Integral Invariant Signatures

For shapes represented as closed planar contours, we introduce a class of functionals that are invariant with respect to the Euclidean and similarity group, obtained by performing integral operations. While such integral invariants enjoy some of the desirable properties of their differential cousins, such as locality of computation (which allows matching under occlusions) and uniqueness of representation (in the limit), they are not as sensitive to noise in the data. We exploit the integral invariants to define a unique signature, from which the original shape can be reconstructed uniquely up to the symmetry group, and a notion of scale-space that allows analysis at multiple levels of resolution. The invariant signature can be used as a basis to define various notions of distance between shapes, and we illustrate the potential of the integral invariant representation for shape matching on real and synthetic data.

[1]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[2]  C. E. Springer,et al.  Geometry and Analysis of Projective Spaces , 1967 .

[3]  J. Dieudonne,et al.  Invariant theory, old and new , 1971 .

[4]  Ralph Roskies,et al.  Fourier Descriptors for Plane Closed Curves , 1972, IEEE Transactions on Computers.

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

[6]  Editors , 1986, Brain Research Bulletin.

[7]  Reiner Lenz,et al.  Group Theoretical Methods in Image Processing , 1990, Lecture Notes in Computer Science.

[8]  金谷 健一.  Group-theoretical methods in image understanding , 1990 .

[9]  Wesley E. Snyder,et al.  Application of Affine-Invariant Fourier Descriptors to Recognition of 3-D Objects , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Guo Lei,et al.  Recognition of planar objects in 3-D space from single perspective views using cross ratio , 1990, IEEE Trans. Robotics Autom..

[11]  David A. Forsyth,et al.  Invariant Descriptors for 3D Object Recognition and Pose , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Hiroshi Murase,et al.  A lie group theoretic approach to the invariance problem in feature extraction and object recognition , 1991, Pattern Recognit. Lett..

[13]  Lars Nielsen,et al.  Projective area-invariants as an extension of the cross-ratio , 1991, CVGIP Image Underst..

[14]  Jan-Olof Eklundh,et al.  Shape Representation by Multiscale Contour Approximation , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  David A. Forsyth,et al.  Projectively invariant representations using implicit algebraic curves , 1991, Image Vis. Comput..

[16]  David A. Forsyth,et al.  Canonical Frames for Planar Object Recognition , 1992, ECCV.

[17]  G. Sandini,et al.  Computer Vision — ECCV'92 , 1992, Lecture Notes in Computer Science.

[18]  Andrew Zisserman,et al.  Geometric invariance in computer vision , 1992 .

[19]  L. Gool,et al.  Semi-differential invariants , 1992 .

[20]  Alfred M. Bruckstein,et al.  Invariant signatures for planar shape recognition under partial occlusion , 1992, [1992] Proceedings. 11th IAPR International Conference on Pattern Recognition.

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

[22]  Isaac Weiss.  Noise-Resistant Invariants of Curves , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[23]  Jan Flusser,et al.  Pattern recognition by affine moment invariants , 1993, Pattern Recognit..

[24]  Thomas H. Reiss,et al.  Recognizing Planar Objects Using Invariant Image Features , 1993, Lecture Notes in Computer Science.

[25]  Jean-Michel Morel,et al.  Integral and local affine invariant parameter and application to shape recognition , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[26]  Guillermo Sapiro,et al.  Area and Length Preserving Geometric Invariant Scale-Spaces , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Luc Van Gool,et al.  Matching of 3-D curves using semi-differential invariants , 1995, Proceedings of IEEE International Conference on Computer Vision.

[28]  P. Olver.  Equivalence, Invariants, and Symmetry: References , 1995 .

[29]  David A. Forsyth,et al.  3D Object Recognition Using Invariance , 1995, Artif. Intell..

[30]  Miroslaw Pawlak,et al.  On Image Analysis by Moments , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[31]  Nassir Navab,et al.  Relative Affine Structure: Canonical Model for 3D From 2D Geometry and Applications , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[32]  Eduardo Bayro-Corrochano,et al.  A new framework for the formation of invariants and multiple-view constraints in computer vision , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[33]  Roberto Cipolla,et al.  Computer Vision — ECCV '96 , 1996, Lecture Notes in Computer Science.

[34]  Feng Lin,et al.  Representations that uniquely characterize images modulo translation, rotation, and scaling , 1996, Pattern Recognit. Lett..

[35]  Luc Van Gool,et al.  Affine/ Photometric Invariants for Planar Intensity Patterns , 1996, ECCV.

[36]  Roberto Cipolla,et al.  Affine integral invariants for extracting symmetry axes , 1997, Image Vis. Comput..

[37]  Wageeh Boles,et al.  Recognition of 2D object contours using the wavelet transform zero-crossing representation , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[38]  Ehud Rivlin,et al.  Scale space semi-local invariants , 1997, Image Vis. Comput..

[39]  Dmitry ChetverikovComputer.  Shape Defect Detection in Ferrite Cores , 1997 .

[40]  Dmitry Chetverikov,et al.  Matching for Shape Defect Detection , 1999, CAIP.

[41]  Ronald-Bryan O. Alferez,et al.  Geometric and Illumination Invariants for Object Recognition , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[42]  C. Hann,et al.  Projective Curvature and Integral Invariants , 2002 .

[43]  A. King,et al.  Differential Equations: Group Theoretical Methods , 2003 .

[44]  Mireille Boutin,et al.  Numerically Invariant Signature Curves , 1999, International Journal of Computer Vision.

[45]  Steven Haker,et al.  Differential and Numerically Invariant Signature Curves Applied to Object Recognition , 1998, International Journal of Computer Vision.

[46]  Alfred M. Bruckstein,et al.  Similarity-invariant signatures for partially occluded planar shapes , 1992, International Journal of Computer Vision.

[47]  Guillermo Sapiro,et al.  Affine invariant scale-space , 1993, International Journal of Computer Vision.

[48]  David A. Forsyth,et al.  Planar object recognition using projective shape representation , 1995, International Journal of Computer Vision.

[49]  P. Newstead.  Moduli Spaces and Vector Bundles: Geometric Invariant Theory , 2009 .