A deep learning-powered web application to detect Copy-Move Image Forgery using a custom-trained convolutional neural network (CNN). Built with TensorFlow/Keras, trained via Jupyter Notebook, and deployed using Flask.
Image forgery refers to manipulating a digital image to alter its content, often to deceive viewers. One common method is Copy-Move Forgery, where a part of an image is copied and pasted to conceal or duplicate elements.
Upload an image via the web app interface, and the model will analyze it to detect possible forgery regions.
Train the model and save into artifacts folder Run all cells to train the model. jupyter notebook Research.ipynb
Activate the virtual env
python -m venv venv venv\Scripts\activate
python3 -m venv venv source venv/bin/activate
pip install -r requirements.txt
python app.py