Image content classification by using visual terms (Contributo in atti di convegno)

Type
Label
  • Image content classification by using visual terms (Contributo in atti di convegno) (literal)
Anno
  • 2007-01-01T00:00:00+01:00 (literal)
Alternative label
  • Amato G.; Magionami V.; Savino P. (2007)
    Image content classification by using visual terms
    in Second international DELOS Conference, Pisa, Italy, 5-7 December 2007
    (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori
  • Amato G.; Magionami V.; Savino P. (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#titoloVolume
  • Second international DELOS Conference (Pisa, Italy, 5-7 December 2007). Proceedings, pp. CD - ROM. DELOS, 2007 (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#note
  • In: Second international DELOS Conference (Pisa, Italy, 5-7 December 2007). Proceedings, pp. CD - ROM. DELOS, 2007. (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#descrizioneSinteticaDelProdotto
  • ABSTRACT: We propose a technique for automatic recognition of content in images. Our technique uses machine learning methods to build classifiers able to decide about the presence of semantic concepts in images. Our classifiers exploits a representation of images in terms of vectors of visual terms. A visual term represents a set of visually similar regions that can be found in images. An image is indexed by first using a segmentation algorithm to extract regions, then extracted regions are replaced by the visual terms that represent them. We discuss how the set of visual terms is generated and how weights are assigned to visual terms to assess their relevance in images. A learning algorithm for Support Vector Machine is used to obtain a classifiers using training sets of images represented by using visual terms. The proposes technique offers very good performance as demonstrated by the experiments that we performed. (literal)
Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni
  • ISTI-CNR (literal)
Titolo
  • Image content classification by using visual terms (literal)
Abstract
  • We propose a technique for automatic recognition of content in images. Our technique uses machine learning methods to build classifiers able to decide about the presence of semantic concepts in images. Our classifiers exploits a representation of images in terms of vectors of visual terms. A visual term represents a set of visually similar regions that can be found in images. An image is indexed by first using a segmentation algorithm to extract regions, then extracted regions are replaced by the visual terms that represent them. We discuss how the set of visual terms is generated and how weights are assigned to visual terms to assess their relevance in images. A learning algorithm for Support Vector Machine is used to obtain a classifiers using training sets of images represented by using visual terms. The proposes technique offers very good performance as demonstrated by the experiments that we performed. (literal)
Prodotto di
Autore CNR
Insieme di parole chiave

Incoming links:


Autore CNR di
Prodotto
Insieme di parole chiave di
data.CNR.it