Proceedings of the First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022)

Design and Generation of Devanagari Script CAPTCHA: Imaginative Technique

Authors
Sanjay E. Pate1, R. J. Ramteke1, *
1School of Computational Sciences, Kaviyatri Bahinabai Chaudhary North Maharashtra University, Jalgaon, MS, India
*Corresponding author. Email: rakeshj.ramteke@gmail.com
Corresponding Author
R. J. Ramteke
Available Online 10 August 2023.
DOI
10.2991/978-94-6463-196-8_28How to use a DOI?
Keywords
CAPTCHA; Devanagari; BOTs
Abstract

CAPTCHA (Completely Automated Public Turing Tests to Tell Computers and Humans Apart). Only humans can pass this test, but existing computer systems cannot. It’s used in a variety of machine and human identification applications. The most common type of CAPTCHA used on websites is text-based. This protected CAPTCHA script is largely made up of English letters, making it difficult for rural people who only speak their local languages to pass the test. Devanagari characters feature more sophisticated characters than typical English characters and numeral-based CAPTCHAs, considerably increasing the challenge of machine recognition. In India, most government websites present information in the Devanagari language. However, Devanagari CAPTCHAs are not utilized on websites. Therefore, we have designed a new Devanagari script text-based CAPTCHA in this article. There are 33 different varieties of Devanagari CAPTCHA images, of varying lengths (5 to 7), generated using printed and handwritten Devanagari characters and numeral combinations. Using digital image processing techniques, general rules for CAPTCHA generation are utilized to introduce noise to the CAPTCHA image so that it is not recognized or broken. The generation of a single CAPTCHA image requires 1.08 ms and 8 KB of storage. A dataset of 1,10,000 (one million and ten thousand) CAPTCHA images was created, requiring storage of 964 MB.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

Volume Title
Proceedings of the First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022)
Series
Advances in Intelligent Systems Research
Publication Date
10 August 2023
ISBN
978-94-6463-196-8
ISSN
1951-6851
DOI
10.2991/978-94-6463-196-8_28How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

TY  - CONF
AU  - Sanjay E. Pate
AU  - R. J. Ramteke
PY  - 2023
DA  - 2023/08/10
TI  - Design and Generation of Devanagari Script CAPTCHA: Imaginative Technique
BT  - Proceedings of the First International Conference on Advances in Computer Vision and Artificial Intelligence Technologies (ACVAIT 2022)
PB  - Atlantis Press
SP  - 356
EP  - 381
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-196-8_28
DO  - 10.2991/978-94-6463-196-8_28
ID  - Pate2023
ER  -