A Factorization Approach to Grouping

The foreground group in a scene may be ‘discovered’ and computed as a factorized approximation to the pairwise affinity of the elements in the scene. A pointwise approximation of the pairwise affinity information may in fact be interpreted as a ‘saliency’ index, and the foreground of the scene may be obtained by thresholding it. An algorithm called ‘affinity factorization’ is thus obtained which may be used for grouping.

[1]  Hans Knutsson,et al.  A Consistency Operation for Line and Curve Enhancement , 1982 .

[2]  A. Pinkus n-Widths in Approximation Theory , 1985 .

[3]  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.

[4]  Steven W. Zucker,et al.  Trace Inference, Curvature Consistency, and Curve Detection , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Christof Koch,et al.  Perceptual contour completion A model based on local, anisotropic, fast-adapting interactions between oriented filters , 1994 .

[6]  T. S. Lee,et al.  Gestalten of Today: Early Processing of Visual Contours and Surfaces , 1996 .

[7]  D. Sagi,et al.  Excitatory-inhibitory network in the visual cortex: psychophysical evidence. , 1997, Proceedings of the National Academy of Sciences of the United States of America.

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