Clustering a dataset of faces using the Laplacian matrix

Hi to everyone, first of all i'm sorry for my bad english. I have to implement an algorithm that compute the clusters of a set of faces. I have the face's matrix(the columns represent the faces;i'll call every column xi, where i =1,...,N=165). To build the Laplacian's matrix i've to create the Adiacency matrix

for i=1:N for j=1:N

x1=double(immagini(:,i)); x2=double(immagini(:,j)); x=(norm(x1-x2))^2;

if i==j A(i,j)=0; else A(i,j)=exp(-x/den);

end end end for i=1:N for j=1:N

if A(i,j)<=epsilon A(i,j)=0;

end end end

After i built the Laplacian: L=D-A; (where D is the degree matrix )

Now i have to work on this matrix using the eigenvectors [U,L1]=eig(L); How can i to continue?