An Affine Invariant Interest Point Detector
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.
KeywordsImage features matching recognition
Unable to display preview. Download preview PDF.
- 2.A. Baumberg. Reliable feature matching across widely separated views. In Proceedings of the Conference on Computer Vision and Pattern Recognition, Hilton Head Island, South Carolina, USA, pages 774–781, 2000.Google Scholar
- 3.Y. Dufournaud, C. Schmid, and R. Horaud. Matching images with different resolutions. In Proceedings of the Conference on Computer Vision and Pattern Recognition, Hilton Head Island, South Carolina, USA, pages 612–618, 2000.Google Scholar
- 5.C. Harris and M. Stephens. A combined corner and edge detector. In Alvey Vision Conference, pages 147–151, 1988.Google Scholar
- 7.T. Lindeberg. Scale-Space Theory in Computer Vision. Kluwer Publishers, 1994.Google Scholar
- 10.D. G. Lowe. Object recognition from local scale-invariant features. In Proceedings of the 7th International Conference on Computer Vision, Kerkyra, Greece, pages 1150–1157, 1999.Google Scholar
- 11.K. Mikolajczyk and C. Schmid. Indexing based on scale invariant interest points. In Proceedings of the 8th International Conference on Computer Vision, Vancouver, Canada, pages 525–531, 2001.Google Scholar
- 12.P. Pritchett and A. Zisserman. Wide baseline stereo matching. In Proceedings of the 6th International Conference on Computer Vision, Bombay, India, pages 754–760, 1998.Google Scholar
- 13.F. Schaffalitzky and A. Zisserman. Viewpoint invariant texture matching and wide baseline stereo. In Proceedings of the 8th International Conference on Computer Vision, Vancouver, Canada, pages 636–643, 2001.Google Scholar
- 15.D. Tell and S. Carlsson. Wide baseline point matching using affine invariants computed from intensity profiles. In Proceedings of the 6th European Conference on Computer Vision, Dublin, Ireland, pages 814–828, 2000.Google Scholar
- 16.T. Tuytelaars and L. Van Gool. Wide baseline stereo matching based on local, affinely invariant regions. In The Eleventh British Machine Vision Conference, University of Bristol, UK, pages 412–425, 2000.Google Scholar
- 17.Test sequences. http://www.inrialpes.fr/movi/people/Mikolajczyk/Database/