Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Surface registration method based on ricci flow

A registration and odd flow technology, applied in image data processing, instruments, calculations, etc., can solve the problem that discrete Rich flow cannot effectively converge, and achieve the effects of avoiding errors, improving calculation speed, and ensuring effectiveness

Active Publication Date: 2013-03-20
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF1 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But in spherical geometry, the discrete Ricci flow cannot effectively converge

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
  • Surface registration method based on ricci flow
  • Surface registration method based on ricci flow
  • Surface registration method based on ricci flow

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0082] The method of the present invention will be further described below through a specific example. This embodiment uses Matlab software to implement the algorithm described in the present invention, and is all completed on a computer that is equipped with a Core 2 Duo 2.2GHz processor, 2Gb internal memory, and an operating system of Windows7.

[0083] This example is for registering the surface of a left hemisphere of the brain. Before registration, it is first necessary to read the data on the surface of the left hemisphere of the brain, the data includes corresponding grid surface information, and the grid surface information includes vertex positions, connection relationships, and the like. The surface to be registered and the target surface such as Figure 5 As shown, the upper image is the surface to be registered, and the lower image is the target surface.

[0084] Step S1: Perform topological correction on the surface of the left hemisphere of the brain to be regi...

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 surface shape registration method based on a ricci flow. The method comprises the steps that a closing surface is parameterized according to an improved ricci flow method firstly; the closing surface is mapped to a spherical surface; in addition, an energy variation condition of the ricci flow is recorded in a computation process; a multi-scale ricci flow energy matrix is established, and then subjected to laplace transformation; a laplace matrix of the multi-scale ricci flow energy matrix is computed; multi-scale feature points based on ricci energy are extracted according to the laplace matrix; furthermore, global ricci flow energy are combined with local feature points; a registration equation is established; a plurality of various surfaces are subjected to registration on a spherical surface domain by utilizing the registration equation; registration results are mapped to the original surface finally; and the whole registration process is accomplished. With the adoption of the method, the computation time in a parameterization process is shortened; global attributes are effectively combined with local features; and the accuracy of the registration is improved.

Description

technical field [0001] The invention relates to the field of computer image processing, in particular to a surface registration method based on Ritchie flow energy and feature points, which combines global features and local feature points. Background technique [0002] Image registration is the process of matching and superimposing two or more images acquired at different times, different sensors (imaging devices) or under different conditions. The accuracy of its registration directly affects the accuracy of subsequent analysis. [0003] There are many methods for surface registration, especially for surface registration in medical image processing. Most of the methods are based on surface curvature or other global attributes for registration. This type of method can perform global registration better, but sometimes the registration results are inaccurate in some parts that need to be studied. Another method is to use feature points for registration. Studies have shown ...

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): G06T7/00
Inventor 何晖光陈雪姣
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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
Eureka Blog
Learn More
PatSnap group products