Abstract | ||
---|---|---|
We design a generic contrast and affine invariant planar shape recognition algorithm. By generic, we mean an algorithm which
delivers a list of all shapes two digital images have in common, up to any affine transform or contrast change. Affine invariance
must not be considered as a weak requirement in shape recognition since it is well known that if 3D objects with smooth boundaries
are being observed, then the deformation of the objects’ images, far enough from the occlusion boundaries, is locally an affine
transform. We define as ”shape elements” all pieces of level lines of the image. We then discuss an efficient local encoding
of the shape elements. We finally show experiments. Applications aimed at include image registration, image indexing, optical
flow.
|
Year | DOI | Venue |
---|---|---|
2000 | 10.1007/10722604_2 | AMDO |
Keywords | Field | DocType |
partial occlusions,shape recognition algorithm robust,affine deformations,optical flow,image registration,digital image,affine transformation | Affine involution,Affine transformation,Computer vision,Affine shape adaptation,Harris affine region detector,Affine combination,Computer science,Affine coordinate system,Artificial intelligence,Optical flow,Image registration | Conference |
Volume | ISSN | ISBN |
1899 | 0302-9743 | 3-540-67912-X |
Citations | PageRank | References |
0 | 0.34 | 15 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jose Luis Lisani | 1 | 42 | 8.41 |
Lionel Moisan | 2 | 599 | 38.20 |
Pascal Monasse | 3 | 255 | 21.14 |
Jean-Michel Morel | 4 | 3590 | 228.85 |