A Medical Image Registration Algorithm Based on Revised Hausdorff Distance
Bo Pan · Dianzi xuebao · 2008
Aim at the inconsistency between precision and computing complication because of using traditional Hausdorff Distance(HD) in medical image registration,we proposed a new Revised HD measure which introduces non-linear Bayesian consistency criterion function for the first time to get the higher registration precision and the strong ability to reject noise.The experimental results demonstrate that the proposed algorithm overcomes the registration faults which were brought by the isolated nodes and the noise using traditional HD and good registration performances are obtained.