Transformational invariance - a primer

Abstract The shape of objects seen in images depends on the viewpoint. This effect confounds recognition. We demonstrate a theoretical framework within which it is possible to construct descriptors for curves which do not vary with viewpoint. These descriptors are known as invariants. We use this framework to construct invariant shape descriptors for plane curves. These invariant shape descriptors make it possible to recognise plane curves, without explicitly determining the relationship between the curve reference frame and the camera coordinate system, and can be used to index quickly and efficiently into a large model base of curves. Many of these ideas are demonstrated by experiments on real image data.

[1]  J. Canny.  Finding Edges and Lines in Images , 1983 .

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

[3]  Isaac Weiss,et al.  Projective invariants of shapes , 1988, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[4]  K. Kanatani.  Group-Theoretical Methods in Image Understanding , 1990 .

[5]  David A. Forsyth,et al.  Invariance-a new framework for vision , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[6]  David A. Forsyth,et al.  Projectively invariant representations using implicit algebraic curves , 1990, Image Vis. Comput..

[7]  L. Rabiner,et al.  Isolated and Connected Word Recognition - Theory and Selected Applications , 1981, IEEE Transactions on Communications.

[8]  G. Rota,et al.  The invariant theory of binary forms , 1984 .

[9]  P. Olver.  Applications of lie groups to differential equations , 1986 .

[10]  V. G. Grove,et al.  A Treatise On Projective Differential Geometry , 1942 .

[11]  John Porrill,et al.  Fitting ellipses and predicting confidence envelopes using a bias corrected Kalman filter , 1990, Image Vis. Comput..

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