An Image Registration Method Combining Edge Regions and Cross-correlation

A technology of edge areas and edge images, applied in the field of image registration, can solve problems such as easy to cause mismatches, and achieve the effects of avoiding interference, ensuring accuracy, and preventing mismatches

Active Publication Date: 2017-03-22
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method is fast, it only uses binary images for calculation and uses too little image information, which is likely to cause mismatching

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
  • An Image Registration Method Combining Edge Regions and Cross-correlation
  • An Image Registration Method Combining Edge Regions and Cross-correlation
  • An Image Registration Method Combining Edge Regions and Cross-correlation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be described in detail below with reference to the accompanying drawings and examples.

[0023] Such as figure 1 As shown, the image registration method combined with edge area and cross-correlation, the specific steps are:

[0024] Step 1. Extract the edges of the reference image and the image to be registered.

[0025] The present invention adopts the Canny operator to extract the edges of the reference image and the image to be registered respectively, and flexibly sets the threshold parameter of the Canny operator according to the different imaging mechanisms of the reference image and the image to be registered.

[0026] Step 2, extracting edge region images of the reference image and the image to be registered.

[0027] According to the Canny edge image, extract the edge area images of the reference image and the image to be registered respectively, and find all areas whose distance from the edge pixel is less than or equal to D (the s...

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 provides an image registration method combined with edge regions and cross-correlation. The image registration method can be used for effectively selecting the edge regions of images, and selecting and improving similarity measure functions and optimization algorithms, and aims to improve robustness and real-time performance of image registration on the premise of meeting image registration accuracy. The image registration method includes the first step of extracting the edges of reference images and images to be registered; the second step of obtaining edge region images of the reference images and the images to be registered through edge images of the two images; the third step of calculating cross-correlation coefficients of the two edge region images obtained at the second step, and using a squared value of the cross-correlation coefficients as a similarity measure function; the fourth step of searching for registration result parameters enabling the similarity measure function obtained at the third step to reach the maximum by means of a particle swarm optimization algorithm.

Description

technical field [0001] The invention belongs to the field of image registration, in particular to an image registration method combining edge regions and cross-correlation. Background technique [0002] Image registration is an important problem in the field of image processing. It is the process of performing spatial transformation on two images collected at different times and angles, so that the two images are consistent in spatial orientation. With the development of science and technology, image registration has been applied in computer vision, medical image processing, pattern recognition and other aspects. [0003] The methods of image registration can be roughly divided into two categories: (1) feature-based image registration, which extracts the salient feature points of the image as reference information, and establishes the geometric transformation relationship between the two images for registration. (2) Image registration based on grayscale. According to the g...

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): G06T7/38
Inventor 陈禾周孟哲章学静马龙曾涛龙腾
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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