Abstract
The ubiquitous growth of multimedia production is causing the creation of new visual information retrieval paradigms. One of the most relevant among them is that represented by Visual Information Retrieval Systems (VIRS), where a common task is ordering a set images according to their similarity to a given one. In this work a new proposal for evaluating similarity between two images is introduced; both images are represented by respective feature vectors, and the perceptual cue used to generate the similarity measure is saliency, a concept thoroughly known in Psychology. New methodologies for quantifying saliency of feature values, for combining them during a comparison process and, eventually, to weight that feature attending to the result of the combination, are introduced as well. The results for the evaluation of this similarity measure in an image based content retrieval task are presented, as well as their comparison with those obtained using euclidean distance in the same task. Both are validated by volunteers who labelled the retrieved sets.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have