Similarity estimation based on sparse spectral correspondence
| Autor: | Dan Li, Shu Ning Liu, Li Han, Yu Nan Liu, Di Tang |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Dense graph
Computer Networks and Communications Computer science 020207 software engineering 02 engineering and technology Sparse approximation Minimum spanning tree Graph Spline (mathematics) Matrix (mathematics) Hardware and Architecture 0202 electrical engineering electronic engineering information engineering Media Technology Leverage (statistics) Algorithm Software Shape analysis (digital geometry) |
| Zdroj: | Multimedia Tools and Applications. 78:14443-14463 |
| ISSN: | 1573-7721 1380-7501 |
| Popis: | We present a sparse spectral correspondence method for deformable shape analysis. Our method exploits randomized sampling for sparse shape representation. By choosing a random subset of points that preserve key properties of the entire data set, it allows one to run algorithms efficiently on a small sample. First we implement random row sampling of an undirected weighted graph matrix by “Lewis weights”, which can be viewed as statistical leverage scores of a reweighted matrix and used directly as sampling probabilities. Second, a sparse graph is constructed on selected sample points by using minimum spanning tree (MST). We then discover the meaningful structural correspondence based on TPS (thin-plate spline) approach in the spectral embedded space. Finally we show how we use the sparse spectral correspondence to implement similarity estimation for shape matching and classification for different topological shapes. A series of experimental results demonstrate that our method is accurate and robust for shape analysis. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink