Supercharge Your Innovation With Domain-Expert AI Agents!

A sift feature matching algorithm that combines color information and global information

A color information, matching method technology, applied in computing, computer parts, character and pattern recognition, etc., can solve the SIFT matching fuzzy problems, to solve the matching fuzzy, maintain rotation invariance, improve robustness and stability sexual effect

Inactive Publication Date: 2017-10-03
BEIHANG UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, because it is a local operator designed for grayscale images, SIFT matching will have problems such as matching blur

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
  • A sift feature matching algorithm that combines color information and global information
  • A sift feature matching algorithm that combines color information and global information
  • A sift feature matching algorithm that combines color information and global information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Such as figure 1 , the present invention creates a brand-new shape-color joint robust image matching descriptor——Shape-Color Alliance Robust Feature (SCARF). It consists of three parts: SIFT descriptor, global descriptor, and color descriptor.

[0026] The whole implementation process is as follows:

[0027] 1) Extract feature points from the input image: This method uses SIFT detectors to process the target image and the image to be matched, collect their respective feature point sets, and store them.

[0028] 2) Construct a concentric circle coordinate system. For the feature point sets extracted from the two images respectively, take each feature point as the center and k×σ as the radius to establish concentric circle coordinates. Among them, k is the experimental parameter, and σ is the scale corresponding to the feature point. In this way, the corresponding region is related to the scale of the feature points, so that the global descriptor has better scale inva...

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 an SIFT (Scale Invariant Feature Transform) based image matching algorithm -SCARF (Shape-Color Alliance Robust Feature) algorithm. The algorithm includes extracting feature points from images prior to creating corresponding coordinate systems, and creating three different descriptors so as to perform image matching. For feature point extraction, an SIFT feature point extraction method is used continuously, then the concentric circular coordinate systems are established by taking each feature point as a circle center, the corresponding descriptors are created according to local information, global information and color information of the images, and the different coordinate systems are created according to selection of weight parameters so as to obtain brand-new descriptors. Since the extracted feature points have good rotation and scale invariance, the global shape information, the local information and the color information of the images are considered when the descriptors are created and the concentric circular coordinate systems are adopted, so that calculation of the algorithm is simplified, robustness in matching is improved, and matching effect is more outstanding.

Description

technical field [0001] The invention relates to a SIFT-based improved image matching algorithm—SCARF (Shape-Color Alliance Robust Feature) algorithm. This method is mainly to match two images of the same scene, and has rich global shape information and color information, which enhances the matching effect, has a moderate amount of computation, and can be applied to image processing equipment that requires high matching accuracy. The method can be widely used in medical image processing, remote sensing image, pattern recognition, 3D reconstruction and other fields. Background technique [0002] Image matching is a very important work in the field of computer vision and image processing. It is mainly used to match two or more images acquired at different times, different sensors, different viewing angles and different shooting conditions. Image matching is the basis of various image processing and applications, and the matching effect directly affects the subsequent image pr...

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): G06K9/46
CPCG06T7/33G06T7/73
Inventor 王睿朱正丹
Owner BEIHANG UNIV
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