Abstract
CAPTCHA is a completely automated public Turing test which has been broadly adopted to enhance the website security and strengthen its attack resistance ability. The research of recognition technology of CAPTCHA has a great benefit for increasing the machine learning ability and aiding to designing high security code. The work in this paper focuses on the most difficult adhesion code in picture. At present, the traditional methods which depend heavily on segmentation will become invalid for most adhesion picture code. To resolve the problem, an integrated recognition algorithm based on mask matching is presented in this paper. The recognition of picture code is completed regardless of segmentation and noise removal beforehand. Especially, the matching degree is controlled by a fuzzy factor which can be adjusted automatically to meet with the picture code. During mask creation, two kinds of methods are provided. Finally, a series of experiments from different websites demonstrate that the algorithm can crack all kinds of picture codes and has a satisfied performance in time and popularity.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Baidu. Captcha, http://baike.baidu.com/view/538168.htm
Mori G, Malik J (2003) Recognizing objects in adversarial clutter: breaking a visual captcha. In: IEEE conference on computer vision and pattern recognition, vol 1. Madison, pp 124–141, June 2003
Moy G, Jones N, Harkless C (2004) Distortion estimation techniques in solving visual captchas. In: IEEE conference on computer vision and pattern recognition, vol 2. Washington, DC, pp 23–28, June 2004
Yan J, EI Ahmad AS (2008) Low-cost attack on a Microsoft captcha. In: Proceedings of the 15th ACM conference on computer and communications security, ACM Press, New York, USA, pp 543–554
Chandavale AA, Sapka AM, Jalnekar RM (2009) Algorithm to break visual captcha. In: 2nd international conference on emerging trends in engineering and technology, pp 258–262
Yin G, Tao L (2011) Verified code recognition algorithm based on SVM. Comput Eng Appl 18:188–190
Wang L, Zhang R, Yin D, Zhan J-C, Wu C-Y (2011) Breaking visual CAPTCHA of merged character. Comput Eng Appl 28:150–153
Pan D-F, Wang B (2007) A digit validation image recognition algorithm based on exterior contour. Microcomput Inf 25:256–258
He Q, Yan L (2011) Recognition algorithm of complicated CAPTCHA based on shape context. Comput Eng 2:200–202
Acknowledgments
The work is supported by National Natural Science Foundation of China (No:61303080), Natural Science Foundation of Fujian Province (No:2013J01249) and High-level Talent Project of Xiamen University of Technology (No:YKJ12024R).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, H., Wen, X. (2014). The Recognition of CAPTCHA Based on Fuzzy Matching. In: Wen, Z., Li, T. (eds) Foundations of Intelligent Systems. Advances in Intelligent Systems and Computing, vol 277. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-54924-3_71
Download citation
DOI: https://doi.org/10.1007/978-3-642-54924-3_71
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-54923-6
Online ISBN: 978-3-642-54924-3
eBook Packages: EngineeringEngineering (R0)