Skip to content

Classifies a given image as authentic or tampered by doing two levels of analysis. Implemented using PyTorch.

Notifications You must be signed in to change notification settings

z1311/Image-Manipulation-Detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Image-Manipulation-Detection

Classifies a given image as authentic or tampered by doing two levels of analysis.
Level 1 - Metadata analysis, to find any software signatures in the metadata of the image.
Level 2 - Feature Engineering(Error Level Analysis) and CNNs for classification. Error Level Analysis(ELA) is a compression method for finding the region which is tampared. This output is given as input to the CNN for classification.
The model is trained and validated on CASIA dataset. It has JPEG images of copy-move and spliced tampared images.

How To Run

Flags

-p or --path: Image pathname (required)

$ python main.py -p pathname

About

Classifies a given image as authentic or tampered by doing two levels of analysis. Implemented using PyTorch.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published