Paper Info
Title
Multiple-Hypothesis Affine Region Estimation With Anisotropic LoG Filters
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 Hasegawa112.04
Mitsuru Ambai2486.36
Kohta Ishikawa320.71
Gou Koutaki42115.79
Yuji Yamauchi54310.45
Takayoshi Yamashita637746.83
fujiyoshi7730101.43