A multi-graph matching method based on low-rank tensor recovery

A graph matching and frame image technology, which is applied in data analysis in the field of genetics, images, and graphics to achieve the effect of improving matching accuracy, reducing false matching, and enriching feature information

Active Publication Date: 2022-05-27
NANJING UNIV OF POSTS & TELECOMM
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Simple pairwise matching is often not the best approach

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 multi-graph matching method based on low-rank tensor recovery
  • A multi-graph matching method based on low-rank tensor recovery
  • A multi-graph matching method based on low-rank tensor recovery

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0079] Below in conjunction with the accompanying drawings and specific embodiments, the present invention will be further clarified. It should be understood that these examples are only used to illustrate the present invention and not to limit the scope of the present invention. Modifications in the form of valence all fall within the scope defined by the appended claims of the present application.

[0080] A multi-graph matching method based on low-rank tensor recovery, the specific steps are as follows:

[0081] Step 1: Preprocess each frame of images and perform feature extraction, that is, extract features of interest points, and obtain position information of interest points.

[0082] SIFT (Scale Invariant Feature Transform) is often used to detect and describe local features in images. The description and detection of local image features can help identify objects. The SIFT algorithm finds feature points (key points) in different scale spaces. And calculate the specifi...

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 multi-image matching method based on low-rank tensor recovery, which includes the following steps: S1: preprocessing each frame of image and performing feature extraction, that is, extracting the feature of interest points; S2: interest of each frame of image Points are processed, and their high-order information features are extracted according to the topological relationship of the interest points; S3: Based on the multi-map cycle consistency, a multi-map high-order feature information tensor is constructed according to the global correspondence between the permutation matrix and image features; S4: Ranked Constraints as a standard, based on Alternating Direction Multiplier Method (ADMM) algorithm to solve the low-rank representation of multi-image high-order feature information tensor, can effectively calculate the corresponding optimal permutation matrix between multiple images, that is, the matching result matrix. The invention proposes a multi-image matching method based on low-rank tensor recovery, which realizes the consistency of image matching and improves the matching accuracy, and has important significance for image matching application research, target recognition and target tracking technology.

Description

technical field [0001] The invention relates to a multi-graph matching method based on low-rank tensor recovery, which can be used in the field of image processing, especially data analysis in the fields of images, graphics, genes and the like. Background technique [0002] As a hot issue in pattern recognition and computer vision research, image matching originated from research in the military field of the United States in the 1970s, and has received extensive attention and research. Image matching theory also plays a very important role in other research directions in the field of pattern recognition, such as image stitching technology, whose core is image matching; target tracking technology, which needs to rely on matching algorithms in the later stages; and for many detection and recognition algorithms, among which A large category is achieved by relying on matching technology. It can be seen that image matching has very important application value and theoretical res...

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): G06V10/44G06V10/75G06K9/62
CPCG06V10/44G06V10/751
Inventor 王雪琴朱虎李海波邓丽珍
Owner NANJING UNIV OF POSTS & TELECOMM
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