Bubble Captcha - A Start of the New Direction of Text Captcha Scheme Development

Abstract

CAPTCHA, A Completely Automated Public Turing test to tell Computers and Humans Apart, iswell-known system widely used in all sorts of internet services around the world designated to secure the webfrom an automatic malicious activity. For almost two decades almost every system utilize a simple approach tothis problem containing a transcription of distorted letters from image to a text eld. The ground idea is to useimperfection of Optical Character Recognition algorithms against the computers. The development of OpticalCharacter recognition algorithms leads only to state, where the CAPTCHA schemes become more complex andhuman users have a great di culty with the transcription.This paper aims to present a new way of development of CAPTCHA schemes based more a human perception.The goal of this work is to implement new Captcha scheme and assess human capability to read unusual fontsnewer seen before.

Usability Evaluation of Randomly Generated Fonts for Bubble Captcha

“…In previous work [5] we developed elementary bi-color Captcha scheme with randomly positioned circles/bubbles forming the font. The main reason was to prepare the framework to generate galleries to test and assess weaknesses of current OCR algorithms and compare results with success rate of other people.…”

“…Every bubble is randomly positioned approximately to its correct position in the grid and randomly scaled in size within predefined limits. The three different variants (denoted as a, b and c hereinafter) of Bubble Captcha are generated in this way as an input dataset of the supervised machine learning algorithms [5].…”

“…Our testing platform previously explained in [5] was extended with web annotating tool. The purpose of this platform was to evaluate the success rate of real people over the prepared gallery.…”

“…The goal of this work is to assess the usability of randomly generated font consist of bubbles to form abstract characters previously presented in [5] and later improved in [4]. We compare two main aspects.…”