Tensor Affinity Learning for Hyperorder Graph Matching
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 extr...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/20/3806 |
| _version_ | 1797471751547912192 |
|---|---|
| author | Zhongyang Wang Yahong Wu Feng Liu |
| author_facet | Zhongyang Wang Yahong Wu Feng Liu |
| author_sort | Zhongyang Wang |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T19:52:38Z |
| format | Article |
| id | doaj.art-e5edac325eee480e926e9182b7de5054 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T19:52:38Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-e5edac325eee480e926e9182b7de50542023-11-24T01:07:17ZengMDPI AGMathematics2227-73902022-10-011020380610.3390/math10203806Tensor Affinity Learning for Hyperorder Graph MatchingZhongyang Wang0Yahong Wu1Feng Liu2School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaSchool of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaSchool of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaHypergraph 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.https://www.mdpi.com/2227-7390/10/20/3806hypergraph matchingsimilarity metricinformation-theoretic metric learning |
| spellingShingle | Zhongyang Wang Yahong Wu Feng Liu Tensor Affinity Learning for Hyperorder Graph Matching Mathematics hypergraph matching similarity metric information-theoretic metric learning |
| title | Tensor Affinity Learning for Hyperorder Graph Matching |
| title_full | Tensor Affinity Learning for Hyperorder Graph Matching |
| title_fullStr | Tensor Affinity Learning for Hyperorder Graph Matching |
| title_full_unstemmed | Tensor Affinity Learning for Hyperorder Graph Matching |
| title_short | Tensor Affinity Learning for Hyperorder Graph Matching |
| title_sort | tensor affinity learning for hyperorder graph matching |
| topic | hypergraph matching similarity metric information-theoretic metric learning |
| url | https://www.mdpi.com/2227-7390/10/20/3806 |
| work_keys_str_mv | AT zhongyangwang tensoraffinitylearningforhyperordergraphmatching AT yahongwu tensoraffinitylearningforhyperordergraphmatching AT fengliu tensoraffinitylearningforhyperordergraphmatching |