Extraction of semantic objects from still images

Alvaro Pardo

Extraction of semantic objects from still images

Alvaro Pardo

Universidad de la República

Research output: Contribution to conference › Paper › peer-review

3 Scopus citations

Abstract

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]).

Original language	English
Pages	III/305-III/308
State	Published - 2002
Externally published	Yes
Event	International Conference on Image Processing (ICIP'02) - Rochester, NY, United States Duration: 22 Sep 2002 → 25 Sep 2002

Conference

Conference	International Conference on Image Processing (ICIP'02)
Country/Territory	United States
City	Rochester, NY
Period	22/09/02 → 25/09/02

Cite this

@conference{d270d0c3b44848e9b31d1c8ad27980b8,

title = "Extraction of semantic objects from still images",

abstract = "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]).",

author = "Alvaro Pardo",

year = "2002",

language = "Ingl{\'e}s",

pages = "III/305--III/308",

note = "International Conference on Image Processing (ICIP'02) ; Conference date: 22-09-2002 Through 25-09-2002",

}

TY - CONF

T1 - Extraction of semantic objects from still images

AU - Pardo, Alvaro

PY - 2002

Y1 - 2002

N2 - 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]).

AB - 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]).

UR - https://www.scopus.com/pages/publications/0036451703

M3 - Artículo

AN - SCOPUS:0036451703

SP - III/305-III/308

T2 - International Conference on Image Processing (ICIP'02)

Y2 - 22 September 2002 through 25 September 2002

ER -

Extraction of semantic objects from still images

Abstract

Conference

Other files and links

Fingerprint

Cite this