In this work we present a low-dimensional color fragmentation-weighted histogram technique specifically designed for the query by sketch approach. It keeps into account the fragmentation colors have in an image and the assumption that the number of colors typically present in a sketch are almost always just a few. The algorithm has been implemented in DrawSearch, our prototype CBIR system. According to our experiments, the algorithm outperforms classic histograms and compares favorably with much more complex techniques

Color fragmentation-weighted histogram for sketch based image queries

DI SCIASCIO, Eugenio;GUARAGNELLA, Cataldo;MONGIELLO, Marina
2000

Abstract

In this work we present a low-dimensional color fragmentation-weighted histogram technique specifically designed for the query by sketch approach. It keeps into account the fragmentation colors have in an image and the assumption that the number of colors typically present in a sketch are almost always just a few. The algorithm has been implemented in DrawSearch, our prototype CBIR system. According to our experiments, the algorithm outperforms classic histograms and compares favorably with much more complex techniques
10th European Signal Processing Conference, EUSIPCO 2000
978-952-1504-43-3
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11589/13757
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
social impact