Editing Image segmentation (section)

===== Iterated conditional modes/gradient descent =====

The [[iterated conditional modes]] (ICM) algorithm tries to reconstruct the ideal labeling scheme by changing the values of each pixel over each iteration and evaluating the energy of the new labeling scheme using the cost function given below,

:<math> \alpha(1-\delta(\ell_i-\ell_{\text{initial }i})+ \beta \Sigma_{q \in N(i)}(1 - \delta(\ell_i,\ell_{q(i)})). </math>

where {{mvar|&alpha;}} is the penalty for change in pixel label and {{mvar|&beta;}} is the penalty for difference in label between
neighboring pixels and chosen pixel. Here <math>N(i)</math> is neighborhood of pixel i and {{mvar|&delta;}} is the Kronecker delta function. A major issue with ICM is that, similar to gradient descent, it has a tendency to rest over local maxima and thus not obtain a globally optimal labeling scheme.