Abstract | ||
---|---|---|
We consider the use of so-called 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. In a set of examples we show the excellent performance of top-points in an object retrieval task. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11577812_19 | DSSCV |
Keywords | Field | DocType |
interest point,anchor point,object retrieval,closed-form vector equation,object retrieval task,image matching,estimated point,invariant matching scheme,coarse estimation,catastrophe theory,so-called top-points,differential property,scale space | Discrete mathematics,Topology,Feature vector,System of linear equations,Computer science,Closed-form expression,Singularity,Algorithm,Scale space,Catastrophe theory,Invariant (mathematics),Offset (computer science) | Conference |
Volume | ISSN | ISBN |
3753 | 0302-9743 | 3-540-29836-3 |
Citations | PageRank | References |
5 | 0.47 | 12 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Bram Platel | 1 | 245 | 21.42 |
E. Balmachnova | 2 | 24 | 1.75 |
L. M. J. Florack | 3 | 1212 | 210.47 |
F. M. W. Kanters | 4 | 13 | 1.40 |
B. M. Ter Haar Romeny | 5 | 167 | 28.71 |