supplementation mechanism and PCNN-based NSCT domain image fusion method, and aims at solving the technical problem that the existing NSCT image fusion methods have image distortion phenomena. The technical scheme of the method is carrying out fusion processing on low-frequency sub-bands decomposed by NSCT by adoption of supplementary wavelet transform so as to retain detailed information of image backgrounds as much as possible, carrying out fusion by utilizing an improved Gaussian weighted SML method so as to enhance the image details, and carrying out fusion by utilizing an edge gradient information incentive PCNN method so as to enhance image edge information. Experiments prove that when being compared with the existing image fusion methods, the method disclosed by the invention has better fusion effect and has the advantages of greatly improving the target significance and further improving the image quality while overcoming the texture detail deficiency and distortion deficiency of images.

Description

technical field [0001] The invention relates to an NSCT domain image fusion method, in particular to an NSCT domain image fusion method based on a supplementary mechanism and PCNN. Background technique [0002] Due to the limitations of imaging mechanism and technology, the images acquired by a single imaging sensor cannot reflect all the characteristics of the observed object. Therefore, it is necessary to extract useful information from different sensor images and fuse them into a pair with more complete information, which is helpful to human beings. Observe and process images. [0003] Image fusion technology can synthesize the complementary information of two different types of images. It is not simply superimposed on different types of images. There are limitations in the acquisition of specific targets, and at the same time, it can improve the spatial resolution and clarity of the image, facilitate image understanding and recognition, and effectively improve the utili...

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): G06T5/50
CPCG06T5/50G06T2207/10048G06T2207/20084G06T2207/20221
Inventor 王健张修飞任萍院文乐
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