What is normalized graph cut?
We treat image segmentation as a graph partitioning problem and propose a novel global criterion, the normalized cut, for segmenting the graph. The normalized cut criterion measures both the total dissimilarity between the di erent groups as well as the total similarity within the groups.
How do you calculate normalized cut?
solution to the normalized cut problem. one can subdivide the existing graph using the eigen vector with the next smallest eigen value. then placing the data into W and D. Solve (D-W)x=λDx for eigen vectors with the smallest eigenvalues.