Dept. of Robotics Science and Technology,
Chubu University

Local Image Feature Conference

Multiple-hypothesis affine region estimation with anisotropic LoG filters

Author
Takahiro Hasegawa, Mitsuru Ambai, Kohta Ishikawa, Gou koutaki, Yuji Yamauchi, Takayoshi Yamashita, Hironobu Fujiyoshi
Publication
International Conference on Computer Vision, 2015.

Download: PDF (English)

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.

Previous Next