Unlock instant, AI-driven research and patent intelligence for your innovation.

Image registration method based on improved scale invariant feature transform (SIFT) algorithm and Lissajous figure track

An algorithm and trajectory technology, applied in image analysis, image data processing, calculation, etc., can solve problems such as low correct matching rate, unstable remote sensing image alignment, geometric deformation and sensitivity to image grayscale changes.

Inactive Publication Date: 2011-03-23
SHANGHAI INST OF TECH
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the shortcomings of the algorithm that is sensitive to geometric deformation and image gray level changes,
As a result, it is very unstable when it is used for remote sensing image alignment, and the correct matching rate between feature points is extremely low.

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 based on improved scale invariant feature transform (SIFT) algorithm and Lissajous figure track
  • Image registration method based on improved scale invariant feature transform (SIFT) algorithm and Lissajous figure track
  • Image registration method based on improved scale invariant feature transform (SIFT) algorithm and Lissajous figure track

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] 1. Improved SURF and SIFT algorithms

[0015] 1. Detect and match with SURF or SIFT algorithm from two images

[0016] 2. Two sets of feature points, the matching feature point pairs are sorted from high to low according to their similarity.

[0017] 3. Detect the contour information or edge information of the two images.

[0018] 4. Calculate the corresponding TAR graph for a pair of matching feature point pairs and a pair of nearby edges. The calculation of the TAR graph is based on the fact that the affine invariance is TAR, which is calculated based on the coordinates of the three vertices of the triangle. If the three vertices of the triangle are: p B (x b ,y b ), p M (x m ,y m ), p E (x e ,y e ), then we have

[0019] TAR ( p B , p M , p E ) = 1 ...

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 relates to an image registration method based on an improved scale invariant feature transform (SIFT) algorithm and a Lissajous figure track, which belongs to the technical field of image aligning and registering for computers and can be used for aligning and registering remote sensing, medical and ordinary images. Boundary information which is relatively stable in a plurality of modes is combined, so that the latent defects of the SIFT / speeded up robust features (SURF) algorithm are overcome. The correct feature matching rate of the SIFT / SURF algorithm in a multi-mode image aligning algorithm is increased effectively, so that the stability of an aligning algorithm is enhanced. A Lissajous figure track-based similarity measuring function is provided to enhance image aligningaccuracy. The similarity measuring function has high stability and higher aligning accuracy. An image aligning algorithm with higher stability and higher aligning accuracy is constructed on the basisof the improved SIFT / SURF algorithm and the provided Lissajous figure track-based similarity measuring function.

Description

Technical field: [0001] The method belongs to the field of computer image alignment and registration. It can be used for alignment and registration of remote sensing, medical and general images. Background technique: [0002] The SIFT and SURF algorithms are used to detect feature points from two related images and perform matching operations. However, due to the shortcomings of the algorithm is sensitive to geometric deformation and image gray level changes. As a result, it is very unstable when it is used for remote sensing image alignment, and the correct matching rate between feature points is extremely low. In order to solve these two problems, this paper proposes an improved SIFT (SURF) algorithm and similarity measure function. Invention content: [0003] When applying SIFT algorithm or SURF algorithm to align remote sensing images, there are two very big defects. These two deficiencies are mainly due to the multimodality of images. This method combines edge an...

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 宋智礼
Owner SHANGHAI INST OF TECH
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com