A fast source-oriented image clustering method for digital forensics

EURASIP Journal on Image and Video Processing

Table 2 Comparison of clustering algorithms on \(\mathcal {D}_{2}\)

Algorithms	1024×1024					512×512					512×256
	\(\mathcal {P}\)	\(\mathcal {R}\)	\(\mathcal {F}\)	\(\mathcal {A}\)	\(\mathcal {N}\)	\(\mathcal {P}\)	\(\mathcal {R}\)	\(\mathcal {F}\)	\(\mathcal {A}\)	\(\mathcal {N}\)	\(\mathcal {P}\)	\(\mathcal {R}\)	\(\mathcal {F}\)	\(\mathcal {A}\)	\(\mathcal {N}\)
SC [31]	0.34	0.98	0.51	0.17	0.28	0.35	0.97	0.51	0.19	0.32	0.41	0.78	0.54	0.21	0.44
HC [34]	0.82	0.58	0.68	0.63	1.48	0.50	0.77	0.61	0.28	0.68	0.85	0.14	0.24	0.59	5.60
SNNC [43]	0.88	0.48	0.62	0.76	1.80	0.60	0.19	0.29	0.37	2.80	0.54	0.16	0.24	0.27	3.16
NCUT [45]	0.86	0.20	0.33	0.71	4.28	0.75	0.30	0.43	0.61	2.56	0.72	0.38	0.50	0.58	1.76
MRF [49]	0.97	0.49	0.65	0.91	1.88	0.79	0.47	0.59	0.58	1.56	0.76	0.50	0.60	0.53	1.44
Proposed	0.97	0.78	0.86	0.91	1.20	0.92	0.87	0.89	0.87	1.04	0.88	0.83	0.85	0.78	1.04