Title :
Robust shape normalization based on implicit representations
Author :
Jiang, Tingting ; Tomasi, Carlo
Author_Institution :
LEAR Group, INRIA Grenoble, Grenoble, France
Abstract :
We introduce a new shape normalization method based on implicit shape representations. The proposed method is robust with respect to deformations and invariant to similarity transformations (translation, isotropic scaling and rotation). The new method has been tested and compared to the classical shape normalization method and previous work in terms of aligning groups of shapes with deformations.
Keywords :
image representation; shape recognition; classical shape normalization method; implicit shape representations; robust shape normalization; shape normalization method; similarity transformations; Animals; Computer science; Computer vision; Deformable models; Density functional theory; Humans; Robustness; Shape; Testing; Visual system;
Conference_Titel :
Pattern Recognition, 2008. ICPR 2008. 19th International Conference on
Conference_Location :
Tampa, FL
Print_ISBN :
978-1-4244-2174-9
Electronic_ISBN :
1051-4651
DOI :
10.1109/ICPR.2008.4761202