Name
Abstract | ||
|---|---|---|
Over the last 30 years, scale space representations have emerged as a fundamental tool for allowing systems to become increasingly robust against changes in camera viewpoint. Unfortunately, the implementation details that are required to properly construct a scale space representation are not published in the literature. Incorrectly implementing these details will lead to extremely poor system performance. In this paper, we address the practical considerations associated with scale space representations. Our focus is to make explicit how a scale space is constructed, thereby increasing the accessibility of this powerful representation to developers of computer vision systems. |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1109/ICVS.2006.9 | ICVS |
Keywords | Field | DocType |
camera viewpoint,powerful representation,scale space representation,scale space,practical consideration,poor system performance,systems view,computer vision system,implementation detail,fundamental tool,computer vision,robustness,image analysis,kernel,object recognition,feature extraction,system performance | Kernel (linear algebra),Computer vision,Scale-space axioms,Computer science,Scale space,Feature extraction,Robustness (computer science),Blob detection,Artificial intelligence,Extremely Poor,Machine learning,Cognitive neuroscience of visual object recognition | Conference |
ISBN | Citations | PageRank |
0-7695-2506-7 | 4 | 1.06 |
References | Authors | |
6 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ross S. Eaton | 1 | 6 | 1.80 |
| Mark R. Stevens | 2 | 75 | 8.93 |
| Jonah C. McBride | 3 | 30 | 2.74 |
| Greydon T. Foil | 4 | 12 | 2.11 |
| Magnus S. Snorrason | 5 | 4 | 1.06 |