Courses Blog Research Lab AI Letters The Lab Code Bank Interactive 3DKodr Earnest Jobs

Interactive 3D/DBSCAN Density Clustering

Stats

Clusters: -

Noise: -

Core: -

Border: -

Press "Run DBSCAN" to cluster

DBSCAN

Density-based clustering - finds clusters of any shape

Dataset

Epsilon ε (px)

ε = 45px

Min Samples

Show ε Circles

Actions

How It Works

Core point: has ≥ min_samples neighbors within ε.

Border point: within ε of a core point but not core itself.

Noise: not within ε of any core point.

DBSCAN finds clusters of arbitrary shape - unlike K-Means which assumes spherical clusters.

Legend

●Core point (large dot)

●Border point (small dot)

✕Noise / outlier

DBSCAN Density Clustering - Interactive Visualization

DBSCAN (Density-Based Spatial Clustering of Applications with Noise) groups points that are closely packed together and marks isolated points as noise. A point is a core point if it has at least min_samples neighbors within radius epsilon. Core points form cluster cores; points reachable from a core are border points; the rest are noise. Unlike k-means, DBSCAN finds arbitrarily shaped clusters and naturally handles outliers.

Drag epsilon and min_samples sliders and watch points instantly reclassified as core (solid), border (ring), or noise (X)
See DBSCAN handle crescent and ring-shaped clusters that completely defeat k-means
Understand how epsilon controls cluster density threshold - too large merges everything, too small fragments clusters
Learn how min_samples controls the minimum density required to form a cluster core - higher values filter more noise
See why DBSCAN is the right tool when you have spatial data with outliers and unknown number of clusters

Part of the EngineersOfAI Interactive 3D - free interactive visualizations covering every major concept in machine learning and AI engineering. Hover any element for a plain-English explanation. No code required.