ABSTRACT
Application of the Total Least Squares Procedure to Linear View Interpolation.
Dawn Kennedy
It is shown that, in comparison to the results obtained from a conventional least squares
approach, a total least squares solution leads to significant improvements in the geometry
and appearance of images synthesised in a linear combination of views procedure. Use of
the total least squares criterion is appropriate when errors on the control points are
independently and identically distributed between the basis images and the target image
being synthesised. When this is not be the case it is pointed out that the generalised
total least squares procedure should be used. A synthetic object is used to evaluate the
improvement in geometric accuracy obtained by use of the total least squares solution in
comparison to a classical least squares method. Simulated and real images of laboratory
test objects are similarly used to illustrate the improvement in appearance of images
reconstructed by means of the total least squares procedure.
Computer Science Home Page
Maintained by rbennett@cs.ucl.ac.uk