threeStageParSel {DRIP} | R Documentation |
image denoising/deblurring, bandwidth selection, bootstrap
Description
Select the bandwidth value for the image restoration method implemented in the function threeStage
Usage
threeStageParSel(image, bandwidth, edge1, edge2, nboot, blur=FALSE)
Arguments
image |
A square matrix object of size n by n, no missing value allowed. |
bandwidth |
Bandwidth values to be chosen from. Each of these values need to be an positive integer which specifies the number of pixels used in the local smoothing. |
edge1 |
A matrix of 0 and 1 of the same size as image represents detected step edge pixels. |
edge2 |
A matrix of 0 and 1 of the same size as image represents detected roof/valley edge pixels. |
nboot |
Required when blur is TRUE. Unused when blur is FALSE. An positive integer to specify the number of bootstraps to perform. See Qiu and Kang (2015) Statistica Sinica for details. |
blur |
TRUE if the image contains blur, FALSE otherwise. If TRUE, the hybrid selection method proposed in Qiu and Kang (2015) Statistica Sinica is used. If FALSE, the leave-one-out cross validation is used. |
Value
Returns a list of the selected bandwdith, and a matrix of CV values with each entry corresponding to each choice of bandwdith.
References
Qiu, P., and Kang, Y. "Blind Image Deblurring Using Jump Regression Analysis," Statistica Sinica, 25, 2015, 879-899.
Examples
data(peppers) # Peppers image is bundled with the package and it is a
# standard test image in image processing literature.
# Not Run
#step.edges <- stepEdgeLLK(peppers, 9, 17) # Step edge detection
#roof.edges <- roofEdge(peppers, 6, 3000, edge1=step.edges) # Roof edge detection
#set.seed(24)
#parSel <- threeStageParSel(image = peppers, edge1 = step.edges, edge2 = roof.edges,
#bandwidth = 4, nboot = 1, blur = TRUE) # Time consuming