Image dataset to train a deep learning model to decode Leetspeak obfuscated characters

  1. De Mendizabal, Iñaki Velez 1
  2. Vidriales, Xabier 1
  3. Fernandes, Vitor Basto 2
  4. Ezpeleta, Enaitz 1
  5. Méndez, José Ramón 3
  6. Zurutuza, Urko 1
  1. 1 Universidad de Mondragón/Mondragon Unibertsitatea
    info

    Universidad de Mondragón/Mondragon Unibertsitatea

    Mondragón, España

    ROR https://ror.org/00wvqgd19

  2. 2 Instituto Universitário de Lisboa (ISCTE-IUL)
  3. 3 Universidade de Vigo
    info

    Universidade de Vigo

    Vigo, España

    ROR https://ror.org/05rdf8595

Show affiliations +

Editor: Zenodo

Year of publication: 2022

Type: Dataset

CC BY 4.0

DOI: 10.5281/ZENODO.6373558 lock_openOpen access editor

Abstract

The dataset contains an image database (18,981 images) that could be used to train a deep learning model to accurately detect characters. We have successfully used it to create a model that identifies characters encoded using LeetSpeak. The original dataset can be found in the Mondragon Unibertsitatea Repository -- https://gitlab.danz.eus/datasharing/ski4spam The training dataset consists of: - Alphabetic letters (a-z) written using different fonts and styles (regular, cursive, bold, cursive+bold) - Handwritten letters: English handwriting from the Chars74k dataset [2] which is available at http://www.ee.surrey.ac.uk/CVSSP/demos/chars74k/.