Normalized cut-based saliency detection by adaptive multi-level region merging
Existing salient object detection models favor over-segmented regions upon which saliency is computed. Such local regions are less effective on representing object holistically and degrade emphasis of entire salient objects. As a result, the existing methods often fail to highlight an entire object...
| Publié dans: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 24(2015), 12 vom: 06. Dez., Seite 5671-83 |
|---|---|
| Auteur principal: | |
| Autres auteurs: | , , |
| Format: | Article en ligne |
| Langue: | English |
| Publié: |
2015
|
| Accès à la collection: | IEEE transactions on image processing : a publication of the IEEE Signal Processing Society |
| Sujets: | Journal Article Research Support, Non-U.S. Gov't |
| Accès en ligne |
Volltext |