Cerebellum and frontal lobe segmentation based on K-Means clustering and morphological transformation

K-means clustering can be used as an algorithm segmentation that can split an area of interest from the image into several different regions containing each pixel based on color. Nevertheless, the result of the color division of the clustering has not been able to display clean segmentation because there are still pixels that connect each other and produce pixel noise or unwanted pixels. In this work, we propose a technique where it can select four dominant colors from the k-means clustering results then display it as digital image output. In our approach, the proposed method can separate the cerebellum and frontal lobe from the background of the brain after several operations of morphological transformation. In implementing this method, three samples of the brain from different people were tested. From the experimental results, the DSI produces a value of 0.72 from 1 for the frontal lobe and 0.86 from 1 for the cerebellum. It means that the proposed method can segment the desired part of the brain properly.