Artificial Intelligence and Communication Technologies
Recognition Of CAPTCHA Characters Using Machine Learning Algorithms
Authors: Dipika Malhotra and Satinder Kaur
Publishing Date: 06-08-2022
ISBN: 978-81-955020-5-9
Abstract
The Completely Automated Public Turing Test to Tell Computers and Humans Apart (CAPTCHA) is a test used in many online applications to safeguard the authentication process by distinguishing humans from bots. Recognition of characters is incorporated with the help of the CAPTCHA method to make web applications safe and trustworthy. CAPTCHA incorporates some complicated pictures in some cases and owing to noisy values, it might be difficult to distinguish the characters from these images. Using machine-learning approaches, several researchers have attempted to overcome this challenge. As a result, the focus of this work is on a comparison of classification algorithms such as k-NN, SVM, and CNN for recognising CAPTCHA characters in the literature. After a careful review of the past work, it has been determined that CNN, rather than k-NN or SVM, is the most accurate strategy in terms of classification accuracy. In the future, CNN might be used to improve the process of character recognition.
Keywords
CAPTCHA, k-NN, SVM, CNN.
Cite as
Dipika Malhotra and Satinder Kaur, "Recognition Of CAPTCHA Characters Using Machine Learning Algorithms", In: Saroj Hiranwal and Garima Mathur (eds), Artificial Intelligence and Communication Technologies, SCRS, India, 2022, pp. 101-106. https://doi.org/10.52458/978-81-955020-5-9-10