Features invariant to linear transformations in 2D and 3D

Planar objects can be recognized independent of viewpoint using features invariant to affine transformations. Such features can be generated from the image moments using algebraic invariants. This paper shows how to use tensors to generate algebraic invariants in 2D and 3D, and shows that these features are much more robust than affine invariant Fourier descriptors.<<ETX>>

[1]  John A. Orr,et al.  Applications of Tensor Theory to Object Recognition and Orientation Determination , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[3]  Ernest L. Hall,et al.  Three-Dimensional Moment Invariants , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Jun Shen,et al.  Fast computation of moment invariants , 1991, Pattern Recognit..

[5]  Hon-Son Don,et al.  3-D Moment Forms: Their Construction and Application to Object Identification and Positioning , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Rui J. P. de Figueiredo,et al.  A general moment-invariants/attributed-graph method for three-dimensional object recognition from a single image , 1986, IEEE J. Robotics Autom..

[7]  Thomas H. Reiss,et al.  The revised Fundamental Theorem of Moment Invariants , 1991, IEEE Trans. Pattern Anal. Mach. Intell..