A Min-Cover Approach for Finding Salient Curves

We consider the problem of deriving a global interpretation of an image in terms of a small set of smooth curves. The problem is posed using a statistical model for images with multiple curves. Besides having important applications to edge detection and grouping the curve finding task is a special case of a more general problem, where we want to explain the whole image in terms of a small set of objects. We describe a novel approach for estimating the content of scenes with multiple objects using a min-cover framework that is simple and powerful. The min-cover problem is NP-hard but there is a good approximation algorithm that sequentially selects objects minimizing a "cost per pixel" measure. In the case of curve detection we use a type of best-first search to quickly find good curves for the covering algorithm. The method integrates image data over long curves without relying on binary feature detection. We have applied the curve detection method for finding object boundaries in natural scenes and measured its performance using the Berkeley segmentation dataset.

[1]  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.

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

[3]  Gérard G. Medioni,et al.  Inferring global perceptual contours from local features , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

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

[5]  Donald Geman,et al.  An Active Testing Model for Tracking Roads in Satellite Images , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Eugene Charniak,et al.  Figures of Merit for Best-First Probabilistic Chart Parsing , 1998, Comput. Linguistics.

[7]  Lance R. Williams,et al.  Stochastic Completion Fields: A Neural Model of Illusory Contour Shape and Salience , 1997, Neural Computation.

[8]  Alan L. Yuille,et al.  Bayesian A* Tree Search with Expected O(N) Convergence Rates for Road Tracking , 1999, EMMCVPR.

[9]  Ian H. Jermyn,et al.  Globally Optimal Regions and Boundaries as Minimum Ratio Weight Cycles , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Shimon Ullman,et al.  Class-Specific, Top-Down Segmentation , 2002, ECCV.

[11]  Jitendra Malik,et al.  A Probabilistic Multi-scale Model for Contour Completion Based on Image Statistics , 2002, ECCV.

[12]  Steven W. Zucker,et al.  Sketches with Curvature: The Curve Indicator Random Field and Markov Processes , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Lance R. Williams,et al.  Segmentation of Multiple Salient Closed Contours from Real Images , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Jitendra Malik,et al.  Learning to detect natural image boundaries using local brightness, color, and texture cues , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Lance R. Williams,et al.  A Comparison of Measures for Detecting Natural Shapes in Cluttered Backgrounds , 1998, International Journal of Computer Vision.

[16]  Daniel P. Huttenlocher,et al.  Spatial priors for part-based recognition using statistical models , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[17]  Jitendra Malik,et al.  Scale-invariant contour completion using conditional random fields , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.