Image reconstruction from a fiducial collection of scale space interest points and attributes (e.g. in terms of image derivatives) can be used to make the amount of information contained in them explicit. Previous work by various authors includes both linear and non-linear image reconstruction schemes. In this paper, the authors present new results on image reconstruction using a top point representation of an image. A hierarchical ordering of top points based on a stability measure is presented, comparable to feature strength presented in various other works. By taking this into account our results show improved reconstructions from top points compared to previous work. The proposed top point representation is compared with previously proposed representations based on alternative feature sets, such as blobs using two reconstruction schemes (one linear, one non-linear). The stability of the reconstruction from the proposed top point representation under noise is also considered.
|Title of host publication||Scale Space and PDE Methods in Computer Vision (Proceedings 5th International Conference, Hofgeismar, Germany, April 7-9, 2005)|
|Editors||R. Kimmel, N.A. Sochen, J. Weickert|
|Place of Publication||Berlin|
|Publication status||Published - 2005|
|Name||Lecture Notes in Computer Science|