Image saliency by isocentric curvedness and color
Authors:
- 1 September 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 2185-2192
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 any 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.Keywords
This publication has 25 references indexed in Scilit:
- Modelling Spatio-Temporal Saliency to Predict Gaze Direction for Short VideosInternational Journal of Computer Vision, 2009
- Learning to Detect A Salient Object2007
- Robust Object Recognition with Cortex-Like MechanismsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2007
- A coherent computational approach to model bottom-up visual attentionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Isophote Properties as Features for Object Detection2005
- Focus-of-attention from local color symmetriesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Learning to detect natural image boundaries using local brightness, color, and texture cuesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2004
- Contrast-based image attention analysis by using fuzzy growing2003
- Fast radial symmetry for detecting points of interestIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- Local grayvalue invariants for image retrievalIEEE Transactions on Pattern Analysis and Machine Intelligence, 1997