Por favor, use este identificador para citar o enlazar a este item:
http://hdl.handle.net/10261/166227
COMPARTIR / EXPORTAR:
SHARE BASE | |
Visualizar otros formatos: MARC | Dublin Core | RDF | ORE | MODS | METS | DIDL | DATACITE | |
Título: | BASS: Boundary-aware superpixel segmentation |
Autor: | Rubio Romano, Antonio CSIC; Yu, LongLong; Simo-Serra, Edgar CSIC; Moreno-Noguer, Francesc CSIC ORCID | Fecha de publicación: | 2016 | Editor: | Institute of Electrical and Electronics Engineers | Citación: | 23rd International Conference on Pattern Recognition (ICPR): 2824-2829 (2016) | Resumen: | We propose a new superpixel algorithm based on exploiting the boundary information of an image, as objects in images can generally be described by their boundaries. Our proposed approach initially estimates the boundaries and uses them to place superpixel seeds in the areas in which they are more dense. Afterwards, we minimize an energy function in order to expand the seeds into full superpixels. In addition to standard terms such as color consistency and compactness, we propose using the geodesic distance which concentrates small superpixels in regions of the image with more information, while letting larger superpixels cover more homogeneous regions. By both improving the initialization using the boundaries and coherency of the superpixels with geodesic distances, we are able to maintain the coherency of the image structure with fewer superpixels than other approaches. We show the resulting algorithm to yield smaller Variation of Information metrics in seven different datasets while maintaining Undersegmentation Error values similar to the state-of-the-art methods. | Descripción: | Trabajo presentado a la 23rd International Conference on Pattern Recognition, celebrada en Cancún (México) del 5 al 8 de diciembre de 2016. | Versión del editor: | https://doi.org/10.1109/ICPR.2016.7900064 | URI: | http://hdl.handle.net/10261/166227 | DOI: | 10.1109/ICPR.2016.7900064 | Identificadores: | doi: 10.1109/ICPR.2016.7900064 isbn: 978-1-5090-4847-2 |
Aparece en las colecciones: | (IRII) Libros y partes de libros |
Ficheros en este ítem:
Fichero | Descripción | Tamaño | Formato | |
---|---|---|---|---|
bassbound.pdf | 5,03 MB | Adobe PDF | Visualizar/Abrir |
CORE Recommender
Page view(s)
279
checked on 02-may-2024
Download(s)
266
checked on 02-may-2024
Google ScholarTM
Check
Altmetric
Altmetric
NOTA: Los ítems de Digital.CSIC están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.