Euclidean skeleton

%the function work in 4 steps:
%1. compute the inverse eucilidean distance trasform ("inv_distance") of "bw"
%2. compute the ridges(watersheds) of "inv_distance" by watershed algorithm
%3. compute the gradient of ridges "rigid_grad"
%4. compute the final skeleton by Thresholding, dilation and thining "rigid_grad".
%The meaning of "gradient of ridges" is defined due to
%Nicholas R. Howe and Alex Telea: "A point on the skeleton sits at the center of a circle that touches the edge of the figure at multiple points.
%The intensity in the gray-level skeleton image ("rigides_grad" in this file) is based on the shortest distance you would have to travel around the perimeter of
%the figure to connect the most distant two points."

%Acknowledgement:
%[1] This work was inspired by Nicholas R. Howe. Please go to his website
%http://maven.smith.edu/~nhowe/research/code/
%for more details.
%[2] Xiaochen He, for the images provided in his file:
%"A Corner Detector based on Global and Local Curvature Properties"
%http://www.mathworks.com/matlabcentral/fileexchange/7652-a-corner-detector
%-based-on-global-and-local-curvature-properties