标题: Local Oscillation Suppression Based on Joint Bilateral Filtering Framework [打印本页] 作者: 彬彬 时间: 2012-1-3 10:26 标题: Local Oscillation Suppression Based on Joint Bilateral Filtering Framework 1 Introduction
Image details are mainly composed of edges and textures. From
the view of pixel intensity or gradient magnitude, both edges and
textures are the drastic variances among the pixels of local image
regions. However, because of the similarity of textures, they usu-
ally feature some regular local oscillations [Subr et al. 2009]. It
makes great sense to distinguishes edges and textures exactly for
many image applications, e.g. detail manipulation. But the current
major bilateral-based [Paris and Durand 2009] and optimization-
based [Farbman et al. 2008] approaches usually emphasize more on
edge-preserving, incompletely preserving some textures instead of
smoothing. These results will produce serious interferences in both
edge preservation and texture extraction. On the basis of the joint
bilateral filtering framework, we take advantage of our degenerative
image to suppress the local oscillations and produce better output
with dual properties of edge-preserving and texture-smoothing, see