Table 4 Performance analysis of the proposed passive KB-CMFD method vs. state-of-the-art CMFD methods on the MICC-F220 dataset (best performances are in bold).

From: Image tampering detection using dynamic histogram equalization based LIOP features and novel scaled K-means +  + clustering

CMFD methods

FPR (%)

TPR (%)

Time (Sec)

BB-CMFD12

14.00

89.00

294.69

Hybrid feature-based22

10.42

95.45

12.40

SIFT feature-based25

9.02

95.88

10.20

SURF feature-based26

8.60

97.40

09.20

Proposed passive KB-CMFD method

5.45

98.82

08.24