Indexing based on scale invariant interest points

Krystian Mikolajczyk 1 Cordelia Schmid 1
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : This paper presents a new method for detecting scale invariant interest points. The method is based on two recent results on scale space: (1) Interest points can be adapted to scale and give repeatable results (geometrically stable). (2) Local extrema over scale of normalized derivatives indicate the presence of characteristic local structures. Our method first computes a multi-scale representation for the Harris interest point detector. We then select points at which a local measure (the Laplacian) is maximal over scales. This allows a selection of distinctive points for which the characteristic scale is known. These points are invariant to scale, rotation and translation as well as robust to illumination changes and limited changes of viewpoint. For indexing, the image is characterized by a set of scale invariant points; the scale associated with each point allows the computation of a scale invariant descriptor. Our descriptors are, in addition, invariant to image rotation, of affine illumination changes and robust to small perspective deformations. Experimental results for indexing show an excellent performance up to a scale factor of 4 for a database with more than 5000 images
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download
Contributor : Thoth Team <>
Submitted on : Tuesday, December 21, 2010 - 11:55:17 AM
Last modification on : Wednesday, April 11, 2018 - 1:54:10 AM
Long-term archiving on : Tuesday, March 22, 2011 - 2:33:21 AM


Files produced by the author(s)





Krystian Mikolajczyk, Cordelia Schmid. Indexing based on scale invariant interest points. International Conference on Computer Vision (ICCV '01), Jul 2001, Vancouver, Canada. pp.525--531, ⟨10.1109/ICCV.2001.937561⟩. ⟨inria-00548276⟩



Record views


Files downloads