Description of Registration Method for Helmut Alt

The results were computed according to an algorithm based on mutual information of normalized distributions. This means

Mutual information would be MI(X,Y):=H(X)+H(Y)-H(X,Y) where H(.) is the entropy and H(.,.) the joint entropy. Let f and g be the cumulative distribution functions of X and Y, resp. Then f(X) and g(Y) are uniformly distributed [0,1] valued random variables. Our objective function is MI(f(X),g(Y)).

Return to previous page