Potentials, valleys, and dynamic global coverings

We present a new approach to effect the transition between local and global representations. It is based on the notion of a covering, or a collection of objects whose union is equivalent to the full one. The mathematics of computing global coverings are developed in the context of curve detection, where an intermediate representation (the tangent field) provides a reliable local description of curve structure. This local information is put together globally in the form of a potential distribution. The elements of the covering are then short curves, each of which evolves in parallel to seek the valleys of the potential distribution. The initial curve positions are also derived from the tangent field, and their evolution is governed by variational principles. When stationary configurations are achieved, the global dynamic covering is defined by the union of the local dynamic curves.

[1]  S. Zucker,et al.  Endstopped neurons in the visual cortex as a substrate for calculating curvature , 1987, Nature.

[2]  David G. Lowe,et al.  Organization of smooth image curves at multiple scales , 1988, International Journal of Computer Vision.

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

[4]  Steven W. Zucker,et al.  Inferring Surface Trace and Differential Structure from 3-D Images , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Tunc Geveci,et al.  Advanced Calculus , 2014, Nature.

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

[7]  J. Doob.  Classical potential theory and its probabilistic counterpart , 1984 .

[8]  Steven W. Zucker,et al.  From orientation selection to optical flow , 1987, Comput. Vis. Graph. Image Process..

[9]  Steven W. Zucker,et al.  On the Foundations of Relaxation Labeling Processes , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[11]  Demetri Terzopoulos,et al.  Matching deformable models to images: Direct and iterative solutions , 1980 .

[12]  David J. Evans,et al.  Algorithm 512: A Normalized Algorithm for Solution of Positive Definite Symmetric Quindiagonal Systems of Linear Equations [F4] , 1977, TOMS.

[13]  Steven W. Zucker,et al.  The Organization Of Curve Detection: Coarse Tangent Fields And Fine Spline Coverings , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[14]  Demetri Terzopoulos,et al.  On Matching Deformable Models to Images , 1987, Topical Meeting on Machine Vision.

[15]  Andrew Blake,et al.  Visual Reconstruction , 1987, Deep Learning for EEG-Based Brain–Computer Interfaces.

[16]  Steven W. Zucker,et al.  Two Stages of Curve Detection Suggest Two Styles of Visual Computation , 1989, Neural Computation.

[17]  Bruce A. Draper,et al.  The schema system , 1988, International Journal of Computer Vision.

[18]  Andrew P. Witkin,et al.  Analyzing Oriented Patterns , 1985, IJCAI.

[19]  Steven W. Zucker,et al.  Early orientation selection: Tangent fields and the dimensionality of their support , 1985, Comput. Vis. Graph. Image Process..

[20]  Demetri Terzopoulos,et al.  Image Analysis Using Multigrid Relaxation Methods , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  S. Zucker.  THE EMERGING PARADIGM OF COMPUTATIONAL VISION , 1987 .

[22]  T. Poggio.  Vision by man and machine. , 1984, Scientific American.

[23]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[24]  Azriel Rosenfeld,et al.  Computer Vision , 1988, Adv. Comput..