DMCA
An affine invariant interest point detector (2002)
Cached
Download Links
| Venue: | In Proceedings of the 7th European Conference on Computer Vision |
| Citations: | 1467 - 55 self |
BibTeX
@INPROCEEDINGS{Mikolajczyk02anaffine,
author = {Krystian Mikolajczyk and Cordelia Schmid},
title = {An affine invariant interest point detector},
booktitle = {In Proceedings of the 7th European Conference on Computer Vision},
year = {2002},
pages = {0--7}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. This paper presents a novel approach for detecting affine invariant interest points. Our method can deal with significant affine transformations including large scale changes. Such transformations introduce significant changes in the point location as well as in the scale and the shape of the neighbourhood of an interest point. Our approach allows to solve for these problems simultaneously. It is based on three key ideas: 1) The second moment matrix computed in a point can be used to normalize a region in an affine invariant way (skew and stretch). 2) The scale of the local structure is indicated by local extrema of normalized derivatives over scale. 3) An affine-adapted Harris detector determines the location of interest points. A multi-scale version of this detector is used for initialization. An iterative algorithm then modifies location, scale and neighbourhood of each point and converges to affine invariant points. For matching and recognition, the image is characterized by a set of affine invariant points; the affine transformation associated with each point allows the computation of an affine invariant descriptor which is also invariant to affine illumination changes. A quantitative comparison of our detector with existing ones shows a significant improvement in the presence of large affine deformations. Experimental results for wide baseline matching show an excellent performance in the presence of large perspective transformations including significant scale changes. Results for recognition are very good for a database with more than 5000 images.
Keyphrases
affine invariant interest point detector interest point affine invariant interest point point location large perspective transformation novel approach affine transformation invariant point normalized derivative significant improvement large affine deformation affine invariant way wide baseline affine invariant point significant affine transformation local structure significant change local extremum affine invariant descriptor illumination change multi-scale version key idea iterative algorithm second moment matrix affine-adapted harris detector quantitative comparison large scale change experimental result excellent performance significant scale change
