As a part of the Reading Group, the following
paper will be presented:

Steven Gold, Anand Rangarajan, Chien-ping Lu and Eric Mjolsness:
New Algorithms for 2D and 3D Point Matching: Pose Estimation and
Correspondence,
Pattern Recognition 31 (1997) 957--964.

--------
Warning: Do not expect this Reading Group to be a short one; reserve sufficient
time for it and notice that it starts at 10:00 and may last up to 13:00!
--------

A fundamental open problem in computer vision---determining pose and
correspondence between two sets of points in space---is solved with a novel,
fast, robust and easily implementable algorithm. The technique works on noisy
2D
or 3D point sets that may be of unequal sizes and may differ by non-rigid
transformations. Using a combination of optimization techniques such as
deterministic annealing and the softassign, which have recently emerged out of
the recurrent neural network/statistical physics framework, analog objective
functions describing the problems are minimized. Over thirty thousand
experiments, on randomly generated points sets with varying amounts of noise
and
missing and spurious points, and on hand-written character sets demonstrate the
robustness of the algorithm.

Send your questions to Miguel by November 23rd noon.