Image registration method, device and storage medium

An image registration and image technology, applied in image analysis, image enhancement, image data processing and other directions, can solve the problems of low efficiency, slow random algorithm, easy to fall into local optimal solution, etc., and achieve good global searchability. , the effect of high position accuracy

Active Publication Date: 2022-02-18
BEIJING LINKING MEDICAL TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Different similarity measurement algorithms and optimization algorithm combinations have their own characteristics, but they also have their own limitations. In summary, there are two main problems: one is that analytical algorithms tend to fall into local optimal solutions, and the other is that random algorithms are often slow. very slow and inefficient

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
  • Image registration method, device and storage medium
  • Image registration method, device and storage medium
  • Image registration method, device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] A method for image registration, suitable for execution in a computing device, comprising the following steps (such as figure 1 shown):

[0057] (1) Mark the region of interest 101 on the image to be registered; preferably in this embodiment, the region of interest is selected manually or automatically selected by algorithm definition, such as defining an area above a certain contour line of the image, etc.;

[0058] figure 2 It is a schematic diagram of manually selecting a region of interest in an exemplary embodiment of the present invention, and the region inside the rectangular frame in the figure is the manually selected region of interest. Those skilled in the art should understand that the shape of the manually selected region of interest is not necessarily a rectangle, and other arbitrary shapes can also be selected.

[0059] In this embodiment, preferably, the region of interest may also be automatically selected through an algorithm definition. The automa...

Embodiment approach 1

[0070] Embodiment 1: The registration rotation angle step size and the registration translation step size are respectively set to the minimum rotation angle step size and the minimum translation step size multiplied by a coefficient not less than 1.

[0071] The minimum rotation angle is θ min , the minimum translation step is {Lx,Ly} (if the length and width of the picture pixels are the same, that is, Lx=Ly), the registration rotation angle step can be set to k=k1*θ min (k1>=1), the registration translation step is set to {k2*Lx, k3*Ly} (k2, k3>=1)

Embodiment approach 2

[0072] Embodiment 2: The registration rotation angle step size and the registration translation step size are set to a fixed step size plus a random step size.

[0073] The minimum rotation angle is θ min , the minimum translation step size is {Lx,Ly}, and the registration rotation transformation step size can be set to k1*θ min +δ (k1>=1, δ>=0 random), the registration translation step is set to {k2*Lx+ε, k3*Ly+τ} (k2, k3>=1, ε,τ>=0 random )

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 belongs to the field of image processing and computer technology, and relates to an image registration method, device and storage medium. The method includes the following steps: setting the region of interest on the image to be registered; performing initial registration; calculating the initial similarity between the image to be registered and the reference image; determining the minimum rotation angle and the minimum translation step; setting rigid registration iterations Step length: transform the image to be registered to obtain the registration image group; calculate the similarity between each image in the registration image group and the reference image, determine the image with the highest similarity and its similarity; judge whether the similarity reaches the optimal specification And whether to reach the set number of iterations. The image registration method provided by the invention has strong global search ability for angle and translation, and can greatly reduce initial value sensitivity. In the process of generating new rigid transformation registration images, the present invention can also adopt self-adaptive step size plus random step size to optimize each generation of registration images and improve image registration efficiency.

Description

technical field [0001] The invention belongs to the field of image processing and computer technology, and relates to an image registration method, device and storage medium. Background technique [0002] Image processing is to process image information to meet the requirements of human vision, psychology and practical application. Image registration is a basic problem in image processing, which is used to match two or more images of the same scene or object acquired at different times, different image acquisition devices or different viewing angles. The application fields of image registration are quite extensive, and the most commonly used fields include medical image analysis, remote sensing data analysis, pattern recognition, computer vision, etc. The essence of image registration is the mapping of two images in space and color. Therefore, to register an image, it is necessary to seek a mapping method so that the image to be registered and the registered image can be o...

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): G06T7/33
CPCG06T7/337G06T2207/20104
Inventor 袁志刚
Owner BEIJING LINKING MEDICAL TECH CO LTD
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