Clustering by Detecting Density Peaks and Assigning Points by Similarity-First Search Based on Weighted K-Nearest Neighbors Graph

Table 5

Performance comparison of algorithms by clustering criteria for the Olivetti face database.

Metric	DPC-SFSKNN	DPC	DBSCAN	AP	FKNN-DPC	K-means
ACC	0.786	0.665	0.648	0.763	0.818	0.681
AMI	0.792	0.728	0.691	0.737	0.832	0.742
ARI	0.669	0.560	0.526	0.619	0.714	0.585
EC/AC	32/40	20/40	—	28/40	36/40	—
Par	6	0.5	0.6/4	2.1	4	40