Traditional image classification techniques are based on the analysis of low-level visual features or on textual information. In this paper, we describe a novel solution which tries to improve image analysis and processing algorithms by incorporating keywords and textual annotation produced by humans in a folksonomy environment, namely Flickr. The obtained experimental results demonstrate that the proposed categorization process achieves quite good performances in terms of efficiency and effectiveness.
Automatic categorization of image Databases using Web Folksonomies / P., Capasso; Chianese, Angelo; Moscato, Vincenzo; A., Penta; Picariello, Antonio. - STAMPA. - (2008), pp. 685-690. (Intervento presentato al convegno 0th IEEE International Symposium on Multimedia tenutosi a Berkely (CA, USA) nel 15-17 Dicembre, 2008) [10.1109/ISM.2008.50].
Automatic categorization of image Databases using Web Folksonomies
CHIANESE, ANGELO;MOSCATO, VINCENZO;PICARIELLO, ANTONIO
2008
Abstract
Traditional image classification techniques are based on the analysis of low-level visual features or on textual information. In this paper, we describe a novel solution which tries to improve image analysis and processing algorithms by incorporating keywords and textual annotation produced by humans in a folksonomy environment, namely Flickr. The obtained experimental results demonstrate that the proposed categorization process achieves quite good performances in terms of efficiency and effectiveness.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
