论文信息 - A Trainable Method of Parametric Shape Description

A Trainable Method of Parametric Shape Description

We have developed a trainable method of shape representation which can automatically capture the invariant properties of a class of shapes and provide a compact parametric description of variability. We have applied the method to a family of flexible ribbons (worms) and to heart shapes in echocardiograms. We show that in both cases a natural parameterisation of shape results.

[1] Keinosuke Fukunaga,et al. Application of the Karhunen-Loève Expansion to Feature Selection and Ordering , 1970, IEEE Trans. Computers.

[2] Charles R. Dyer,et al. Model-based recognition in robot vision , 1986, CSUR.

[3] Kweku-Muata Osei-Bryson,et al. An object location strategy using shape and grey-level models , 1989, Image Vis. Comput..

[4] Christopher J. Taylor,et al. Shape verification using belief updating , 1990, BMVC.

[5] William Grimson,et al. Object recognition by computer - the role of geometric constraints , 1991 .

[6] Christopher J. Taylor,et al. Model-based image interpretation using genetic algorithms , 1992, Image Vis. Comput..

[7] Timothy F. Cootes,et al. Locating Overlapping Flexible Shapes Using Geometrical Constraints , 1991, BMVC.