🕵️♂️ Image Classifier CNN: Automating Digital Forensics with Deep Learning

Leverage Convolutional Neural Networks to Detect Image Manipulation Artifacts with 94.7% Accuracy

🔍 Research Questions

1. Can deep learning identify manipulation artifacts in images?
   Exploring CNN's capability to detect subtle tampering clues like noise patterns, edge inconsistencies, and compression artifacts.

2. How effective are CNNs in forensic image classification?
   Quantifying performance metrics (accuracy, F1-score) across diverse manipulation types (splicing, copy-move, retouching).

3. What challenges exist in DL-based forensic analysis?
   Investigating limitations like adversarial attacks, dataset biases, and generalization across image formats.

🚀 Project Highlights

✨ Key Features

🛠️ Tech Stack

Core Libraries:

matplotlib, seaborn, numpy, pandas, imgaug, lime
 
## 🔧 Getting Started
 
### 📌 Prerequisites
 
Ensure you have the following installed:
 
- **Python 3.9 or 3.10**
- **Required libraries:**
 
```bash
pip install tensorflow opencv-python scikit-learn matplotlib seaborn
 
 
## 📥 Installation
 
1. **Clone the repository:**
 
   ```bash
   git clone https://github.com/tinolinton/cnn.git