Fast image registration via joint gradient maximization: application to multimodal data

Xue Mei, Fatih PorikliProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 2006 · DOI

Abstract

We present a computationally inexpensive method for multi-modal image registration. Our approach employs a joint gradient similarity function that is applied only to a set high spatial gradient pixels. We obtain motion parameters by maximizing the similarity function by gradient ascent method, which secures a fast convergence. We apply our technique to the task of affine model based registration of 2D images which undergo large rigid motion, and show promising results.
BibTeX
@inproceedings{mei2006fast,
  author = {Xue Mei and Fatih Porikli},
  title = {{Fast image registration via joint gradient maximization: application to multimodal data}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {2006},
  doi = {10.1117/12.690077},
}

Loading related content...

Figure