Abstract | ||
---|---|---|
We propose a method for estimating multiple-hypothesis affine regions from a keypoint by using an anisotropic Laplacian-of-Gaussian (LoG) filter. Although conventional affine region detectors, such as Hessian/Harris-Affine, iterate to find an affine region that fits a given image patch, such iterative searching is adversely affected by an initial point. To avoid this problem, we allow multiple detections from a single keypoint. We demonstrate that the responses of all possible anisotropic LoG filters can be efficiently computed by factorizing them in a similar manner to spectral SIFT. A large number of LoG filters that are densely sampled in a parameter space are reconstructed by a weighted combination of a limited number of representative filters, called \"eigenfilters\", by using singular value decomposition. Also, the reconstructed filter responses of the sampled parameters can be interpolated to a continuous representation by using a series of proper functions. This results in efficient multiple extrema searching in a continuous space. Experiments revealed that our method has higher repeatability than the conventional methods. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/ICCV.2015.74 | ICCV |
Keywords | DocType | Volume |
continuous space,multiple extrema searching,continuous representation,sampled parameters,reconstructed filter responses,singular value decomposition,eigenfilters,representative filters,parameter space,spectral SIFT,iterative searching,image patch,Hessian/Harris-Affine,affine region detectors,anisotropic Laplacian-of-Gaussian,multiple-hypothesis affine regions,anisotropic LoG filters,multiple-hypothesis affine region estimation | Conference | 2015 |
Issue | ISSN | Citations |
1 | 1550-5499 | 1 |
PageRank | References | Authors |
0.35 | 24 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Takahiro Hasegawa | 1 | 1 | 2.04 |
Mitsuru Ambai | 2 | 48 | 6.36 |
Kohta Ishikawa | 3 | 2 | 0.71 |
Gou Koutaki | 4 | 21 | 15.79 |
Yuji Yamauchi | 5 | 43 | 10.45 |
Takayoshi Yamashita | 6 | 377 | 46.83 |
fujiyoshi | 7 | 730 | 101.43 |