Skip to content
Snippets Groups Projects
Select Git revision
  • main default protected
1 result
Compare History
Iuliia Tkachenko's avatar
Upload New File
Iuliia Tkachenko authored
bba0eb1f
Name Last commit Last update
assets
README.md
dataset_JISA_2022.zip
README.md

Regular Test Pattern Datasets

Table of content

Overview

This web-page is dedicated to public databases of Regular Test Patterns printed using rotogravure prinitng process using two cylinders C1 and C2 and two presses P1 and P2. These datasets are used in the paper Authentication of rotogravure print-outs using a regular test pattern and Printed packaging authentication: similarity metric learning for rotogravure manufacture process identification. Please cite the corresponding papers while using these datasets in your academic work.

Dataset

We worked with a regular test pattern E (see Fig.a) printed using two presses (P1 and P2) and two types of engraving cylinders: 1) two cylinders engraved using chemical etching (C1 and C2); and 2) a cylinder engraved using electro-mechanical process (M1). The samples printed using the cylinders engraved using chemical etching (Fig.b-c) differ a lot from the samples printed using the electro-mechanically engraved cylinder (Fig.d-e). Additionally, we studied the impact of the printing support used, using the regular test patterns printed on: 1) thin aluminium foils - called blisters (letter 'b' in the table); and 2) thick aluminium foils - called strips (letter 's' in the table). The details about the data set used are given in the following Table:

Press&Cylinder E1 E2 E3 E4 E5 E6
P1C1s 50 50 50 50 50 50
P2C1s 50 50 50 50 50 50
P1C2s 50 50 50 50 50 50
P2C2s 50 50 50 50 50 50
P1C1b 50 50 50 50 50 50
P2C1b 50 50 50 50 50 50
P1M1s 50 50 50 50 50 50
P2M1s 49 48 49 48 49 48
Example of genuine and fake document from PaySlip dataset

Augmented PaySlip samples

Citation

The dataset could only be used for scientific purposes. It must not be republished other than by the original authors. The scientific use includes processing the data and showing it in publications and presentations. If you use it, please cite the following papers.

Journal paper about cylinder signature identifiaction:

@article{tkachenko2022authentication,
  title={Authentication of rotogravure print-outs using a regular test pattern},
  author={Tkachenko, Iuliia and Tr{\'e}meau, Alain and Fournel, Thierry},
  journal={Journal of Information Security and Applications},
  volume={66},
  pages={103133},
  year={2022},
  publisher={Elsevier}
}

Conference paper on VISAPP 2023 about similarity metric learning for press and support identification:

@InProceedings{yemelianenko2023printed,
    author    = {Yemelianenko, T., Trémeau, A. and Tkachenko I.},
    title     = {Printed packaging authentication: similarity metric learning for rotogravure manufacture process identification},
    booktitle = {VISIGRAPP (4: VISAPP)},
    month     = {February},
    year      = {2023}
}

Acknowledgements

All the printed samples were provided by Sergusa Solutions Pvt Ltd in the context of PackMark project (IFCPAR-7127) supported by the Indo-French Center for the Promotion of Advanced Research.