View-Based Object Matching
Abstract
We introduce a novel view-based object representation, called the saliency map graph (SMG), which captures the salient regions of an object view at multiple scales using a wavelet transform. This compact representation is highly invariant to translation, rotation (image and depth), and scaling, and offers the locality of representation required for occluded object recognition. To compare two saliency map graphs, we introduce two graph similarity algorithms. The first computes the topological similarity between two SMG's, providing a coarse-level matching of two graphs. The second computes the geometrical similarity between two SMG's, providing a fine-level matching of two graphs. We test and compare these two algorithms on a large database of model object views.
Cite
Text
Shokoufandeh et al. "View-Based Object Matching." IEEE/CVF International Conference on Computer Vision, 1998. doi:10.1109/ICCV.1998.710777Markdown
[Shokoufandeh et al. "View-Based Object Matching." IEEE/CVF International Conference on Computer Vision, 1998.](https://mlanthology.org/iccv/1998/shokoufandeh1998iccv-view/) doi:10.1109/ICCV.1998.710777BibTeX
@inproceedings{shokoufandeh1998iccv-view,
title = {{View-Based Object Matching}},
author = {Shokoufandeh, Ali and Marsic, Ivan and Dickinson, Sven J.},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {1998},
pages = {588-595},
doi = {10.1109/ICCV.1998.710777},
url = {https://mlanthology.org/iccv/1998/shokoufandeh1998iccv-view/}
}