TR2006-109

Fast Image Registration via Joint Gradient Maximization: Application to Multi-Modal Data

    •  Mei, X., Porikli, F., "Fast Image Registration via Joint Gradient Maximization: Application to Multi-Modal Data", SPIE Conference on Electro-Optical and Infrared Systems Technology and Applications, September 2006, vol. 6395.
      BibTeX TR2006-109 PDF
      • @inproceedings{Mei2006sep,
      • author = {Mei, X. and Porikli, F.},
      • title = {Fast Image Registration via Joint Gradient Maximization: Application to Multi-Modal Data},
      • booktitle = {SPIE Conference on Electro-Optical and Infrared Systems Technology and Applications},
      • year = 2006,
      • volume = 6395,
      • month = sep,
      • isbn = {978-0-8194-6493-4},
      • url = {https://www.merl.com/publications/TR2006-109}
      • }
  • Research Area:

    Computer Vision

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 rigit motion, and show promising results.

 

  • Related News & Events