Title :
A hybrid approach for retrieving diverse social images of landmarks
Author :
Duc-Tien Dang-Nguyen ; Piras, Luca ; Giacinto, Giorgio ; Boato, Giulia ; De Natale, Francesco G. B.
Author_Institution :
DIEE, Univ. of Cagliari, Cagliari, Italy
fDate :
June 29 2015-July 3 2015
Abstract :
In this paper, we present a novel method that can produce a visual description of a landmark by choosing the most diverse pictures that best describe all the details of the queried location from community-contributed datasets. The main idea of this method is to filter out non-relevant images at a first stage and then cluster the images according to textual descriptors first, and then to visual descriptors. The extraction of images from different clusters according to a measure of user´s credibility, allows obtaining a reliable set of diverse and relevant images. Experimental results performed on the MediaEval 2014 “Retrieving Diverse Social Images” dataset show that the proposed approach can achieve very good performance outperforming state-of-art techniques.
Keywords :
image filtering; image retrieval; pattern clustering; MediaEval 2014; image clustering; image extraction; landmark visual description; social images retrieval; textual descriptors; visual descriptors; Clustering algorithms; Face; Filtering; Histograms; Image color analysis; TV; Visualization; Diversity; Social Image Retrieval;
Conference_Titel :
Multimedia and Expo (ICME), 2015 IEEE International Conference on
Conference_Location :
Turin
DOI :
10.1109/ICME.2015.7177486