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

Non-rigid image registration method based on image feature and Demons

An image feature and image registration technology, applied in the field of image processing, can solve the problem that the non-rigid image registration method cannot meet the requirements of registration accuracy and registration time at the same time.

Inactive Publication Date: 2017-05-31
SHANDONG UNIV
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem that the traditional non-rigid image registration method cannot meet the registration accuracy and registration time requirements at the same time, the present invention provides a non-rigid image registration method based on image features and Demons

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
  • Non-rigid image registration method based on image feature and Demons
  • Non-rigid image registration method based on image feature and Demons
  • Non-rigid image registration method based on image feature and Demons

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments.

[0023] The present invention realizes the registration process of medical images through the following steps in sequence:

[0024] Step 1: Read in the reference image S and floating image M, and preprocess S and M;

[0025] Step 2: Construct the scale space and set the parameters of the Gaussian difference operator; use the Hessian matrix to construct the scale space;

[0026] Step 3: Screen extreme points and generate SIFT or SURF descriptors of these extreme points;

[0027] Step 4: Use the descriptor obtained in step 3 to perform feature point matching, generate a deformation field, and perform rough registration on the floating image M;

[0028] Step 5: Use step 4 to obtain the rough registration image M' and the reference image S for Demons iterative fine registration:

[0029]

[0030] Step 6: Use the reference image S and...

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, which belongs to the image processing field, discloses a non-rigid image registration method based on an image feature and Demons. In order to solve problems that registration precision and registration time requirements can not be met simultaneously by the traditional non-rigid image registration method, the invention provides two kinds of non-rigid image registration methods (SIFT-Demons and SURF-Demons) based on the classical Demons method from a coarse level to a refined level and from a feature level to a pixel level. According to the a non-rigid image registration method, feature point extraction is carried out on a floating image and a reference image by using an SIFT method or an SURF method, and coarse registration (feature-level registration) is carried out on the extracted feature point; and then on the basis of the coarse registration, refined registration (pixel-level registration) is carried out by using an optical-flow-field-based Demons method. Lots of registration tests demonstrate that accurate, rapid, and stable registration of a medical image can be realized by using the non-rigid image registration method and defects of the traditional non-rigid image registration method can be overcome.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a non-rigid image registration method based on image features and Demons. Background technique [0002] Image registration technology is the process of matching two or more images of the same scene (Scene) or the same target (Object) with different acquisition times (Time), different sensors (Sensor), and different acquisition conditions (Condition). It is widely used in medical image processing, remote sensing image processing, etc. In the registration of medical images, large non-uniform deformation usually occurs between the two images that need to be registered. Therefore, non-rigid image registration technology is a hot issue in the research of medical image processing. At present, non-rigid image registration methods are mainly divided into registration methods based on image features and registration methods based on image grayscale. The registration method based on image...

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): G06T7/33
CPCG06T2207/20016G06T2207/30004
Inventor 董恩清贾大宇薛鹏唐振超
Owner SHANDONG 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