• Stars
    star
    189
  • Rank 204,649 (Top 5 %)
  • Language
    Jupyter Notebook
  • License
    MIT License
  • Created about 6 years ago
  • Updated over 1 year ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Image Tampering Detection using ELA and CNN

Fake Image Detector

Image Tampering Detection using ELA and CNN


Members

  1. Agus Gunawan
  2. Holy Lovenia
  3. Adrian Hartanto Pramudita

Indonesian paper/documentation

Get it here!

Project objective

Combine the implementation of error-level analysis (ELA) and deep learning to detect whether an image has undergone fabrication or/and editing process or not, e.g. splicing.

Methods

  1. Error-level analysis
  2. Convolutional neural networks (CNN)

Architecture

full-architecture

Result

  • Convergence: Epoch 9
  • Best accuracy: 91.83% (epoch 9)

Dataset

Please refer to issue #1.