Invariant Features from Interest Point Groups

10 years 24 days ago
Invariant Features from Interest Point Groups
This paper approaches the problem of finding correspondences between images in which there are large changes in viewpoint, scale and illumination. Recent work has shown that scale-space `interest points' may be found with good repeatability in spite of such changes. Furthermore, the high entropy of the surrounding image regions means that local descriptors are highly discriminative for matching. For descriptors at interest points to be robustly matched between images, they must be as far as possible invariant to the imaging process. In this work we introduce a family of features which use groups of interest points to form geometrically invariant descriptors of image regions. Feature descriptors are formed by resampling the image relative to canonical frames defined by the points. In addition to robust matching, a key advantage of this approach is that each match implies a hypothesis of the local 2D (projective) transformation. This allows us to immediately reject most of the fals...
Matthew Brown, David G. Lowe
Added 30 Sep 2010
Updated 30 Sep 2010
Type Conference
Year 2002
Where BMVC
Authors Matthew Brown, David G. Lowe
Comments (0)