A non-rigid medical image anti-rotation registration method based on ellipsoid model

An ellipsoid model, medical image technology, applied in the field of medical image registration and image processing, can solve the problems of incompatibility with large-angle transformation, slow registration speed, poor anti-rotation, etc., achieve good anti-rotation, improve registration The effect of reducing speed and time consumption

Inactive Publication Date: 2019-06-04
DALIAN UNIVERSITY OF FOREIGN LANGUAGES
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] In order to overcome the problems of poor anti-rotation existing in existing medical image registration methods, inadaptability to large-angle transformations, and slow registration speed, the present invention provides a non-rigid anti-rotation registration method for medical images based on an ellipsoid model

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-rigid medical image anti-rotation registration method based on ellipsoid model
  • A non-rigid medical image anti-rotation registration method based on ellipsoid model
  • A non-rigid medical image anti-rotation registration method based on ellipsoid model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0065] See attached Picture 8 Attached Figure 20 . Select the standard image CT1109 in the Visual Human image library as the original reference image (attached Picture 8 ), the image PD1110 is used as the original image to be registered (attached Picture 9 ).

[0066] Perform edge detection operations based on wavelet transform on images CT1109 and PD1110. After extracting the characteristic rectangular domain of the image, select n=64. The reference image constructed by the ellipsoid model and the image to be registered are respectively as attached Picture 10 And Picture 11 As shown, the registered image after Fourier rotation transform is as attached Picture 12 Shown.

[0067] Select n=16, and the reference image and the image to be registered constructed with the ellipsoid model are as attached Figure 13 And Figure 14 As shown, the registered image after Fourier rotation transform is as attached Figure 15 Shown.

[0068] Select n=4, and the reference image and 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 a non-rigid medical image anti-rotation registration method based on an ellipsoidal model. The method comprises steps of under a precondition that initial transformation of an image is carried out to obtain the image feature point and the minimum feature rectangular domain, dividing the minimum feature rectangular domain of the image by the ellipsoidal model to obtain the average value of the gray level of the pixels in each partition, and taking the average value as the representative of the pixel gray level of the region; based on the pixel gray level sequence, using the Fourier transform algorithm to obtain the image rotation transformation parameter; subjecting the image to rotation transformation to complete one registration process; and reducing the division parameter of the ellipsoidal model to re-divide and re-transform the image, so as to gradually improve the image registration precision; and repeating the abovementioned steps until the image partition number is 1, and carrying out interpolation of the image to achieve the image registration. Compared with the conventional image registration method, the method provided by the invention is faster in registration speed, higher in precision, and better in robustness.

Description

Technical field [0001] The invention belongs to the technical field of image processing, in particular the technical field of medical image registration, and specifically relates to a non-rigid medical image anti-rotation registration method based on an ellipsoid model. Background technique [0002] Image registration is the process of matching and superimposing two or more images acquired at different times, different sensors (imaging equipment) or under different conditions (weather, illuminance, camera position and angle, etc.). It is widely used in remote sensing data analysis, computer vision, medical image processing and other fields. [0003] Image registration is a very important technology in image analysis. It is mainly by looking for a certain transformation to make the corresponding points of two images reach the same spatial position. In the process of medical diagnosis, due to the existence of different modes of images showing different properties Physical mechanism,...

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): G06T7/33G06T7/00
CPCG06T7/0012G06T2207/30004
Inventor 陶永鹏刘朝霞顼聪郭鹏刘建鑫
Owner DALIAN UNIVERSITY OF FOREIGN LANGUAGES
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