Abstract
In this paper we address the problem of object retrieval based on scale-space interest points, namely top-points. The original retrieval algorithm can only cope with scale-Euclidean transformations. We extend the algorithm to the case of non-rigid transformations like affine and perspective transformations and investigate its robustness. The proposed algorithm is proven to be highly robust under various degrading factors, such as noise, occlusion, rendering artifacts, etc. and can deal with multiple occurrences of the object.
Original language | English |
---|---|
Title of host publication | Proceedings of the 11th International Conference on Computer Vision (ICCV 2007) 14-21 October 2007, Rio de Janeiro, Brazil |
Editors | W. Niessen, C.F. Westin, M. Nielsen |
Place of Publication | Piscataway, New Jersey, USA |
Publisher | Institute of Electrical and Electronics Engineers |
Pages | 2591-2598 |
Number of pages | 8 |
ISBN (Print) | 978-1-4244-1631-8 |
DOIs | |
Publication status | Published - 2007 |
Event | 11th International Conference on Computer Vision (ICCV 2007) - Rio de Janeiro, Brazil Duration: 14 Oct 2007 → 21 Oct 2007 |
Conference
Conference | 11th International Conference on Computer Vision (ICCV 2007) |
---|---|
Country/Territory | Brazil |
City | Rio de Janeiro |
Period | 14/10/07 → 21/10/07 |
Other | ICCV 2007, Rio de Janeiro, Brazil |