A Novel Method to Recognise Closely Connected CAPTCHA

Abstract:

Nowadays, most of text CAPTCHAs use character connection as a primary means to avoid being recognized. To recognize this kind of CAPTCHA, a new image analysis model, Concept Component Analysis (CCA), is proposed. Based on the approaching idea in Newton’s iteration, this new model is solved by a multi-population genetic algorithm. Compared with traditional image analysis models, such as PCA, components obtained by CCA have obvious concept meanings. Images can be recognized by solely relying on these components, No classifier is needed. CCA has achieved good recognition results in our experiments. Suggestions for securing text recognition CAPTCHAs are also provided based on experiments results.

• Periodical: Advanced Materials Research (Volumes 457-458)
• Pages: 620-627
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.457-458.620
• Online since: January 2012
• Authors: Liang Zhang, Shu Guang Huang, Rong Gui Hu, He Ping Tang, Zhao Xiang Shi
• Keywords: Completely Automated Public Turing Test to Tell Computers and Humans Apart (CAPTCHA), Concept Component Analysis, Human Interactive Proofs (HIPs), Image Processing

References

[1] Luis von Ahn, Manuel Blum, Nicholas J. Hopper and John Langford, CAPTCHA: Using Hard AI Problems for Security, Advances in Cryptology, Eurocrypt, 2003. pp: 294-311.

DOI: 10.1007/3-540-39200-9_18

[2] Luis von Ahn, Manuel Blum, Nicholas J. Hopper and John Langford. The CAPTCHA Web Page: http: /www. captcha. net. (2000).

[3] Luis von Ahn, Benjamin Maurer, Colin McMillen, David Abraham, Manuel Blum, reCAPTCHA: Human-Based Character Recognition via Web Security Measures, SCIENCE, Vol 321, 2008. 9.

DOI: 10.1126/science.1160379

[4] Amalia Rusu and Venu Govindaraju, Handwritten CAPTCHA: Using the difference in the abilities of humans and machines in reading handwritten words, Proceedings of the 9th Int'l Workshop on Frontiers in Handwriting Recognition (IWFHR-9 2004).

DOI: 10.1109/iwfhr.2004.54

[5] Clark Pope and Khushpreet Kaur, Is It Human or Computer? Defending E-Commerce with Captchas, IT Pro, March❘April (2005).

DOI: 10.1109/mitp.2005.37

[6] M. Turk, A. Pentland. Eigenface for Recognition. Journal of Cognitive Neuro Science. 1991, 3(1), pp: 71-86.

[7] Jian Yang, David Zhang, F. Alejandro and Jing-yu Yang. Two-Dimensional PCA: A New Approach to Appearance-Based Face Representation and Recognition. IEEE Trans. on Pattern Analysis and Machine Intelligence. 2004, 26(1), pp: 117~129.

DOI: 10.1109/tpami.2004.1261097

[8] M.S. Bartlett. H. M. Lades and T.J. Sejnowsld, Independent Component Representations for Face Recognition, Proc. of SPIE. 1998. pp: 528-539.

[9] Iorio A, X Li. Parameter control within a co-operative co-evolutionary genetic algorithm. In Proceedings of the Seventh Conference on Parallel Problem Solving From Nature. 2002. pp: 247-256.

DOI: 10.1007/3-540-45712-7_24

[10] Matthew Wall, GAlib: A C++ Genetic Algorithm Library, version 2. 4. 7, http: /lancet. mit. edu/ga/dist/, (2007).

[11] Rich Gossweiler, Maryam Kamvar, Shumeet Baluja, What's Up CAPTCHA? A CAPTCHA Based On Image Orientation, International World Wide Web Conference Committee (IW3C2). WWW 2009, April 20–24, (2009).

DOI: 10.1145/1526709.1526822

[12] Horst Bunke, Recognition of Cursive Roman Handwriting -Past, Present and Future, Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR'03), (2003).

DOI: 10.1109/icdar.2003.1227707