Skip to content

AlexMetsai/Contrained-Convolutional-Neural-Networks

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

93 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Contrained-Convolutional-Neural-Networks

A Keras implementation of a Constrained Convolutional Neural Network [1], used for image manipulation detection.

This code was written by reading the paper, the authors do mention that they released some source code, but since I wanted to implement the paper my own, I didn't look at their code. Therefore, it is not guaranteed that this code is one hundred percent on par with what they did. But I do think it's pretty close.

It should be noted that a fully connected layer is used instead of the extremely randomized tree mentioned in the paper.

Tested on keras 2.1.2 with Tensorflow 1.4.0 as backend.

References

[1] Belhassen Bayar and Matthew C. Stamm (2018). "Constrained Convolutional Neural Networks: A New Approach Towards General Purpose Image Manipulation Detection", IEEE Transactions on Information Forensics and Security, volume 13.

[2] Belhassen Bayar and Matthew C. Stamm (2016). "A deep learning approach to universal image manipulation detection using a new convolutional layer", 2016 ACM Workshop on Information Hiding and Multimedia Security

About

A keras implementation of the method

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors