Abstract | ||
---|---|---|
We consider the use of top-points for object retrieval. These points are based on scale-space and catastrophe theory, and are invariant under gray value scaling and offset as well as scale-Euclidean transformations. The differential properties and noise characteristics of these points are mathematically well understood. It is possible to retrieve the exact location of a top-point from any coarse estimation through a closed-form vector equation which only depends on local derivatives in the estimated point. All these properties make top-points highly suitable as anchor points for invariant matching schemes. By means of a set of repeatability experiments and receiver-operator-curves we demonstrate the performance of top-points and differential invariant features as image descriptors. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11744023_33 | ECCV |
Keywords | Field | DocType |
interest point,anchor point,closed-form vector equation,image matching,estimated point,differential invariant feature,invariant matching scheme,gray value scaling,coarse estimation,catastrophe theory,exact location,differential property,receiver operator curve,scale space | Computer science,Image processing,Singularity,Scale space,Artificial intelligence,Differential invariant,Computer vision,Topology,Feature vector,Algorithm,Catastrophe theory,Invariant (mathematics),Offset (computer science) | Conference |
Volume | ISSN | ISBN |
3951 | 0302-9743 | 3-540-33832-2 |
Citations | PageRank | References |
14 | 0.80 | 12 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bram Platel | 1 | 245 | 21.42 |
E. Balmachnova | 2 | 24 | 1.75 |
L. M. J. Florack | 3 | 1212 | 210.47 |
B. M. Ter Haar Romeny | 4 | 167 | 28.71 |