Name
Abstract | ||
|---|---|---|
In this paper we describe a feature-based approach to object recognition. The correspondence problem is solved by optimization of an energy function. While similar approaches suffer from local minima, we derive an energy function suitable for minimizing by deterministic annealing. Hereby global optimization can be achieved. Algorithms matching model features to image features in a coarse-to-fine manner are described. |
Year | DOI | Venue |
|---|---|---|
1997 | 10.1016/S0262-8856(97)00025-5 | Image and Vision Computing |
Keywords | Field | DocType |
Object recognition,Correspondence problem,Deterministic annealing optimization,Maximum entropy method | Mathematical optimization,Global optimization,Feature (computer vision),Image processing,Maximum entropy method,Algorithm,Maxima and minima,Deterministic annealing,Correspondence problem,Mathematics,Cognitive neuroscience of visual object recognition | Journal |
Volume | Issue | ISSN |
15 | 11 | 0262-8856 |
Citations | PageRank | References |
4 | 1.42 | 9 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Detlev Noll | 1 | 53 | 8.62 |
| W von Seelen | 2 | 503 | 140.13 |