Segmentation of salient closed contours from real images

Using a saliency measure based on the global property of contour closure, we have developed a method that reliably segments out salient contours bounding unknown objects from real edge images. The measure also incorporates the Gestalt principles of proximity and smooth continuity that previous methods have exploited. Unlike previous measures, we incorporate contour closure by finding the eigen-solution associated with a stochastic process that models the distribution of contours passing through edges in the scene. The segmentation algorithm utilizes the saliency measure to identify multiple closed contours by finding strongly-connected components on an induced graph. The determination of strongly-connected components is a direct consequence of the property of closure. We report for the first time, results on large real images for which segmentation takes an average of about 10 secs per object on a general-purpose workstation. The segmentation is made efficient for such large images by exploiting the inherent symmetry in the task.

[1]  Pietro Perona,et al.  A Factorization Approach to Grouping , 1998, ECCV.

[2]  Lance R. Williams,et al.  Analytic solution of stochastic completion fields , 1995, Biological Cybernetics.

[3]  Lance R. Williams,et al.  A Comparison of Measures for Detecting Natural Shapes in Cluttered Backgrounds , 1998, ECCV.

[4]  David W. Jacobs.  Robust and efficient detection of convex groups , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Lance R. Williams,et al.  Local Parallel Computation of Stochastic Completion Fields , 1997, Neural Computation.

[6]  K. Thornber,et al.  Analytic solution of stochastic completion fields , 1995, Proceedings of International Symposium on Computer Vision - ISCV.

[7]  Steven W. Zucker,et al.  Computing Contour Closure , 1996, ECCV.

[8]  David G. Lowe,et al.  Perceptual Organization and Visual Recognition , 2012 .

[9]  Shimon Ullman,et al.  Structural Saliency: The Detection Of Globally Salient Structures using A Locally Connected Network , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[10]  Kim L. Boyer,et al.  Quantitative measures of change based on feature organization: eigenvalues and eigenvectors , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.