Content-based Access in Image Database by Quantitative Relationships

In this paper, we describe a novel technique to perform content-based access in image databases using quantitative spatial relationships. Usually, spatial relation-based indexing methods fail if the metric spatial information contained in the images must be preserved. In order to provide a more robu...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Journal of visual languages and computing Ročník 11; číslo 5; s. 573 - 589
Hlavní autoři: CIBELLI, MAURIZIO, NAPPI, MICHELE, TUCCI, MAURIZIO
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 2000
ISSN:1045-926X
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, we describe a novel technique to perform content-based access in image databases using quantitative spatial relationships. Usually, spatial relation-based indexing methods fail if the metric spatial information contained in the images must be preserved. In order to provide a more robust approach to directional relations indexing with respect to metric differences in images, this paper introduces an improvement of the virtual image index, namely quantitative virtual image, using a quantitative methodology. A scalar quantitative measure is associated with each spatial relation, in order to discriminate among images of the image database having the same objects and spatial relationships, but different degree of similarity if we also consider distance relationships. The measure we introduce does not correspond to any significant increase of complexity with respect to the standard virtual image providing a more precise answer set.
ISSN:1045-926X
DOI:10.1006/jvlc.2000.0171