Transformation model estimation of image registration via least square support vector machines

Abstract

This paper describes a new approach to the determination of a mapping function from given coordinates of control points based on least square support vector machines (LS-SVM). An interesting property of this approach is that it constitutes a practical implementation of the structural risk minimization (SRM) principle that aims at minimizing a bound on the generalization error of a model, rather than minimizing the mean square error over control points. Computer simulation results indicate that this new approach can remove geometric deformation and adapt to correct the errors induced by inaccuracy location of control points.