In this technical demonstration we present a content-based image retrieval system based on the `query by example' paradigm. The system e ectiveness will be proved for both category and target search on two standard image databases, even without a \good" initial exam-ple and ancillary information, such as device metadata, text annotations, etc. These results are obtained by incorporating in the system our re-cently proposed prosemantic features coupled with a relevance feedback mechanism, and by maximizing novelty and diversity in the result sets.
Ciocca, G., Cusano, C., Schettini, R., Santini, S. (2012). Prosemantic Image Retrieval. In 12th European Conference on Computer Vision, ECCV 2012; Florence; Italy; 7-13 October 2012 / Issue PART 3 (pp.643-646) [10.1007/978-3-642-33885-4_72].
Prosemantic Image Retrieval
CIOCCA, GIANLUIGI;CUSANO, CLAUDIO;SCHETTINI, RAIMONDO;
2012
Abstract
In this technical demonstration we present a content-based image retrieval system based on the `query by example' paradigm. The system e ectiveness will be proved for both category and target search on two standard image databases, even without a \good" initial exam-ple and ancillary information, such as device metadata, text annotations, etc. These results are obtained by incorporating in the system our re-cently proposed prosemantic features coupled with a relevance feedback mechanism, and by maximizing novelty and diversity in the result sets.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
