ML Anthology

Implicit Similarity: A New Approach to Multi-Sensor Image Registration

Yosi Keller, Amir Averbuch
CVPR 2003 pp. 543-548
doi:10.1109/CVPR.2003.1211514 /cvpr/2003/keller2003cvpr-implicit/

Abstract

This paper presents an implicit similarity-based approach to registration of significantly dissimilar images, acquired by sensors at different modalities. The proposed algorithm introduces a robust matching criterion by aligning the locations of gradient maxima. The alignment is formulated as a parametric variational optimization problem, which is solved iteratively by considering the intensities of a single image. The location of the maxima of the second image's gradient are used as initialization. We are able to robustly estimate affine and projective global motions using 'coarse to fine' processing, even when the images are characterized by complex space varying intensity transformations. Finally, we present the registration of real images, which were taken by multi-sensor and multi-modality using affine and projective motion models.

CVPR Semantic Scholar

Cite

Text

Keller and Averbuch. "Implicit Similarity: A New Approach to Multi-Sensor Image Registration." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003. doi:10.1109/CVPR.2003.1211514

Markdown

[Keller and Averbuch. "Implicit Similarity: A New Approach to Multi-Sensor Image Registration." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2003.](https://mlanthology.org/cvpr/2003/keller2003cvpr-implicit/) doi:10.1109/CVPR.2003.1211514

BibTeX

@inproceedings{keller2003cvpr-implicit,
  title     = {{Implicit Similarity: A New Approach to Multi-Sensor Image Registration}},
  author    = {Keller, Yosi and Averbuch, Amir},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2003},
  pages     = {543-548},
  doi       = {10.1109/CVPR.2003.1211514},
  url       = {https://mlanthology.org/cvpr/2003/keller2003cvpr-implicit/}
}