Modeling Positional Uncertainty in Object Recognition

  title={Modeling Positional Uncertainty in Object Recognition},
  author={Arthur R. Pope and David G. Lowe},
Iterative alignment is one method for feature-based matching of an image and a model for the purpose of object recognition. The method alternately hypothesizes feature pairings and estimates a viewpoint transformation from those pairings; at each stage a refined transformation estimate is used to suggest additional pairings. This paper extends iterative alignment in the domain of 2D similarity transformations so that it represents the uncertainty in the position of each model and image feature… CONTINUE READING
9 Citations
17 References
Similar Papers

Similar Papers

Loading similar papers…