Authors: M M Fouad R M Dansereau A D Whitehead
Publish Date: 2010/08/27
Volume: 6, Issue: 4, Pages: 521-532
Abstract
In geometric image registration illumination variations that exist between image pairs tend to degrade the precision of the registration which can negatively affect subsequent processing In this paper we present a model to improve the subpixel geometric registration precision of image pairs when there exists locally variant illuminations with arbitrary shape This model extends on our previous work to include multiple local shading levels of arbitrary shape where the illposed problem is conditioned by constraining the solution to an estimated number of shading levels The proposed model is solved using leastsquares estimation and is cast in an iterative coarsetofine framework which allows a convergence rate that is similar to competing intensitybased image registration approaches The primary advantage of the proposed approach is the nearly tenfold improvement in subpixel precision for the registration when convergence is obtained in this class of technique
Keywords: