Saliency of Interest Points under Scale Changes

Interest point detectors are commonly employed to reduce the amount of data to be processed. The ideal interest point detector would robustly select those features which are most appropriate or salient for the application and data at hand. There is however a tradeoff between the robustness and the discriminance of the selected features. Whereas robustness in terms of repeatability is relatively well explored, the discriminance of interest points is rarely discussed. This paper formalizes the notion of saliency and evaluates three state-of-the-art interest point detectors with respect to their capability of selecting salient image features in two recognition settings.

[1]  Cordelia Schmid,et al.  Indexing Based on Scale Invariant Interest Points , 2001, ICCV.

[2]  Bernt Schiele,et al.  Recognition without Correspondence using Multidimensional Receptive Field Histograms , 2004, International Journal of Computer Vision.

[3]  Patrick J. Flynn.  Saliencies and symmetries: toward 3D object recognition from large model databases , 1992, CVPR.

[4]  Arnold W. M. Smeulders,et al.  Color and Scale: The Spatial Structure of Color Images , 2000, ECCV.

[5]  J. T. Robinson,et al.  The K-D-B-tree: a search structure for large multidimensional dynamic indexes , 1981, SIGMOD '81.

[6]  Nicu Sebe,et al.  Salient Points for Content-Based Retrieval , 2001, BMVC.

[7]  Katsushi Ikeuchi,et al.  Detectability, Uniqueness, and Reliability of Eigen Windows for Stable Verification of Partially Occluded Objects , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[10]  Bernt Schiele,et al.  Probabilistic object recognition using multidimensional receptive field histograms , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[11]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[12]  J. Koenderink,et al.  Representation of local geometry in the visual system , 1987, Biological Cybernetics.

[13]  Tony Lindeberg,et al.  Feature Detection with Automatic Scale Selection , 1998, International Journal of Computer Vision.

[14]  Rajesh P. N. Rao,et al.  An Active Vision Architecture Based on Iconic Representations , 1995, Artif. Intell..

[15]  James L. Crowley,et al.  Visual Recognition Using Local Appearance , 1998, ECCV.

[16]  Timothy F. Cootes,et al.  Locating Salient Object Features , 1998, BMVC.

[17]  James L. Crowley,et al.  Object Recognition Using Coloured Receptive Fields , 2000, ECCV.