Study of Hollow Letter CAPTCHAs Recognition Technology Based on Color Filling Algorithm
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The hollow letter CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart)is an optimized version of solid CAPTCHA, specifically designed to weaken characteristic information andincrease the difficulty of machine recognition. Although convolutional neural networks can solve CAPTCHAin a single step, a good attack result heavily relies on sufficient training data. To address this challenge, wepropose a seed filling algorithm that converts hollow characters to solid ones after contour line restoration andapplies three rounds of detection to remove noise background by eliminating noise blocks. Subsequently, weutilize a support vector machine to construct a feature vector for recognition. Security analysis and experimentsshow the effectiveness of this algorithm during the pre-processing stage, providing favorable conditions forsubsequent recognition tasks and enhancing the accuracy of recognition for hollow CAPTCHA.
Abstract
The hollow letter CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart)is an optimized version of solid CAPTCHA, specifically designed to weaken characteristic information andincrease the difficulty of machine recognition. Although convolutional neural networks can solve CAPTCHAin a single step, a good attack result heavily relies on sufficient training data. To address this challenge, wepropose a seed filling algorithm that converts hollow characters to solid ones after contour line restoration andapplies three rounds of detection to remove noise background by eliminating noise blocks. Subsequently, weutilize a support vector machine to construct a feature vector for recognition. Security analysis and experimentsshow the effectiveness of this algorithm during the pre-processing stage, providing favorable conditions forsubsequent recognition tasks and enhancing the accuracy of recognition for hollow CAPTCHA.
참고문헌 (17)
- Luis von Ahn, "Telling humans and computers apart automatically", Communications of the ACM, 47(2), pp.56~60 (2004), Association for Computing Machinery (ACM)[DOI]
- J. Yan, "A low-cost attack on a Microsoft CAPTCHA", Proceedings of the 15th ACM Conference on Computer and Communications Security, pp.543~554 (2008)
- H. Gao, "The robustness of hollow CAPTCHAs", Proceedings of the 2013 ACM SIGSAC Conference on Computer and Communications Security, pp.1075~1086 (2013)
- F. Stark, "Captcha recognition with active deep learning", Proceedings of the Workshop on New Challenges in Neural Computation, pp.94~102 (2015)
- M. J. J. Ghrabat, "An effective image retrieval based on optimized genetic algorithm utilized a novel SVM-based convolutional neural network classifier", Human-centric Computing and Information Sciences, 9 (2019)[DOI]
- Fuquan Zhang, "Human motion recognition based on SVM in VR art media interaction environment", Human-centric Computing and Information Sciences, 9(1) (2019), Springer Science and Business Media LLC[DOI]
- Sana Shokat, "Deep learning scheme for character prediction with position-free touch screen-based Braille input method", Human-centric Computing and Information Sciences, 10(1) (2020), Springer Science and Business Media LLC[DOI]
- Guoqing Xu, "Fast Leaf Recognition and Retrieval Using Multi-Scale Angular Description Method", JIPS(Journal of Information Processing Systems), 16(5), pp.1083~1094 (2020), 한국정보처리학회[DOI]
- R. E. Fan, "Working set selection using second order information for training support vector machines", Journal of Machine Learning Research, 6(12), pp.1889~1918 (2005)
- Mubarak Adam Ishag Mahmoud, "Forest fire detection and identification using image processing and SVM", JIPS(Journal of Information Processing Systems), 15(1), pp.159~168 (2019), 한국정보처리학회[DOI]
- E. W. Dijkstra, "A note on two problems in connexion with graphs", Numerische Mathematik, 1(1), pp.269~271 (1959), Springer Science and Business Media LLC[DOI]
- C. Y. Lee, "An Algorithm for Path Connections and Its Applications", IEEE Transactions on Electronic Computers, EC-10(3), pp.346~365 (1961), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- H. Gao, "Divide and conquer: an efficient attack on Yahoo! CAPTCHA", Proceedings of 2012 IEEE 11th International Conference on Trust, Security and Privacy in Computing and Communications, pp.9~16 (2012)
- H. Liu, "On the generation and pruning of skeletons using generalized Voronoi diagrams", Pattern Recognition Letters, 33(16), pp.2113~2119 (2012)[DOI]
- T. Y. Zhang, "A fast parallel algorithm for thinning digital patterns", Communications of the ACM, 27(3), pp.236~239 (1984), Association for Computing Machinery (ACM)[DOI]
- Chih-Chung Chang, "LIBSVM", ACM Transactions on Intelligent Systems and Technology, 2(3), pp.1~27 (2011), Association for Computing Machinery (ACM)[DOI]
- Jun Chen, "An Attack on Hollow CAPTCHA Using Accurate Filling and Nonredundant Merging", IETE Technical Review, 35(sup1), pp.106~118 (2018), Informa UK Limited[DOI]