Shape Matching Using Curvature Processes

Shape matching is a fundamental problem of vision in general atrd interpretation of deforming shapes in particular. The objective of marching in this instance is to recover the deformation and therefore generalizes the notion of correlation, which aims to only produce a numerical me:rsure of the similarity between two shapes. To address shape matching, we introduce a new representation of a closed 2D shape as a cyclic sequence of the extended circular images of the convex and concave segments of its contour. This representation is then used to establish correspondences between segments of the two contours using dynamic programming. Finally, we compute a recrvery of the differences between two similar contours in terms of the action of curvature process. Computation of convex and concave segments of the contours, given in piecewise linear form, is accomplished using the analytic representation of a local B-spline fit. We show the result of our deformation recovery scheme appliedto dynamis cloud silhouette analysis using hand-traced input from real satellite images. o lese Academic Prcss, Inc.

[1]  Farzin Mokhtarian,et al.  Scale-Based Description and Recognition of Planar Curves and Two-Dimensional Shapes , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  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.

[3]  Michael Brady,et al.  The Curvature Primal Sketch , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Larry S. Davis,et al.  Shape Matching Using Relaxation Techniques , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Larry S. Davis,et al.  Understanding Shape: Angles and Sides , 1977, IEEE Transactions on Computers.

[6]  Deborah Walters,et al.  Selection of image primitives for general-purpose visual processing , 1987, Comput. Vis. Graph. Image Process..

[7]  M. Brady,et al.  Smoothed Local Symmetries and Their Implementation , 1984 .

[8]  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.

[9]  Y. J. Tejwani,et al.  Robot vision , 1989, IEEE International Symposium on Circuits and Systems,.

[10]  Linda G. Shapiro,et al.  A Structural Model of Shape , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Jan J. Koenderink,et al.  Inferring 3D Shapes from 2D Codons , 1985 .

[12]  A. Ardeshir Goshtasby,et al.  Comments on "Scale-Based Description and Recognition of Planar Curves and Two-Dimensional Shapes" , 1986, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Theodosios Pavlidis,et al.  Algorithms for Shape Analysis of Contours and Waveforms , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Donald D. Hoffman,et al.  Parts of recognition , 1984, Cognition.

[15]  F. Attneave.  Some informational aspects of visual perception. , 1954, Psychological review.

[16]  John K. Tsotsos,et al.  A framework for visual motion understanding , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  George M. Phillips,et al.  Theory and applications of numerical analysis , 1976, The Mathematical Gazette.

[18]  Michael Leyton,et al.  Symmetry-curvature duality , 1987, Comput. Vis. Graph. Image Process..

[19]  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.

[20]  Michael Leyton,et al.  A Process-Grammar for Shape , 1988, Artif. Intell..

[21]  Patrick Bouthemy,et al.  Modeling of Atmospheric Disturbances in Meteorological Pictures , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.