Recaptured video detection based on sensor pattern noise

EURASIP Journal on Image and Video Processing

Table 3 Detection result at different levels of scaling factors

	SF80		SF80 (QF80)		SF60		SF60 (QF80)
	TP	FP	TP	FP	TP	FP	TP	FP
Proposed (k = 0)	0.99	0.00	0.95	0.00	0.98	0.00	0.92	0.00
	1.00	0.01	0.97	0.01	0.99	0.01	0.94	0.01
	1.00	0.03	0.98	0.03	1.00	0.03	0.97	0.03
Proposed (k = 2)	1.00	0.00	0.99	0.00	1.00	0.00	0.96	0.00
	1.00	0.01	1.00	0.01	1.00	0.01	0.98	0.01
	1.00	0.03	1.00	0.03	1.00	0.03	0.99	0.03
Wang and Farid [11]	0.84	0.35	0.86	0.35	0.86	0.35	0.92	0.35
Bestagini et al. [13]	0.61	0.00	0.60	0.00	0.62	0.00	0.61	0.00
Jung et al. [14]	0.26	0.00	0.23	0.00	0.18	0.00	0.16	0.00
Cao and Kot [9]	0.77	0.27	0.78	0.27	0.78	0.27	0.78	0.27
Gao et al. [10]	0.98	0.32	0.97	0.32	0.98	0.33	0.97	0.33

[9] and [10] are image-based recapturing detection methods included here for reference only. Correlations between frames are not used here in our comparison