Computing Correspondence Based on Regions and Invariants Without Feature Extraction and Segmentation
Abstract
The problem addressed is the matching of corresponding regions in two images, even when the image intensity may be smoothly varying without distinctive edges. Corresponding small regions are assumed to be related by affine transformations. The matching is done by using a new class of low computational cost affine invariants. This approach also computes the affine transformation, and is ideal for applications to 3-D motion estimation and 3-D surface reconstruction, image alignment, etc. No feature extraction, segmentation or epipolar constraint is required. The advantage of the authors' approach over area matching is that it handles large baselines, i.e., the distance between camera positions, where the differences in orientation and linear distortion of two areas being compared is large.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Cite
Text
Lee et al. "Computing Correspondence Based on Regions and Invariants Without Feature Extraction and Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993. doi:10.1109/CVPR.1993.341042Markdown
[Lee et al. "Computing Correspondence Based on Regions and Invariants Without Feature Extraction and Segmentation." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993.](https://mlanthology.org/cvpr/1993/lee1993cvpr-computing/) doi:10.1109/CVPR.1993.341042BibTeX
@inproceedings{lee1993cvpr-computing,
title = {{Computing Correspondence Based on Regions and Invariants Without Feature Extraction and Segmentation}},
author = {Lee, Chi-Yin and Cooper, David B. and Keren, Daniel},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {1993},
pages = {655-656},
doi = {10.1109/CVPR.1993.341042},
url = {https://mlanthology.org/cvpr/1993/lee1993cvpr-computing/}
}