Code and pretrained Real-world CNN model for:

Benedikt Lorch, Shruti Agarwal, Hany Farid. Forensic Reconstruction of Severely Degraded License Plates. Media Watermarking, Security, and Forensics 2019, Burlingame, CA, USA, MWSF-529. bibtex

Forensic Reconstruction of Severely Degraded License Plates - PDF

Can you enhance it? - Forensic Reconstruction of Severely Degraded License Plates - Slides - PDF

Tested on MacOS 10.14 with Python 3.7, TensorFlow 2.1.0.

Python 3

LaTeX 3

Clone this repo.

git clone https://github.com/btlorch/license-plates.git
cd license-plates

Setup python virtual environmennt

python3 -m pip install --user --upgrade pip
python3 -m pip install --user virtualenv
python3 -m venv env
source env/bin/activate

Inside your virtual environment install required packages.

pip install -r requirements.txt

Download trained model to <repo>/model or a directory of your choice.

Alternate link to trained model

wget https://faui1-files.cs.fau.de/public/mmsec/license-plates/license-plates-trained-model.zip

shasum -a 256 license-plates-trained-model.zip 
	ec2fad6f73e123e181780476b6e36b34228efde475fa1e053c45bd2a17234536  license-plates-trained-model.zip

unzip license-plates-trained-model.zip -d model

cd src
jupyter notebook

Then open demo.ipynb.

Depending on the location of the trained weights, you may need to update the path in the first cell.

(View image to enlarge)