This is the official implementation code of the paper "ArtDet: Machine Learning Software for Automated Detection of Art Deterioration in Easel Paintings" (Paper
)
git clone https://github.com/frangam/artdet.git
cd artdet
-
Install Python 3.12 (if not already installed). On macOS or Linux:
sudo apt update sudo apt install -y python3.12 python3.12-venv python3.12-dev
For macOS (if using Homebrew):
brew install [email protected]
-
Create a virtual environment using Python 3.12:
python3.12 -m venv venv
-
Activate the environment:
On macOS/Linux:
source venv/bin/activate
On Windows:
.\venv\Scripts\activate
git clone https://github.com/alsombra/Mask_RCNN-TF2.git
cd Mask_RCNN-TF2
pip install -r requirements.txt
python setup.py install
cd ..
pip install -r requirements.txt
python src/run.py
Then, the wep app is running on http://127.0.0.1:5000
You can download our ArtInsight Dataset at:
Place images in this folder: data/--- data/train/--- data/val/---
Click the links below to download the checkpoint for the corresponding model type.
Locate the downloaded model to this path: model/---
If you use our code in your research, please use the following BibTeX entry:
@article{GARCIAMORENO2024101917,
title = {ARTDET: Machine learning software for automated detection of art deterioration in easel paintings},
journal = {SoftwareX},
volume = {28},
pages = {101917},
year = {2024},
issn = {2352-7110},
doi = {https://doi.org/10.1016/j.softx.2024.101917},
url = {https://www.sciencedirect.com/science/article/pii/S2352711024002875},
author = {Francisco M. Garcia-Moreno and Jesús Cortés Alcaraz and José Manuel {del Castillo de la Fuente} and Luis Rodrigo Rodríguez-Simón and María Visitación Hurtado-Torres}
}
And also cite our Dataset:
(Submitted to)
@article{Garcia-MorenoArtInsight,
title={ArtInsight: A Detailed Dataset for Detecting Deterioration in Easel Paintings},
author={Garcia-Moreno, Francisco Manuel and del Castillo de la Fuente, Jose Manuel and Rodríguez-Simón, Luis Rodrigo and Hurtado-Torres, María Visitación},
year={2024},
journal={Data in Brief}
doi={pending},
url={},
}