Fig. 2From: In-line recognition of agglomerated pharmaceutical pellets with density-based clustering and convolutional neural networkA cluster consists of core points (red) and border points (green). Core points have at least minPts in their neighborhood N ε (constrained by ε), whereas border points have less than minPts in their N ε , but are inside N ε of a core point. Points that are outside N ε of any core point and have less than minPts in their N ε are considered noise (blue)Back to article page