A Robust k-Means Clustering Algorithm Based on Observation Point Mechanism

Figure 3

Two-dimensional illustrations corresponding to four synthetic data sets (the red data points are outliers.). (a) Data set 3 (five clusters). (b) Data set 4 (six clusters). (c) Data set 5 (six clusters). (d) Data set 6 (seven clusters).

(a)

(b)

(c)

(d)