Multiple-Hypothesis Affine Region Estimation With Anisotropic LoG Filters
Takahiro Hasegawa, Mitsuru Ambai, Kohta Ishikawa, Gou Koutaki, Yuji Yamauchi, Takayoshi Yamashita, Hironobu Fujiyoshi
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.
BibTeX
@inproceedings{iccv2015_multiplehypothes,
title = {Multiple-Hypothesis Affine Region Estimation With Anisotropic LoG Filters},
author = {Takahiro Hasegawa and Mitsuru Ambai and Kohta Ishikawa and Gou Koutaki and Yuji Yamauchi and Takayoshi Yamashita and Hironobu Fujiyoshi},
booktitle = {ICCV 2015},
year = {2015}
}