Nowadays unsupervised classification (Clustering) has become more and more important because it is used in several fields (industry, business, image processing . . .etc ).
It is actually the process of grouping data into groups or classes. This is done in such a way that the objects of the same group have a high similarity compared to the objects of the other groups. The k-medoid algorithm is an unsupervised classification algorithm that aims to group a dataset of n objects into k clusters. It is robust to noise and outliers. The algorithm starts by representing the centers of the clusters by real objects. Then each remaining object will be assigned to the closest cluster. This treatment is repeated until the process stagnates.