Statistical Approaches to Feature-Based Object Recognition

  • Authors:
  • William M. Wells, III

  • Affiliations:
  • Massachusetts Institute of Technology, Artificial Intelligence Laboratory, 545 Technology Square, Cambridge, Massachusetts 02139/ and Department of Radiology, Brigham and Women's Hospital, Harva ...

  • Venue:
  • International Journal of Computer Vision
  • Year:
  • 1997

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper examines statistical approaches to model-based object recognition.Evidence is presented indicating that, in some domains, normal(Gaussian) distributions are more accurate than uniform distributionsfor modeling feature fluctuations.This motivates the development of newmaximum-likelihood and MAP recognition formulations which are based onnormal feature models. These formulations lead to anexpression for the posterior probability of the pose andcorrespondences given an image.Several avenues are explored for specifying a recognition hypothesis.In the first approach, correspondences are included as a part of the hypotheses. Search for solutions may be ordered as a combinatorial search in correspondence space, or as a search over pose space, where the same criterion can equivalently be viewed as a robust variant of chamfer matching. In the second approach, correspondences are not viewed as being a part of the hypotheses. This leads to a criterion that is a smooth function of pose that is amenable to local search by continuous optimization methods. The criteria is also suitable for optimization via the Expectation-Maximization (EM) algorithm, which alternates between pose refinement and re-estimation of correspondence probabilities until convergence is obtained.Recognition experiments are describedusing the criteria with features derived from video imagesand from synthetic range images.