On random field CAPTCHA generation
Michael A. Kouritzin, Bi Wu, Fraser Newton · ERA: Education and Research Archive (University of Alberta) · 2013
Herein, we propose generating CAPTCHAs through random field simulation and give a novel, effective and efficient algorithm to do so. Indeed, we demonstrate that sufficient information about word tests for easy human recognition is contained in the site marginal probabilities and the site-to-nearby-site covariances and these quantities can be embedded into KNW conditional probabilities, designed for effective simulation. The CAPTCHAs are then partial random realizations of the random CAPTCHA word: we start with an initial random field (e.g., randomly scattered letter pieces) and use Gibbs resampling to re-simulate portions of the field repeatedly using the KNW conditional probabilities until the word becomes human-readable. The residual randomness from the initial random field together with the random implementation of the CAPTCHA word provide significant resistance to attack. This results in a CAPTCHA which is unrecognizable to modern OCR but is recognized about 95% of the time in a human readability study. Image processing, security, statistical information compression, Markov random field, simulation.