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

A Non-Feature Extraction and Non-parametric 3D Image Registration Method

An image registration, non-parametric technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of heavy dependence on method initialization quality, inconvenient extraction of feature sets, etc.

Inactive Publication Date: 2019-09-06
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Obviously, this method has several disadvantages: (1) It is inconvenient to extract the relevant feature set; (2) It is limited by the use of parametric geometric transformation; (3) It is heavily dependent on the initialization quality of the method; (4) It is easy to obtain local extremes. small, not the global minimum

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
  • A Non-Feature Extraction and Non-parametric 3D Image Registration Method
  • A Non-Feature Extraction and Non-parametric 3D Image Registration Method
  • A Non-Feature Extraction and Non-parametric 3D Image Registration Method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] Below in conjunction with accompanying drawing and example the invention is further described:

[0051] Our proposed image registration procedure consists of five main steps, which are described in detail as follows:

[0052] Step 1: Use an edge detector to detect the reference image Z to be observed R edge voxels;

[0053] Step 2: For the voxel (x, y, z) of the real reference image R that has been given, take the voxel as the center and the radius is r 1 The circular neighborhood of is expressed as Ο(x,y,z; r 1 ), if in Ο(x,y,z; r 1 The number of edge voxels detected in ) is less than [nr 1 ], where [] is the rounding operation symbol, then (x, y, z) is considered to be the continuous voxels of the reference image R, in this case, if the denominator on the right side of the equation (6) (in After M is replaced by R) is greater than or equal to the pre-specified threshold μ n , then (x, y, z) is considered to be a local non-degenerate voxel of R; otherwise, it is ...

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 the technical field of image fusion and image sequence monitoring, and in particular to a non-characteristic extraction and non-parameter-based 3D image registration new algorithm. The algorithm comprises the following steps of: detecting edge voxels of a to-be-observed reference image ZR by using an edge detector; judging voxels (x, y, z) of a given reference image R; carrying out geometric transformation on local non-degradation bodies of R; defining T (x, y, x) by using local degradation points of R; and outputting geometric transformation parameters. The algorithm is flexible in local smoothing, so that the geometric transformation related to the algorithm does not need any parametric form or other global law conditions, and is practical and effective in practice.

Description

technical field [0001] The invention relates to technical fields such as image fusion and image sequence monitoring, and in particular relates to a non-feature extraction and non-parametric 3D image registration method. Background technique [0002] In many image applications, in order to complete the fusion and difference detection of image objects, we need to compare multiple images of the same object. For example, in order to closely monitor the tumor growth of a patient with a brain tumor, we need to compare MRI images of the patient's brain taken at different times. Because when capturing images, the relative positions of the imaging device and the image objects are almost not the same at different times. For the alignment to be effective, we need to quickly complete the geometric matching of the related images. Image registration (IR) is for this purpose, and it is a fundamental task in many image applications including medical imaging, remote sensing technology, fin...

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): G06T7/00G06T7/13G06T7/32
Inventor 宋华军周光兵任鹏
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