Exploiting Contextual Information in Image Retrieval Tasks

In Content-based Image Retrieval (CBIR) systems, accurately ranking images is of great relevance, since users are interested in the returned images placed at the first positions, which usually are the most relevant ones. In general, CBIR systems consider only pairwise image analysis, that is, compute similarity measures considering only pairs of images, ignoring the rich information encoded in the relations among several images. On the other hand, the user perception usually considers the query specification and responses in a given context. We propose five re-ranking and rank aggregation algorithms aiming at exploit contextual information for improving the effectiveness of CBIR systems. Re-ranking algorithms exploit contextual information, encoded in the relationships among collection images, while rank aggregation approaches have been used to combine results produced by different image descriptors. We also propose approaches for combining the re-ranking and rank aggregation methods and for efficient re-ranking computation on GPUs. Keywords-content-based image retrieval; contextual information; re-ranking; rank aggregation; multimodal retrieval; parallel computing;