Boundary Processing of bidimensional EMD using texture synthesis

Abstract

A novel boundary processing technique is proposed for bidimensional empirical mode decomposition (BEMD). BEMD is a new form of multiscale decomposition and has superior quality in extracting intrinsic components of textures. Although the boundary effect of BEMD is one of its main questions, there have been no concrete discussions or effective methods for it. A modified algorithm of nonparametric sampling for texture synthesis is used to extend images before applying BEMD. Experiments indicate that the technique proposed in This work can form better decomposition compared with past algorithms not only for textures but also for natural images.