User Ratings

★★★★★
★★★★
★★★
★★
0
0
0
0
1
ease 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 0 / 5
features 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 0 / 5
design 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 0 / 5
support 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 0 / 5

Rate This Project
Login To Rate This Project

User Reviews

  • tried the example App1 and altered the code, but it is not working. Syntax error happens Tried to convert this: function im_out = our_RF(im_in, sigma_s, sigma_r) [R C CH] = size(im_in); % Compute the domain transform (Equation 11 of our paper). % Estimate horizontal and vertical partial derivatives using finite % differences. dIdx = zeros(R,C); dIdy = zeros(R,C); % Compute the l1-norm distance of neighbor pixels. % use sobel filters matrices dx = [-1, 0, 1; -2, 0, 2; -1, 0, 1] / 8.0; dy = [-1, -2, -1; 0, 0, 0; 1, 2, 1] / 8.0; for ch = 1:CH % original work derivatives % dIdx(:,2:end) = dIdx(:,2:end) + abs( dIcdx(:,:,ch) ); % dIdy(2:end,:) = dIdy(2:end,:) + abs( dIcdy(:,:,ch) ); dIcdx(:,:,ch) = conv2(im_in(:,:,ch) , dx, 'same'); dIcdy(:,:,ch) = conv2(im_in(:,:,ch) , dy, 'same'); dIdx = dIdx + abs( dIcdx(:,:,ch) ); dIdy = dIdy + abs( dIcdy(:,:,ch) ); end dIdx = dIdx / CH; dIdy = dIdy / CH; % Compute the derivatives of the horizontal and vertical domain transforms. dHdx = (1 + sigma_s/sigma_r * dIdx); dVdy = (1 + sigma_s/sigma_r * dIdy); % The vertical pass is performed using a transposed image. dVdy = dVdy'; % Perform the filtering. im_out = image_transpose(im_in); im_out = TransformedDomainRecursiveFilter_Horizontal(im_out, dVdy, sigma_s); im_out = image_transpose(im_out); im_out = TransformedDomainRecursiveFilter_Horizontal(im_out, dHdx, sigma_s); end % Recursive filter. function F = TransformedDomainRecursiveFilter_Horizontal(im_in, D, sigma_s) % Feedback coefficient (Appendix of our paper). a = exp(-sqrt(2) / sigma_s); F = im_in; V = a .^ D; [R C CH] = size(im_in); % Left -> Right filter. for i = 2:C for ch = 1:CH F(:,i,ch) = F(:,i,ch) + V(:,i) .* ( F(:,i - 1,ch) - F(:,i,ch) ); end end % Right -> Left filter. for i = C-1:-1:1 for ch = 1:CH F(:,i,ch) = F(:,i,ch) + V(:,i+1) .* ( F(:,i + 1,ch) - F(:,i,ch) ); end end end % Recursive filter. % function im_out = image_transpose(im_in) [R C CH] = size(im_in); im_out = zeros([C, R, CH], class(im_in)); for ch = 1:CH im_out(:,:,ch) = im_in(:,:,ch)'; end end
    2 users found this review helpful.
  • Previous
  • You're on page 1
  • Next