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 original | Inglés |
---|---|
Páginas | III/305-III/308 |
Estado | Publicada - 2002 |
Publicado de forma externa | Sí |
Evento | International Conference on Image Processing (ICIP'02) - Rochester, NY Duración: 22 set. 2002 → 25 set. 2002 |
Conferencia
Conferencia | International Conference on Image Processing (ICIP'02) |
---|---|
País/Territorio | United States |
Ciudad | Rochester, NY |
Período | 22/09/02 → 25/09/02 |