Retinal image registration method with affine invariance and device thereof

An affine invariance and image registration technology, applied in the field of image processing, can solve the problems of lesion detection interference, limited shooting content, retinal image differences and changes, etc.

Active Publication Date: 2019-10-22
CENT SOUTH UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to different imaging angles and imaging environments, multiple shots often cause subtle differences and changes in retinal images
This differential change will bring difficult interference to the detection of lesions, thus affe...

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
  • Retinal image registration method with affine invariance and device thereof
  • Retinal image registration method with affine invariance and device thereof
  • Retinal image registration method with affine invariance and device thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0095] The technical solutions in the present invention are clearly and completely described below in combination with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0096] like figure 1 As shown, a kind of retinal image registration method with affine invariance provided by the present invention comprises the following steps:

[0097] Step 1: Obtain the image of the main area of ​​the blood vessel;

[0098] Input two retinal images (respectively perform steps 1-6 on the two images), one as the reference image I src (like Figure 2A shown), and the other as the image to be registered I dst (like Figure 2B shown), and then extract th...

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 retinal image registration method with affine invariance and a device thereof, and relates to the technical field of image processing. Compared with the whole treatment of the traditional technology, the invention discloses a retinal image registration method with affine invariance. On the basis of a retinal skeletal network image, a local image structure (namely a candidate feature region) is intercepted through two intersections which are communicated with each other in a connected domain; and the local image structure is transformed (rotated, Gaussian filtered andcompressed) into a form suitable for a circular Gaussian filter, so that the problem of visual angle and scale change is solved, the registration precision of multiple images is improved, the construction of complete retinal image information is facilitated, the interference of retinal lesions on diagnosis is reduced, and the diagnosis accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a retinal image registration method with affine invariance and a device thereof. Background technique [0002] Since the 20th century, medical imaging technology has developed rapidly, and various imaging devices have emerged one after another. ), optical coherence tomography (OCT) and positron emission tomography (PET), etc., are increasingly relying on the analysis of medical images in clinical diagnostic analysis. Different imaging devices provide different information for the same organ due to different imaging principles. How to properly register these images to obtain more information has become an urgent need for clinicians. Therefore, the research on medical image registration has been favored by many scholars and has gradually become a hot topic. [0003] Image registration is an extremely important technology in image processing. It is widely used...

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): G06T7/00G06T7/136G06T7/33
CPCG06T7/0012G06T2207/30041G06T7/136G06T7/33
Inventor 邹北骥劳承鹏陈再良朱承璋
Owner CENT SOUTH 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