tIndependence of neighboring pixels and image stationarity are major concepts in conventional similaritymetrics, used in image registration tasks. The accuracy of image registration decreases due to the presenceof spatially varying intensity distortion in images. In this study, we hypothesized that changes in imageillumination have limited total variation (TV). Accordingly, we introduced a similarity metric by reducingthe weighted TV in the residual image. The primal dual method was then chosen to solve the proposedregistration problem. The efficiency of the proposed method was compared to conventional methods,including the residual complexity (RC) method, the robust Huber similarity measure (RHSM), and thelocal linear reconstruction method (LLRM) which have been very successful in this field. The efficacy ofthe proposed method was confirmed by experimental findings on real-world and synthetic images.
