18-12-2014, 07:39 PM
guided filter operation and what is the operator used in edge preserving
|
guided image filtering ppt
|
guided filter operation and what is the operator used in edge preserving
04-04-2017, 02:26 PM
A new explicit image filter called a guided filter. Derived from a local linear model, the guided filter calculates the filtering output by considering the contents of a guide image, which may be the input image itself or another different image. The guided filter can be used as an edge smoothing operator as the popular two-sided filter, but has better behavior near the edges. The guided filter is also a more generic concept beyond smoothing: it can transfer the structures of the guide image to the filtration outlet, allowing new filtration applications such as deshazing and guided plumage. In addition, the guided filter naturally has a fast and non-approximate linear time algorithm, regardless of core size and intensity range. It is currently one of the fastest edge conservation filters. Experiments demonstrate that the guided filter is effective and efficient in a wide variety of computer graphics and computer vision applications, including edge smoothing, detail enhancement, HDR compression, image stamping, deshazing, joint upsampling, etc.
Edge conservation filters aim to simplify image rendering (for example, reducing noise or removing irrelevant details) while preserving their most significant edges. These filters are typically non-linear and locally smooth the structure of the image while minimizing both blurring and sharpening of the visually important edges. Here we present the Alternate Oriented Filter (AGF) that achieves edge smoothing by combining two recently introduced filters: the Rolling Guided Filter (RGF) and the Smooth and iteratively Restore Filter (SiR). We show that the integration of RGF and SiR into an iterative alternative framework results in a new smoothing operator that preserves significant image edges while effectively eliminating small-scale details. The AGF combines the large-scale and local intensity edge preservation properties of the RGF with the restoring properties of the SiR edge, eliminating the drawbacks of both previous methods (ie, RGF edge curl smoothing and Local intensity and small-scale detail restoration near large-scale edges by SiR).
Edge conservation filters aim to simplify image rendering (for example, reducing noise or removing irrelevant details) while preserving their most significant edges. These filters are typically non-linear and locally smooth the structure of the image while minimizing both blurring and sharpening of the visually important edges. Here we present the Alternate Oriented Filter (AGF) that achieves edge smoothing by combining two recently introduced filters: the Rolling Guided Filter (RGF) and the Smooth and iteratively Restore Filter (SiR). We show that the integration of RGF and SiR into an iterative alternative framework results in a new smoothing operator that preserves significant image edges while effectively eliminating small-scale details. The AGF combines the large-scale and local intensity edge preservation properties of the RGF with the restoring properties of the SiR edge, eliminating the drawbacks of both previous methods (ie, RGF edge curl smoothing and Local intensity and small-scale detail restoration near large-scale edges by SiR).
|
« Next Oldest | Next Newest »
|
