Leibe, Bastian ; Schiele, Bernt (2006)
Interleaving object categorization and segmentation.
In: Cognitive vision systems : sampling the spectrum of approaches
doi: 10.1007/11414353_10
Buchkapitel, Bibliographie
Kurzbeschreibung (Abstract)
In this chapter, we aim to connect the areas of object categorization and figure-ground segmentation. We present a novel method for the categorization of unfamiliar objects in difficult real-world scenes. The method generates object hypotheses without prior segmentation, which in turn can be used to obtain a category-specific figure-ground segmentation. In particular, the proposed approach uses a probabilistic formulation to incorporate knowledge about the recognized category as well as the supporting information in the image to segment the object from the background. This segmentation can then be used for hypothesis verification, to further improve recognition performance. Experimental results show the capacity of the approach to categorize and segment object categories as diverse as cars and cows.
| Typ des Eintrags: | Buchkapitel |
|---|---|
| Erschienen: | 2006 |
| Autor(en): | Leibe, Bastian ; Schiele, Bernt |
| Art des Eintrags: | Bibliographie |
| Titel: | Interleaving object categorization and segmentation |
| Sprache: | Englisch |
| Publikationsjahr: | 2006 |
| Ort: | Berlin |
| Verlag: | Springer |
| Buchtitel: | Cognitive vision systems : sampling the spectrum of approaches |
| Reihe: | Lecture notes in computer science |
| Band einer Reihe: | 3948 |
| DOI: | 10.1007/11414353_10 |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | In this chapter, we aim to connect the areas of object categorization and figure-ground segmentation. We present a novel method for the categorization of unfamiliar objects in difficult real-world scenes. The method generates object hypotheses without prior segmentation, which in turn can be used to obtain a category-specific figure-ground segmentation. In particular, the proposed approach uses a probabilistic formulation to incorporate knowledge about the recognized category as well as the supporting information in the image to segment the object from the background. This segmentation can then be used for hypothesis verification, to further improve recognition performance. Experimental results show the capacity of the approach to categorize and segment object categories as diverse as cars and cows. |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Multimodale Interaktive Systeme |
| Hinterlegungsdatum: | 20 Nov 2008 08:25 |
| Letzte Änderung: | 29 Nov 2024 09:21 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum