Paper: Splicing image forgery detection based on DCT and Local Binary Pattern, 2013 IEEE Global Conference on Signal and Information Processing
- opencv-python
- sklearn
- skimage
- progressbar2
Dataset | Cross Validation |
---|---|
CASIA v1 | 98.0 +- 0.01 |
CASIA v2 | 96.0 +- 0.01 |
- Change value of block_sizes and strides for feature extraction in multiple case
- Example block_sizes = [16, 32] and strides = [8, 16]