Extracting Salient Curves from Images: An Analysis of the Saliency Network

The Saliency Network proposed by Shashua and Ullman (1988) is a well-known approach to the problem of extracting salient curves from images while performing gap completion. This paper analyzes the Saliency Network. Although the network is attractive for a number reasons, our analysis reveals certain weaknesses with the method. In particular, we show cases in which the most salient element does not lie on the perceptually most salient curve. Furthermore, the saliency measure may change its preferences when curves are scaled uniformly. Also, for certain fragmented curves the measure prefers large gaps over a few small gaps of the same total size. We analyze the time complexity required by the method and discuss problems due to coarse sampling of the range of possible orientations. We show that with proper sampling the complexity of the network becomes cubic in the size of the network. Finally, we consider the possibility of using the Saliency Network for grouping. We show that the Saliency Network recovers the most salient curve efficiently, but it has problems with identifying any salient curve other than the most salient one.

[1]  Ugo Montanari,et al.  On the optimal detection of curves in noisy pictures , 1971, CACM.

[2]  Alberto Martelli,et al.  An application of heuristic search methods to edge and contour detection , 1976, CACM.

[3]  W. Eric L. Grimson,et al.  Shape Encoding and Subjective Contours , 1980, AAAI.

[4]  M. Brady,et al.  The Perception of Subjective Surfaces , 1981 .

[5]  Berthold K. P. Horn.  The Curve of Least Energy , 1983, TOMS.

[6]  Jon A. Webb,et al.  The Shape of Subjective Contours , 1984, AAAI.

[7]  Isaac Weiss.  3-D Shape Representation by Contours , 1985, IJCAI.

[8]  Stephen Grossberg,et al.  Neural dynamics of surface perception: Boundary webs, illuminants, and shape-from-shading , 1987, Comput. Vis. Graph. Image Process..

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

[11]  Ramesh C. Jain,et al.  Using Dynamic Programming for Solving Variational Problems in Vision , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Theodosios Pavlidis,et al.  Integrating Region Growing and Edge Detection , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Alfred M. Bruckstein,et al.  On Minimal Energy Trajectories , 1990, Comput. Vis. Graph. Image Process..

[14]  S. Ullman,et al.  Grouping Contours by Iterated Pairing Network , 1990, NIPS 1990.

[15]  J. B. Subirana-Vilanova.  Curved Inertia Frames Visual Attention and Perceptual Organization Using Convexity and Symmetry , 1991 .

[16]  R. Nevatia,et al.  Perceptual Organization for Scene Segmentation and Description , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  David W. Jacobs,et al.  Recognizing 3-D Objects Using 2-D Images , 1992 .

[18]  W. Freeman.  Steerable filters and local analysis of image structure , 1992 .

[19]  Leif H. Finkel,et al.  Object Discrimination Based on Depth-from-Occlusion , 1992, Neural Computation.

[20]  J. Brian Subirana-Vilanova,et al.  Multi-Scale Vector-Ridge-Detection for Perceptual Organization Without Edges , 1992 .

[21]  Rüdiger von der Heydt,et al.  A computational model of neural contour processing: Figure-ground segregation and illusory contours , 1993, 1993 (4th) International Conference on Computer Vision.

[22]  Radu Horaud,et al.  Figure-Ground Discrimination: A Combinatorial Optimization Approach , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Allen R. Hanson,et al.  Perceptual completion of occluded surfaces , 1996, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[24]  D. Mumford.  Elastica and Computer Vision , 1994 .

[25]  Lance R. Williams,et al.  Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience , 1995, Neural Computation.

[26]  Alok Gupta,et al.  Dynamic Programming for Detecting, Tracking, and Matching Deformable Contours , 1995, IEEE Trans. Pattern Anal. Mach. Intell..