Abstract | ||
---|---|---|
A region based saliency detection method is proposed.A region extraction method is proposed to group similar elements into a region.Surroundedness is proposed for saliency detection.Surroundedness is measured via the average outer contour confidence of a region. In this paper, a surroundedness-based multiscale saliency method is proposed based on the Gestalt principles for figure-ground segregation, which states that (1) surrounded regions are more likely to be perceived as figures, (2) the humans understand the external stimuli as whole rather than the sum of their parts. First, an image is characterized by a set of binary images, which is generated by a simple and effective homogeneous region extraction method with well contour preservation. And the contour confidence map is obtained by a fast contour detection method. Then for each connect homogeneous region in a binary map, surroundedness is defined by the average outer contour confidence. Finally, integrating the background priors, multiscale saliency maps are generated and combined to the final saliency map. The proposed method is evaluated on two widely used public datasets with pixel accurate salient region annotations using both precision and recall analysis and ROC analysis. And the experimental results show that the proposed method outperforms 14 alternative methods. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1016/j.jvcir.2015.09.017 | Journal of Visual Communication and Image Representation |
Keywords | Field | DocType |
Saliency detection,Figure-ground segregation,The Gestalt principles,Image decomposition,Homogeneous region extraction,Surroundedness,Multiscale,Contour confidence | Computer vision,Pattern recognition,Salience (neuroscience),Precision and recall,Binary image,Gestalt psychology,Artificial intelligence,Pixel,Prior probability,Mathematics,Binary number,Salient | Journal |
Volume | Issue | ISSN |
33 | C | 1047-3203 |
Citations | PageRank | References |
3 | 0.38 | 34 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Beiji Zou | 1 | 231 | 41.61 |
Qing Liu | 2 | 19 | 3.99 |
Zailiang Chen | 3 | 43 | 9.10 |
Hongpu Fu | 4 | 3 | 0.38 |
chengzhang zhu | 5 | 15 | 3.91 |