Abstract
Clustering is one of the most important data analysis tasks. It is used to organize data points into groups or clusters. Each cluster has similar instances, which are dissimilar to instances belonging to other clusters. Clustering is used in multiple disciplines and has an integral role in a wide variety of applications. This paper presents a comparative study of three common density-based clustering algorithms namely, DBSCAN, OPTICS and Mean-shift. The results are supported by an experimental evaluation using twelve datasets.