Holistic Matching

Abstract

This paper describes a new approach to extracting affine structure from 2D point-sets. The novel feature is to unify the tasks of estimating transformation geometry and identifying point-correspondence matches. Unification is realised by constructing a mixture model over the bi-partite graph representing the correspondence match and by effecting optimisation using the EM algorithm. According to our EM framework the probabilities of structural correspondence gate contributions to the expected likelihood function used to estimate maximum likelihood affine parameters. This provides a means of rejecting structural outliers. We evaluate the technique on the matching of different affine views of 3.5in floppy discs. We provide a sensitivity study based on synthetic data.