Baldur10 / Digital-Fake-Image-Detection-Based-on-ANN-and-ML

Designed an ANN-based system which will identify and classify the morphed images By processing through ELA

Digital-Fake-Image-Detection-Based-on-ANN-and-ML

Image Tampering Detection using ELA and CNN

---

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)

---

Activity Diagram

Architecture

Result

• Convergence: Epoch 30
• Best accuracy: 98.13% (epoch 30)