Usability Evaluation of Randomly Generated Fonts for Bubble Captcha

  • Ondrej Bostik
  • Karel Horak
  • Jan Klecka
Keywords: OCR, CAPTCHA, Neural Networks, k-NN, Decision trees, SVM, Bubble Captcha


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.


von Ahn, L., Maurer, B., Mcmillen, C., Abraham, D., Blum, M.: reCAPTCHA: Human-Based Character Recognition via Web Security Measures. Science (80-. ). 321(12 September 2008), 1465–1468 (2008). DOI 10.1126/science.1160379. URL

Altman, N.S.: An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression. Am. Stat. 46(3), 175–185 (1992). DOI 10.1080/00031305.1992.10475879. URL

Bishop, C.M.: Pattern recognition and machine learning. Springer (2006). URL

Bostik, O.: Creating a Random Characters for Captcha Schemes From Existing Fonts. In: V. Nov´ak (ed.) Proc. 24nd Conf. STUDENT EEICT 2018, p. 5. Brno University of Technology, Brno (2018)

Bostik, O., Horak, K., Klecka, J., Davidek, D.: Bubble CAPTCHA - A Start of the New Direction of Text CAPTCHA Scheme Development. In: Mendel, 23, vol. 23, pp. 57–64. Brno University of Technology (2017). URL

Bostik, O., Klecka, J.: Recognition of CAPTCHA Characters by Supervised Machine Learning Algorithms. In: 15th IFAC Conf. Program. Devices Embed. Syst. PDES 2018, p. 6. IFAC-PapersOnLine, Ostrava (2018)

Breiman, L., Friedman, J., Stone, C.J., Olshen, R.: Classification and regression trees. Chapman & Hall (1993). URL

Bursztein, E., Martin, M., Mitchell, J.C.: Text-based CAPTCHA strengths and weaknesses. Proc. 18th ACM Conf. Comput. Commun. Secur. 2011, 125–138 (2011). DOI 10.1145/2046707.2046724. URL

Carnegie Mellon University: The Official CAPTCHA Site (2010). URL

Cortes, C., Vapnik, V.N.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995). DOI 10.1007/BF00994018. URL

Dietterich, T.G., Bakiri, G.: Solving Multiclass Learning Problems via Error-Correcting Output Codes. J. Artif. Intell. Res. (1994). URL

Kaur, K., Behal, S.: Designing a Secure Text-based CAPTCHA. In: Procedia Comput. Sci., vol. 57, pp. 122–125. Elsevier (2015). DOI 10.1016/j.procs.2015.07.381

Møller, M.F.: A scaled conjugate gradient algorithm for fast supervised learning. NEURAL NETWORKS 6(4), 525—-533 (1993). URL

Rokach, L., Maimon, O.: Data Mining with Decision Trees, 2 edn. Series in Machine Perception and Artificial Intelligence. World Scientific (2014). DOI 10.1142/9097. URL

How to Cite
Bostik, O., Horak, K. and Klecka, J. 2018. Usability Evaluation of Randomly Generated Fonts for Bubble Captcha. MENDEL. 24, 1 (Jun. 2018), 143-150. DOI: