Abstract The study of CAPTCHA recognition can discover CAPTCHA security vulnerabilities in time to make it more secure. Distorted and merged CAPTCHA can resist character segmentation,which is the difficult in CAPTCHA recognition. An approach based on DENSE SIFT and RANSAC algorithm is presented for recognition of distorted and merged CAPTCHA. Firstly,matching set is obtained through the matching of DENSE SIFT. Then,matching information is got by using RANSAC algorithm. Finally,recognition results are acquired by means of queue-analysis algorithm. The experimental results show that the proposed method has good performance on CAPTCHAs in different levels of difficulty.
[1] Chellapilla K,Simard P Y. Using Machine Learning to Break Visual Human Interaction Proofs // Proc of the Advances in Neural Information Processing Systems. Cambridge,USA,2005: 265-272 [2] Chandavale A A,Sapkal A M,Jalnekar R M. Algorithm to Break Visual CAPTCHA // Proc of the 2nd International Conference on Emerging Trends in Engineering and Technology. Nagpur,India,2009: 258-262 [3] Zhang J S,Wang X F. Breaking Internet Banking CAPTCHA Based on Instance Learning // Proc of the 3rd International Symposium on Computational Intelligence and Design. Hangzhou,China,2010: 39-43 [4] Yin G,Tao L. Verified Code Recognition Algorithm Based on SVM. Computer Engineering and Applications,2011,47(18): 188-190 ( in Chinese) (殷 光,陶 亮.一种SVM验证码识别算法.计算机工程与应用,2011,47(18): 188-190 ) [5] Wang L. The Research on CAPTCHA Recognition Technology. Master Dissertation. Hefei,China: University of Science and Technology of China,2010 ( in Chinese) (王 璐.验证码识别技术研究.硕士学位论文.合肥:中国科学技术大学,2010 ) [6] Gao H C,Wang W,Fan Y. Divide and Conquer: An Efficient Attack on Yahoo! CAPTCHA // Proc of the 11th IEEE International Conference on Trust,Security and Privacy in Computing and Communications. Liverpool,UK,2012: 9-16 [7] Bursztein E,Martin M,Mitchell J C. Text-Based CAPTCHA Strengths and Weaknesses // Proc of the ACM Conference on Computer and Communications Security. Chicago,USA,2011: 125-138 [8] Zhang L,Huang S G,Shi Z X,et al. CAPTCHA Recognition Method Based on RNN of LSTM. Pattern Recognition and Artificial Intelligence,2011,24(1): 40-47 ( in Chinese) (张 亮,黄曙光,石昭祥,等.基于LSTM型RNN的CAPTCHA识别方法.模式识别与人工智能,2011,24(1): 40-47) [9] Lowe D G. Distinctive Image Features form Scale Invariant Keypoints. International Journal of Computer Vision,2004,60(2): 91-110 [10] Liu C,Yuen J,Torralba A. SIFT Flow: Dense Correspondence across Scenes and Its Applications. IEEE Trans on Pattern Analysis and Machining Intelligence,2011,33(5): 978-994 [11] Szeliski R. Computer Vision. London,UK: Springer-Verlag,2010 [12] Papazov C,Burschka D. An Effcient RANSAC for 3D Object Recognition in Noisy and Occluded Scenes // Proc of the 10th Asian Conference on Computer Vision. Queenstown,New Zealand,2010: 135-148
2014, Vol. 27 
