We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Tensor Affinity Learning for Hyperorder Graph Matching.
- Authors
Wang, Zhongyang; Wu, Yahong; Liu, Feng
- 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.
- Subjects
MANHATTAN (New York, N.Y.); IMAGE registration; GRAPH algorithms; COMPUTER vision; EUCLIDEAN distance; APPLICATION software; SIMILARITY (Geometry); COSINE function
- Publication
Mathematics (2227-7390), 2022, Vol 10, Issue 20, p3806
- ISSN
2227-7390
- Publication type
Article
- DOI
10.3390/math10203806