Shape Representation and Recognition from Multiscale Curvature

We present a technique for shape representation and the recognition of objects based on multiscale curvature information. It provides a single framework for both the decomposition and recognition of both planar curves as well as surfaces in three-dimensional space. The decomposition operation simultaneously performs data interpolation, data smoothing, and segmentation. The unification of these three stages results in a smoothing operation that is coupled with the primitives to be used in description. Each of the minimization operators, in addition to having a curvature tuning, also has a different spatial sensitivity function. As a result, the different possible descriptions capture information at multiple spatial scales. This allows a single region of an object to be described in more than one way, when appropriate. The practicality of the ensuing representation is demonstrated by the recognition of planar curves. A matching strategy based on dynamic programming is used. The results illustrate the manner in which a continuous spectrum of similar objects can be defined, ranging from those that are very similar to a target to those that are very different from it.

[1]  Benjamin B. Kimia,et al.  On the evolution of curves via a function of curvature , 1992 .

[2]  W. R. Garner,et al.  Filtering and condensation tasks with integral and separable dimensions , 1975 .

[3]  Lawrence C. Sager,et al.  Perception of wholes and of their component parts: some configural superiority effects. , 1977, Journal of experimental psychology. Human perception and performance.

[4]  Evangelos E. Milios,et al.  Recovering Shape Deformation By An Extended Circular Image Representation , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[5]  Paul L. Rosin Representing curves at their natural scales , 1992, Pattern Recognit..

[6]  Donald D. Hoffman,et al.  Codon constraints on closed 2D shapes , 1985, Comput. Vis. Graph. Image Process..

[7]  Edward J. Delp,et al.  Invariant reconstruction of visual surfaces , 1989, [1989] Proceedings. Workshop on Interpretation of 3D Scenes.

[8]  Owen Robert Mitchell,et al.  Partial Shape Recognition Using Dynamic Programming , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  K. Rektorys Variational Methods in Mathematics, Science and Engineering , 1977 .

[10]  H. Piaggio Differential Geometry of Curves and Surfaces , 1952, Nature.

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

[12]  D. Mumford,et al.  Optimal approximations by piecewise smooth functions and associated variational problems , 1989 .

[13]  John K. Tsotsos,et al.  Using Curvature Information in the Decomposition and Representation of Planar Curves , 1992 .

[14]  Farzin Mokhtarian,et al.  A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Michael Werman,et al.  Variations on regularization , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[16]  Nasser Kehtarnavaz,et al.  A 3-D Contour Segmentation Scheme Based on Curvature and Torsion , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Andrew P. Witkin,et al.  Scale-Space Filtering , 1983, IJCAI.

[18]  Paul L. Rosin Multiscale Representation and Matching of Curves Using Codons , 1993, CVGIP Graph. Model. Image Process..

[19]  William I. Grosky,et al.  Shape matching utilizing indexed hypotheses generation and testing , 1989, IEEE Trans. Robotics Autom..

[20]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Gregory Dudek Shape metrics from curvature-scale space and curvature-tuned smoothing , 1991, Optics & Photonics.

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

[23]  Anand Rangarajan,et al.  Generalized graduated nonconvexity algorithm for maximum a posteriori image estimation , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[24]  R. Courant,et al.  Methods of Mathematical Physics , 1962 .

[25]  Gil J. Ettinger,et al.  Large hierarchical object recognition using libraries of parameterized model sub-parts , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[26]  John K. Tsotsos Knowledge and the visual process: Content, form and use , 1984, Pattern Recognit..

[27]  David H. Marimont A Representation for Image Curves , 1984, AAAI.

[28]  Kaleem Siddiqi,et al.  Geometric heat equation and nonlinear diffusion of shapes and images , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[29]  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.

[30]  John K. Tsotsos,et al.  Shape representation and recognition from curvature , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[31]  John Oliensis Local Reproducible Smoothing Without Shrinkage , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  Eric Saund,et al.  Adding scale to the primal sketch , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[33]  Tony P. Pridmore,et al.  Segmentation and description of binocularly viewed contours , 1987, Image Vis. Comput..

[34]  Lawrence B. Wolff,et al.  Segmentation of surface curvature using a photometric invariant , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[35]  Manfredo P. do Carmo,et al.  Differential geometry of curves and surfaces , 1976 .

[36]  Eric L. W. Grimson,et al.  From Images to Surfaces: A Computational Study of the Human Early Visual System , 1981 .

[37]  Olivier D. Faugeras,et al.  HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[38]  Demetri Terzopoulos,et al.  Regularization of Inverse Visual Problems Involving Discontinuities , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[39]  Alan C. Bovik,et al.  Improved initial approximation and intensity-guided discontinuity detection in visible-surface reconstruction , 1989, Comput. Vis. Graph. Image Process..

[40]  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.

[41]  David G. Lowe,et al.  Perceptual Organization and Visual Recognition , 2012 .

[42]  Demetri Terzopoulos,et al.  The Role of Constraints and Discontinuities in Visible-Surface Reconstruction , 1983, IJCAI.

[43]  Demetri Terzopoulos,et al.  Multiresolution computation of visible-surface representations , 1984 .

[44]  David G. Lowe,et al.  Stabilized Solution For 3-D Model Parameters , 1990, ECCV.

[45]  Paul J. Besl,et al.  Surfaces in Range Image Understanding , 1988, Springer Series in Perception Engineering.

[46]  J. Koenderink,et al.  Photometric Invariants Related to Solid Shape , 1980 .

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

[48]  A.L Yuille,et al.  Zero crossings on lines of curvature , 1989, Comput. Vis. Graph. Image Process..

[49]  Eric Saund,et al.  The role of knowledge in visual shape representation , 1988 .

[50]  Edward J. Delp,et al.  Partial Shape Recognition: A Landmark-Based Approach , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[51]  Pengfei Zhu,et al.  On Critical Point Detection of Digital Shapes , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[52]  Pnvid H Ivl,et al.  A Representation for Image Curves , 1984, AAAI.

[53]  T. R. Tauchert,et al.  Large deformation and postbuckling behavior of an initially deformed rod , 1987 .

[54]  Marcel Worring,et al.  Digital curvature estimation , 1993 .

[55]  Tomaso Poggio,et al.  Probabilistic Solution of Ill-Posed Problems in Computational Vision , 1987 .

[56]  Naonori Ueda,et al.  Automatic shape model acquisition using multiscale segment matching , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

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