Name
Title | ||
|---|---|---|
A fast illumination and deformation insensitive image comparison algorithm using wavelet-based geodesics |
Abstract | ||
|---|---|---|
We present a fast image comparison algorithm for handling variations in illumination and moderate amounts of deformation using an efficient geodesic framework. As the geodesic is the shortest path between two images on a manifold, it is a natural choice to use the length of the geodesic to determine the image similarity. Distances on the manifold are defined by a metric that is insensitive to changes in scene lighting. This metric is described in the wavelet domain where it is able to handle moderate amounts of deformation, and can be calculated extremely fast (less than 3ms per image comparison). We demonstrate the similarity between our method and the illumination insensitivity achieved by the Gradient Direction. Strong results are presented on the AR Face Database. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1007/978-3-642-33765-9_6 | ECCV (4) |
Keywords | Field | DocType |
efficient geodesic framework,image similarity,gradient direction,wavelet-based geodesic,deformation insensitive image comparison,fast image comparison algorithm,image comparison,illumination insensitivity,moderate amount,natural choice,ar face database,scene lighting,fast illumination | Computer vision,Facial recognition system,Image gradient,Shortest path problem,Gradient direction,Computer science,Algorithm,Artificial intelligence,Deformation (mechanics),Geodesic,Manifold,Wavelet | Conference |
Volume | ISSN | Citations |
7575 | 0302-9743 | 1 |
PageRank | References | Authors |
0.35 | 12 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Anne Jorstad | 1 | 46 | 4.74 |
| David W. Jacobs | 2 | 4599 | 348.03 |
| Alain Trouvé | 3 | 1248 | 106.40 |