Contour Grouping and Object-Based Attention with Saliency Maps

Jingjing ZHONG  Siwei LUO  Jiao WANG  

IEICE TRANSACTIONS on Information and Systems   Vol.E92-D   No.12   pp.2531-2534
Publication Date: 2009/12/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E92.D.2531
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Pattern Recognition
contour grouping,  object-based attention,  saliency map,  

Full Text: PDF(667.5KB)>>
Buy this Article

The key problem of object-based attention is the definition of objects, while contour grouping methods aim at detecting the complete boundaries of objects in images. In this paper, we develop a new contour grouping method which shows several characteristics. First, it is guided by the global saliency information. By detecting multiple boundaries in a hierarchical way, we actually construct an object-based attention model. Second, it is optimized by the grouping cost, which is decided both by Gestalt cues of directed tangents and by region saliency. Third, it gives a new definition of Gestalt cues for tangents which includes image information as well as tangent information. In this way, we can improve the robustness of our model against noise. Experiment results are shown in this paper, with a comparison against other grouping model and space-based attention model.