PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Image Saliency by Isocentric Curvedness and Color
Roberto Valenti, Nicu Sebe and Theo Gevers
In: IEEE International Conference on Computer Vision(2009).

Abstract

In this paper we propose a novel computational method to infer visual saliency in images. The method is based on the idea that salient objects should have local characteristics that are different than the rest of the scene, being edges, color or shape. By using a novel operator, these characteristics are combined to infer global information. The obtained information is used as a weighting for the output of a segmentation algorithm so that the salient object in the scene can easily be distinguished from the background. The proposed approach is fast and it does not require an learning. The experimentation shows that the system can enhance interesting objects in images and it is able to correctly locate the same object annotated by humans with an F-measure of 85:61% when the object size is known, and 79:19% when the object size is unknown, improving the state of the art performance on a public dataset.

EPrint Type:Conference or Workshop Item (Poster)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:6180
Deposited By:Christof Monz
Deposited On:08 March 2010