A unified framework for image-derived invariants
We propose a general framework for computing invariant features from images. The proposed approach is based on a simple concept of basis expansion. It is widely applicable to many popular basis representations, such as wavelets, short-time Fourier transform, and splines.
Unable to display preview. Download preview PDF.
- 1.I. Daubechies. Orthonormal Bases of Compactly Supported Wavelets. Comm-Pure Appl. Math., 41:909–960, 1988.Google Scholar
- 2.H. W. Guggenheimer. Differential Geometry. M.Graw-Hill, New York, 1963.Google Scholar
- 3.T. H. Reiss. Recognizing Planar Objects Using Invariant Image Features. Springer-Verlag, Berlin, 1993.Google Scholar
- 4.D. F. Roger. and J. A. Adams. Mathematical Elements for Computer Graphics, 2nd Ed. McGraw-Hill, New York, NY, 1990.Google Scholar
- 5.Y. F. Wang. A New Framework for Image Invariants using Basis Expansion. Technical Report TRCS97-02, Dept. of Computer Science, UCSB, Feb. 1997.Google Scholar
- 6.I. Weiss. Geometric Invariants and Object Recognition. It. J. Comput. Vision, 10(3):207–231, 1993.Google Scholar