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

Image Fusion Method Based on Feature Extraction of Two-dimensional Empirical Mode Decomposition Method

An empirical mode decomposition and feature extraction technology, applied in the field of image processing, can solve problems such as reducing the quality of fusion images and introducing pseudo-Gibbs phenomena into images, and achieve the effect of improving and protecting features

Active Publication Date: 2016-06-15
INNER MONGOLIA UNIV OF SCI & TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Currently, image fusion methods include methods based on spatial domain transform and frequency domain transform. Among them, image fusion methods based on multiresolution analysis represented by wavelet transform and various ultrawavelet transforms are the most widely used, but wavelet transform and its improved methods rely on prior The defined filter or basis function, the wavelet transform will have a downsampling operation, and the transformed image will introduce pseudo-Gibbs phenomenon, which will reduce the quality of the fusion image

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 Feature Extraction of Two-dimensional Empirical Mode Decomposition Method
  • Image Fusion Method Based on Feature Extraction of Two-dimensional Empirical Mode Decomposition Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] This embodiment includes the following steps:

[0021] Step 1: Registered medical head CT and MR images and BEMD decomposition is performed separately to obtain a limited number of two-dimensional intrinsic modulus functions (BIMF) and residuals (trend images) with frequencies ranging from high to low;

[0022] The algorithm steps of BEMD decomposition are as follows:

[0023] 1) Initialize, set the source image , the trend image is:

[0024] ;

[0025] 2) If the trend image is monotonous or reaches the number of decomposition layers of the image, the algorithm stops; otherwise, let ,which is , enter the screening process;

[0026] 3) Using the morphological algorithm, the image Solve the extreme points, find out the regional maximum point set and minimum point set;

[0027] 4) Perform plane interpolation on the regional maximum point set and minimum point set respectively to obtain the upper and lower envelope surfaces of the image , get the image ...

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 an image fusion method based on two-dimensional empirical mode decomposition method feature extraction. The invention applies BEMD to medical image feature extraction, and obtains them by inputting sub-images and trend graphs decomposed by BEMD into a neural network. According to the ignition map, the medical image features corresponding to different decomposition layers are extracted; after that, the coefficients corresponding to the image texture information and background information are selected through PCNN and dual-channel PCNN respectively. The features in the image are protected, and the effect of PCNN in the selection of medical image coefficients is effectively improved.

Description

technical field [0001] The invention relates to an image processing method, in particular to a head medical image fusion method based on BEMD feature extraction. Background technique [0002] With the rapid development of imaging technology, all kinds of precision imaging equipment have promoted the development of medical imaging, providing a wealth of human medical images for clinical practice. However, there are many types of imaging devices, and their imaging mechanisms are different, which reflect their own emphasis on medical information. In order to comprehensively analyze the anatomical information and functional information contained in medical images, it is necessary to fuse multimodal medical images. [0003] Medical image fusion technology is oriented to multi-modal medical images. It organically combines information from various medical images to complete the fusion of various medical information. It not only effectively utilizes existing medical images, but also...

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): G06T5/50G06T7/40
Inventor 张宝华张飞梁浩刘鹤
Owner INNER MONGOLIA UNIV OF SCI & TECH
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