Tensor Affinity Learning for Hyperorder Graph Matching

Zhongyang Wang, Yahong Wu and Feng Liu ()
Additional contact information
Zhongyang Wang: School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
Yahong Wu: School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
Feng Liu: School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China

Mathematics, 2022, vol. 10, issue 20, 1-18

Abstract: Hypergraph matching has been attractive in the application of computer vision in recent years. The interference of external factors, such as squeezing, pulling, occlusion, and noise, results in the same target displaying different image characteristics under different influencing factors. After extracting the image feature point description, the traditional method directly measures the feature description using distance measurement methods such as Euclidean distance, cosine distance, and Manhattan distance, which lack a sufficient generalization ability and negatively impact the accuracy and effectiveness of matching. This paper proposes a metric-learning-based hypergraph matching (MLGM) approach that employs metric learning to express the similarity relationship between high-order image descriptors and learns a new metric function based on scene requirements and target characteristics. The experimental results show that our proposed method performs better than state-of-the-art algorithms on both synthetic and natural images.

Keywords: hypergraph matching; similarity metric; information-theoretic metric learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/2227-7390/10/20/3806/pdf (application/pdf)
https://www.mdpi.com/2227-7390/10/20/3806/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:10:y:2022:i:20:p:3806-:d:943130

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().