Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fourier-Mellin transform-based image geometric matching method

A technology of Fourier transform and matching method, which is applied in the field of image geometric matching based on Fourier Merlin transform, can solve the problems of increasing matching time and improving matching accuracy not much, and achieves improved accuracy, short matching time, and improved matching. The effect of matching accuracy

Inactive Publication Date: 2016-07-13
XIDIAN UNIV
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, for some image matching, although the error-match removal algorithm is added, the final matching accuracy is not much improved, and the matching time is increased due to the addition of the error-match removal algorithm.

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
  • Fourier-Mellin transform-based image geometric matching method
  • Fourier-Mellin transform-based image geometric matching method
  • Fourier-Mellin transform-based image geometric matching method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] The present invention proposes a kind of image geometric matching method based on Fourier Merlin transform, see figure 1 , to match the image to be matched with the reference image, the matching steps include:

[0044] Step 1: Use Fourier Merlin Transform to find the rotation angle between the image to be matched and the reference image. First, input the image to be matched and the reference image. The reference image and the image to be matched are images of the same scene. There is a certain rotation angle difference, that is, there is a certain rotation angle difference between the image to be matched and the reference image. Both the image to be matched and the reference image are transformed into the Fourier frequency domain to obtain the spectrum of the image to be matched and the reference image, and then the spectrum of the image to be matched and the Fourier spectrum of the reference image are respectively modulo values ​​to establish a relationship between the...

Embodiment 2

[0057] The image geometric matching method based on Fourier Mellin transform is the same as embodiment 1, see figure 2 , wherein the use of Fourier Merlin transform described in step 1 to obtain the rotation angle between the image to be matched and the reference image includes the following steps:

[0058] 1.1 Input the image to be matched and the reference image. The reference image and the image to be matched are images of the same scene. There is a certain rotation angle difference between them. The relationship can be expressed by the following formula,

[0059] f 2 (x,y)=f 1 [a(xcosθ 0 +ysinθ 0 )-Δx,a(-xcosθ 0 +ysinθ 0 )-Δy]

[0060] In the above formula, f 1 (x,y) is the reference image, f 2 (x,y) is the image to be matched, a is the scaling factor, θ 0 is the rotation angle between the image to be matched and the reference image, Δx and Δy are f 1 (x,y) and f 2 (x, y) translation on the x-axis and y-axis;

[0061] 1.2 Perform Fourier transform on both the ...

Embodiment 3

[0087] The image geometric matching method based on Fourier Merlin Transform is the same as that in Embodiment 1-2, wherein the feature points in the reference image saliency map and the image to be matched are extracted using the SURF corner point extraction algorithm described in step 3, including the following steps :

[0088] 3.1 Use the spectral residue theory to obtain the saliency maps of the reference image and the image to be matched.

[0089] 3.2 Determine the candidate feature points in the saliency map of the reference image and the saliency map of the image to be matched, calculate the value of the determinant of the Hessian matrix of each point, and calculate the determinant of the Hessian matrix of each point. The 3×3 three-dimensional area is subjected to non-maximum value suppression, that is, by comparing the values ​​of 8 points near a certain point on this scale and 9 points on the upper and lower adjacent scales, the largest or smallest one is selected as ...

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 Fourier-Mellin transform-based image geometric matching method, so as to solve problems of poor matching precision and long time due to a large rotation angle between a to-be-matched image and a reference image. The matching process comprises steps: the Fourier-Mellin transform is used for solving the rotation angle between the to-be-matched image and the reference image; the rotation angle is corrected to obtain an initial matching image; feature points of the above two image salient maps are extracted; the feature points are associated; an affine transform model is solved; and the model is used for transforming the initial matching image, a bilinear interpolation method is used for carrying out interpolation on the transformed image, and a final matching image is obtained. The condition of a small rotation angle difference between the to-be-matched image and the reference image can be effectively handled, the condition of a large rotation angle between the two images can also be processed, and the matching time is far less than that in an SIFT algorithm. The method of the invention is high in precision and matching efficiency, and can be used for processing image matching in the case of a large rotation angle difference between the images.

Description

technical field [0001] The invention belongs to the technical field of image processing, and mainly relates to algorithms such as feature extraction, feature association, optimization, and image interpolation. Specifically, it is an image geometric matching method based on Fourier Merlin transform, which can be used in medical image processing, remote sensing image processing, and computer processing. Vision, pattern recognition and other fields. Background technique [0002] In the middle of the 20th century, scientists proposed the concept of image geometric matching in the process of navigation, and image geometric matching was widely used in the military field. After the 1980s, image geometric matching began to be used in civilian fields, such as medical image processing, remote sensing image fusion, etc., and effectively promoted the development of these fields. [0003] Image geometric matching is the process of aligning the same structure or the same position in two ...

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): G06K9/62
CPCG06V10/757G06F18/22
Inventor 那彦廖萌萌刘强强
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com