Extraction of semantic objects from still images
- Autor(es):
- Pardo, Alvaro
- Tipo:
- Artículo
- Versión:
- Publicado
- Resumen:
-
In this work, we study the extraction of semantic objects from still images. We combine different ideas to extract them in a structured manner together with a perceptual metric that ranks them according with its perceptual relevance. The algorithm has four steps, the regularization of the initial segmentation using probability diffusion [1], simplification of the segmentation via region merging, computation of the perceptual metric based on [2] and construction of the structure that represents the image (the binary partition tree [3]).
- Año:
- 2002
- Idioma:
- Inglés
- Temas:
- Image segmentation
Feature extraction
Still images
- Institución:
- Universidad de la República
- Repositorio:
- COLIBRI
- Enlace(s):
- https://hdl.handle.net/20.500.12008/21219
- Nivel de acceso:
- Acceso abierto