Extraction of semantic objects from still images

Producción científica: Contribución a una conferenciaArtículorevisión exhaustiva

3 Citas (Scopus)

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]).

Idioma originalInglés
PáginasIII/305-III/308
EstadoPublicada - 2002
Publicado de forma externa
EventoInternational Conference on Image Processing (ICIP'02) - Rochester, NY
Duración: 22 set. 200225 set. 2002

Conferencia

ConferenciaInternational Conference on Image Processing (ICIP'02)
País/TerritorioUnited States
CiudadRochester, NY
Período22/09/0225/09/02

Huella

Profundice en los temas de investigación de 'Extraction of semantic objects from still images'. En conjunto forman una huella única.

Citar esto