Publication detail

Evaluation of Randomly Generated Fonts for Bubble Captcha

BOŠTÍK, O. HORÁK, K. KLEČKA, J.

Original Title

Evaluation of Randomly Generated Fonts for Bubble Captcha

English Title

Evaluation of Randomly Generated Fonts for Bubble Captcha

Type

journal article in Scopus

Language

en

Original Abstract

A Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA), is the wide-spread concept of systems suited to secure the web services from automated SPAM scripts. The most common CAPTCHA systems benefit from imperfections of Optical Character Recognition algorithms. This paper presents our ongoing work focused on the development of a new CAPTCHA scheme based on a human perception. The goal of this work is to evaluate the usability of randomly generated fonts used in Bubble Captcha scheme with both humans and OCR classifiers.

English abstract

A Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA), is the wide-spread concept of systems suited to secure the web services from automated SPAM scripts. The most common CAPTCHA systems benefit from imperfections of Optical Character Recognition algorithms. This paper presents our ongoing work focused on the development of a new CAPTCHA scheme based on a human perception. The goal of this work is to evaluate the usability of randomly generated fonts used in Bubble Captcha scheme with both humans and OCR classifiers.

Keywords

OCR, CAPTCHA, Neural Networks, k-NN, Decision trees, SVM, Bubble Captcha

Released

26.06.2018

Publisher

VUT Brno

Location

Brno, Czech Republic

ISBN

1803-3814

Periodical

Mendel Journal series

Year of study

2018

Number

24

State

CZ

Pages from

143

Pages to

150

Pages count

8

URL

https://mendel-journal.org/index.php/mendel/article/view/35/37

Documents

BibTex 


@article{BUT148331,
  author="Ondřej {Boštík} and Karel {Horák} and Jan {Klečka}",
  title="Evaluation of Randomly Generated Fonts for Bubble Captcha",
  annote="A Completely Automated Public Turing test to tell Computers and Humans Apart (CAPTCHA), is the wide-spread concept of systems suited to secure the web services from automated SPAM scripts. The most common CAPTCHA systems benefit from imperfections of Optical Character Recognition algorithms.

This paper presents our ongoing work focused on the development of a new CAPTCHA scheme based on a human perception. The goal of this work is to evaluate the usability of randomly generated fonts used in Bubble Captcha scheme with both humans and OCR classifiers.",
  address="VUT Brno",
  chapter="148331",
  doi="10.13164/mendel.2018.1.143",
  howpublished="online",
  institution="VUT Brno",
  number="24",
  volume="2018",
  year="2018",
  month="june",
  pages="143--150",
  publisher="VUT Brno",
  type="journal article in Scopus"
}