Based on these concepts, DBSCAN defines clusters as follows
- Cluster: the largest set of points for which all points are density-connected to each other and from which any point in the cluster can be reached from any other point.
- Noise point: not belonging to any cluster.
Thus, DBSCAN defines clusters based on data density and identifies noise points.
This page is auto-translated from /nishio/DBSCANにおけるクラスタの定義 using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.