Canonical Frames for Planar Object Recognition
Abstract
We present a canonical frame construction for determining projectively invariant indexing functions for non-algebraic smooth plane curves. These invariants are semi-local rather than global, which promotes tolerance to occlusion. Two applications are demonstrated. Firstly, we report preliminary work on building a model based recognition system for planar objects. We demonstrate that the invariant measures, derived from the canonical frame, provide sufficient discrimination between objects to be useful for recognition. Recognition is of partially occluded objects in cluttered scenes. Secondly, jigsaw puzzles are assembled and rendered from a single strongly perspective view of the separate pieces. Both applications require no camera calibration or pose information, and models are generated and verified directly from images.
Cite
Text
Rothwell et al. "Canonical Frames for Planar Object Recognition." European Conference on Computer Vision, 1992. doi:10.1007/3-540-55426-2_86Markdown
[Rothwell et al. "Canonical Frames for Planar Object Recognition." European Conference on Computer Vision, 1992.](https://mlanthology.org/eccv/1992/rothwell1992eccv-canonical/) doi:10.1007/3-540-55426-2_86BibTeX
@inproceedings{rothwell1992eccv-canonical,
title = {{Canonical Frames for Planar Object Recognition}},
author = {Rothwell, Charlie and Zisserman, Andrew and Forsyth, David A. and Mundy, Joseph L.},
booktitle = {European Conference on Computer Vision},
year = {1992},
pages = {757-772},
doi = {10.1007/3-540-55426-2_86},
url = {https://mlanthology.org/eccv/1992/rothwell1992eccv-canonical/}
}