Matching Images With Multiple Descriptors : An Unsupervised Approach for Locally Adaptive Descriptor Selection
With the aim to improve the performance of feature matching, we present an unsupervised approach for adaptive description selection in the space of homographies. Inspired by the observation that the homographies of correct feature correspondences vary smoothly along the spatial domain, our approach...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 24(2015), 12 vom: 09. Dez., Seite 5995-6010
|
|---|
| 1. Verfasser: |
Hu, Yuan-Ting
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Lin, Yen-Yu,
Chen, Hsin-Yi,
Hsu, Kuang-Jui,
Chen, Bing-Yu |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2015
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|
|---|
| Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't |
|---|