Visual Attention Guided Multi-Scale Boundary Detection in Natural Images for Contour Grouping

Jingjing ZHONG  Siwei LUO  Qi ZOU  

IEICE TRANSACTIONS on Information and Systems   Vol.E92-D   No.3   pp.555-558
Publication Date: 2009/03/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E92.D.555
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Image Processing and Video Processing
boundary detection,  selective attention,  global spatial prior,  contour grouping,  

Full Text: PDF(673.4KB)>>
Buy this Article

Boundary detection is one of the most studied problems in computer vision. It is the foundation of contour grouping, and initially affects the performance of grouping algorithms. In this paper we propose a novel boundary detection algorithm for contour grouping, which is a selective attention guided coarse-to-fine scale pyramid model. Our algorithm evaluates each edge instead of each pixel location, which is different from others and suitable for contour grouping. Selective attention focuses on the whole saliency objects instead of local details, and gives global spatial prior for boundary existence of objects. The evolving process of edges through the coarsest scale to the finest scale reflects the importance and energy of edges. The combination of these two cues produces the most saliency boundaries. We show applications for boundary detection on natural images. We also test our approach on the Berkeley dataset and use it for contour grouping. The results obtained are pretty good.