TABLE 7.
Classification accuracy of the proposed and existing algorithm for GAN generated images.
Algorithm | Accuracy % |
---|---|
Bharati et al. (2016) (Unsupervised DBM) | 81.90 |
Bharati et al. (2016) (Supervised DBM) | 87.10 |
Jain et al. (2018) (Thresholding) | 99.48 |
Jain et al. (2018) (SVM) | 99.65 |
Proposed (MagNet) | 99.96 |
Result of the best performing algorithm is highlighted in bold.