DoCA (Document Classification and Analysis)
Submission for "PARDUS Dosya Sınıflandırma ve Analiz (DoSA)" Competition in which we won the first place: source.
Houssem Menhour
Kübra Köksal
Assoc. Prof. Dr. Ahmet Sayar
Res. Asst. Dr. Süleyman Eken
libreoffice-dev
libmagickwand-dev
ffmpeg
couchdb
git clone https://github.com/husmen/DoCA_GUI.git
cd DoCA_GUI
conda env create -f pardus.yml
source activate pardus
# edit settings.ini if necessary
python main_gui.py
This work has been published in IEEE Open Access. You can cite it in your publication:
@ARTICLE{8768370,
author={S. {Eken} and H. {Menhour} and K. {Köksal}},
journal={IEEE Access},
title={DoCA: A Content-Based Automatic Classification System Over Digital Documents},
year={2019},
volume={7},
number={},
pages={97996-98004},
keywords={Task analysis;Feature extraction;Text analysis;Optical character recognition software;Libraries;Pattern matching;Organizations;Document analysis;document classification;OCR;video-audio analysis},
doi={10.1109/ACCESS.2019.2930339},
ISSN={2169-3536},
month={},}