Vectorial Scale-Based Image Filtering

Abstract

As to the filtering of medical images, it is important to preserve edges and details. A major drawback of filtering is that it often blurs important structures along with noise. Scale-based filtering methods of scalar images have been studied in recent years. In this paper, we generalize the scale-based filtering method from scalar images to vectorial images. Here we introduce three vectorial scale-based image filtering methods on the basis of conventional VMF, BVDF, and DDF. These new methods use local structure size or “object scale” information to arrest smoothing around fine structures. The object scale allows us to better control the filtering process by constraining smoothing in regions with fine details while permitting effective smoothing in the interior of homogeneous regions. Qualitative and quantitative experiments based on Visible Human Project data sets demonstrate that our proposed methods outperform the corresponding conventional filtering methods in preserving edges and details.