Abstract
A CAPTCHA which humans find to be highly legible and which is designed to resist automatic character–segmentation attacks is described. As first detailed in [BR05], these ‘ScatterType’ challenges are images of machine-print text whose characters have been pseudorandomly cut into pieces which have then been forced to drift apart. This scattering is designed to repel automatic segment-then-recognize computer vision attacks. We report results from an analysis of data from a human legibility trial with 57 volunteers that yielded 4275 CAPTCHA challenges and responses. We have located an operating regime—ranges of the parameters that control cutting and scattering—within which human legibility is high (better than 95% correct) even though the degradations due to scattering remain severe.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Blum, M., von Ahn, L.A., Langford, J.: The CAPTCHA Project, Completely Automatic Public Turing Test to tell Computers and Humans Apart, Dept. of Computer Science, Carnegie-Mellon Univ., www.captcha.net , and personal communications (November 2000)
Baird, H.S., Popat, K.: Human Interactive Proofs and Document Image Analysis. In: Lopresti, D.P., Hu, J., Kashi, R.S. (eds.) DAS 2002. LNCS, vol. 2423, pp. 507–518. Springer, Heidelberg (2002)
Baird, H.S., Riopka, T.: ScatterType: a Reading CAPTCHA Resistant to Segmentation Attack. In: Proc., IS&T/SPIE Document Recognition & Retrieval XII Conf., San Jose, CA, January 16-20 (2005)
AltaVista’s “Add-URL” site: altavista.com/sites/addurl/newurl , protected by the earliest known CAPTCHA
Chew, M., Baird, H.S.: BaffleText: a Human Interactive Proof. In: Proc., 10th SPIE/IS&T Document Recognition and Retrieval Conf (DRR2003), Santa Clara, CA, January 23-24 (2003)
Coates, A.L., Baird, H.S., Fateman, R.: Pessimal Print: a Reverse Turing Test. In: Proc. IAPR 6th Intl. Conf. on Document Analysis and Recognition, Seattle,WA, September 10-13, pp. 1154–1158 (2001)
Hopper, N.J., Blum, M.: Secure Human Identification Protocols. In: Boyd, C. (ed.) ASIACRYPT 2001. LNCS, vol. 2248, pp. 52–66. Springer, Heidelberg (2001)
Lillibridge, M.D., Abadi, M., Bharat, K., Broder, A.Z.: Method for Selectively Restricting Access to Computer Systems, U.S. Patent No. 6,195,698, Issued February 27 (2001)
Legge, G.E., Pelli, D.G., Rubin, G.S., Schleske, M.M.: Psychophysics of Reading: I. Normal Vision. Vision Research 25(2), 239–252 (1985)
Mori, G., Malik, J.: Recognizing Objects in Adversarial Clutter: Breaking a Visual CAPTCHA. In: Proc. IEEE CS Society Conf. on Computer Vision and Pattern Recognition (CVPR 2003), Madison, WI, June 16-22 (2003)
Nagy, G., Seth, S.: Modern optical character recognition. The Froehlich / Kent Encyclopaedia of Telecommunications 11, 473–531 (1996)
Pavlidis, T.: Thirty Years at the Pattern Recognition Front. In: King-Sun Fu Prize Lecture, 11th ICPR, Barcelona (September 2000)
PayPal Captha, on display starting in 2002 at www.paypal.com
Rice, S.V., Nagy, G., Nartker, T.A.: OCR: An Illustrated Guide to the Frontier. Kluwer Academic Publishers, Dordrecht (1999)
Rice, S.V., Jenkins, F.R., Nartker, T.A.: The Fifth Annual Test of OCR Accuracy, ISRI TR-96-01, Univ. of Nevada, Las Vegas (1996)
Saygin, A.P., Cicekli, I., Akman, V.: Turing Test: 50 Years Later. Minds and Machines 10(4), Kluwer (2000)
Sarkar, P., Nagy, G.: Style Consistent Classification of Isogenous Patterns. IEEE Trans. on PAMI 27(1) (January 2005)
Simard, P.Y., Szeliski, R., Benaloh, J., Couvreur, J., Calinov, I.: Using Character Recognition and Segmentation to Tell Computer from Humans. In: Proc. IAPR Int’l Conf. on Document Analysis and Recognition, Edinburgh, Scotland, August 4–6 (2003)
Turing, A.: Computing Machinery and Intelligence. Mind 59(236), 433–460 (1950)
Veeramachaneni, S., Nagy, G.: Style context with second order statistics. IEEE Trans. on PAMI 27(1) (January 2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Baird, H.S., Moll, M.A., Wang, SY. (2005). A Highly Legible CAPTCHA That Resists Segmentation Attacks. In: Baird, H.S., Lopresti, D.P. (eds) Human Interactive Proofs. HIP 2005. Lecture Notes in Computer Science, vol 3517. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11427896_2
Download citation
DOI: https://doi.org/10.1007/11427896_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26001-1
Online ISBN: 978-3-540-32117-0
eBook Packages: Computer ScienceComputer Science (R0)