This Article 
 Bibliographic References 
 Add to: 
Local Invariants For Recognition
March 1995 (vol. 17 no. 3)
pp. 226-238

Abstract—Geometric invariants are shape descriptors that remain unchanged under geometric transformations such as projection or changing the viewpoint. A new method of obtaining local projective and affine invariants is developed and implemented for real images. Being local, the invariants are much less sensitive to occlusion than global invariants. The invariants’ computation is based on a canonical method. This consists of defining a canonical coordinate system by the intrinsic properties of the shape, independently of the given coordinate system. Since this canonical system is independent of the original one, it is invariant and all quantities defined in it are invariant. The method was applied without the use of a curve parameter. This was achieved by fitting an implicit polynomial to an arbitrary curve in a vicinity of each curve point. Several configurations are treated: a general curve without any correspondence and curves with known correspondences of one or two feature points or lines. Experimental results for different 2D objects in 3D space are presented.

[1] E. Barrett,P. Payton,N. Haag,, and M. Brill,“General methods for determining projective invariants in imagery,” CVGIP:IU, vol. 53, pp. 45-65, 1991.
[2] I.N. Bronshtein,K.A. Semendyayev,Handbook of Mathematics.New York: Van Nostrand, 1985.
[3] A.M. Bruckstein, R.J. Holt, A.N. Netravali, and T.J. Richardson, "Invariant Signatures for Planar Shape Recognition Under Partial Occlusion," CVGIP: Image Understanding, vol. 58, pp. 49-65, July 1993.
[4] H. Burkhardt,A. Fenske,, and H. Schulz-Mirbach,“Invariants for the recognition of planar contour and gray-scale images,” ESPRIT Workshop “Invariants for Recognition,” ECCV 92, 1992.
[5] F.S. Cohen and J.-Y. Wang, “Modeling Image Curve Using Invariant 3-D Object Curve Models—A Path to 3D Recognition and Shape Estimation from Image Contours,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 1, pp. 1-12, Jan. 1994.
[6] R.O. Duda and P.E. Hart,Pattern Recognition and Scene Analysis,New York: Wiley, 1973.
[7] D. Forsyth, J.L. Mundy, A. Zisserman, C. Coelho, A. Heller, and C. Rothwell, "Invariant descriptors for 3-D object recognition and pose," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 10, pp. 971-991, 1991.
[8] H. Guggenheimer,Differential Geometry.New York: Dover, 1963.
[9] M. Halphen,“Sur les invariants différentiels des courbes gauches,” J. Ec. Polyt., vol. 28, no. 1, 1880.
[10] D. Keren,D. Cooper,, and J. Subrahmonia,“Describing complicated objects by implicit polynomials,” IEEE Trans. Pattern Anal. and Machine Intelligence, vol. 16, pp. 13-23, Jan. 1994.
[11] J. Mundy and A. Zisserman,“Appendix_Projective geometry for machine vision,” J. Mundy and A. Zisserman, eds., Geometric Invariances in Computer Vision.Cambridge, Mass.: MIT Press, 1992.
[12] T.H. Reiss,“Recognizing planar object using invariant image features,” Lecture Notes in Computer Science, no. 676. Berlin: Springer-Verlag, 1993.
[13] G. Taubin,“Estimation of planar curves, surfaces, and nonplanar space curves defined by implicit equations with applications to edge and range image segmentation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 11, pp. 1115-1137, Nov. 1991.
[14] L. Van Gool,J. Wagemans,J. Vandeneede,, and A. Oosterlinck,“Similarity extraction and modeling,” 3rd Int’l Conf. on Computer Vision, pp. 530-534, 1990.
[15] I. Weiss,“Projective invariants of shapes,” Proc. DARPA Image Understanding Workshop, pp. 1125-1134, 1988.
[16] I. Weiss,“Noise resistant invariants of shapes,” Proc. DARPA-ESPRIT Workshop on Invariance,Reykjavik, Iceland, March 1991.
[17] I. Weiss, “Geometric Invariants and Object Recognition,” Int'l J. Computer Vision, vol. 10, no. 3, pp. 201-231, June 1993.
[18] I. Weiss,“Noise-resistant invariants of curves,” IEEE Trans. Pattern Anal. and Machine Intelligence, vol. 15, no. 9, pp. 943-948, Sept. 1993.
[19] I. Weiss,“Local projective and affine invariants,” Annals of Mathematics and Artificial Intelligence, Special Issue on Formal Methods in 2D Shape Analysis, to appear.
[20] I. Weiss,“High-order differentiation filters that work,” IEEE Trans. Pattern Anal. and Machine Intelligence, vol. 16, no. 7, pp. 734-739, July 1994.
[21] E.J. Wilczynski,Projective Differential Geometry of Curves and Ruled Surfaces.Leipzig: Teubner, 1906.
[22] H.J. Wolfson, "On Curve Matching," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 5, pp. 483-489, May 1990.

Index Terms:
Object recognition, invariants, image matching, geometry.
Ehud Rivlin, Isaac Weiss, "Local Invariants For Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 3, pp. 226-238, March 1995, doi:10.1109/34.368188
Usage of this product signifies your acceptance of the Terms of Use.