In this paper, we investigate the problem of designing compact support interpolation kernels for a given class of signals. By using calculus of variations, we simplify the optimization problem from an infinite nonlinear problem to a finite dimensiona
l linear case, and then find the optimum compact support function that best approximates a given filter in the least square sense (l2 norm). The benefit of compact support interpolants is the low computational complexity in the interpolation process while the optimum compact support interpolant gaurantees the highest achivable Signal to Noise Ratio (SNR). Our simulation results confirm the superior performance of the proposed splines compared to other conventional compact support interpolants such as cubic spline.
The goal of this paper is to design compact support basis spline functions that best approximate a given filter (e.g., an ideal Lowpass filter). The optimum function is found by minimizing the least square problem ($ell$2 norm of the difference betwe
en the desired and the approximated filters) by means of the calculus of variation; more precisely, the introduced splines give optimal filtering properties with respect to their time support interval. Both mathematical analysis and simulation results confirm the superiority of these splines.
