Journal of Information Processing Systems

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Study of Hollow Letter CAPTCHAs Recognition Technology Based on Color Filling Algorithm

  • Huishuang Shao (College of Computer Science and Technology, Chongqing University of Posts and Telecommunications) ;
  • Yurong Xia (Dept. of Training Center, Jining Polytechnic) ;
  • Kai Meng (China Unicom Shanxi Industrial Internet Limited Company) ;
  • Changhao Piao (School of Automation, Chongqing University of Posts and Telecommunications)
  • Received : 2021.02.09
  • Published : 2023.08.31
Download PDF
⟨ Previous Next ⟩

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 and increase the difficulty of machine recognition. Although convolutional neural networks can solve CAPTCHA in a single step, a good attack result heavily relies on sufficient training data. To address this challenge, we propose a seed filling algorithm that converts hollow characters to solid ones after contour line restoration and applies three rounds of detection to remove noise background by eliminating noise blocks. Subsequently, we utilize a support vector machine to construct a feature vector for recognition. Security analysis and experiments show the effectiveness of this algorithm during the pre-processing stage, providing favorable conditions for subsequent recognition tasks and enhancing the accuracy of recognition for hollow CAPTCHA.

Keywords

Acknowledgement

This paper is supported by the National Natural Science Foundation of China (No. 61703068).

References

  1. L. Von Ahn, M. Blum, and J. Langford, "Telling humans and computers apart automatically," Communications of the ACM, vol. 47, no. 2, pp. 56-60, 2004. https://doi.org/10.1145/966389.966390
  2. J. Yan and A. S. El Ahmad, "A low-cost attack on a Microsoft CAPTCHA," in Proceedings of the 15th ACM Conference on Computer and Communications Security, Alexandria, VA, 2008, pp. 543-554. https://doi.org/10.1145/1455770.1455839
  3. H. Gao, W. Wang, J. Qi, X. Wang, X. Liu, and J. Yan, "The robustness of hollow CAPTCHAs," in Proceedings of the 2013 ACM SIGSAC Conference on Computer and Communications Security, Berlin, Germany, 2013, pp. 1075-1086. https://doi.org/10.1145/2508859.2516732
  4. F. Stark, C. Hazirbas, R. Triebel, and D. Cremers, "Captcha recognition with active deep learning," in Proceedings of the Workshop on New Challenges in Neural Computation, Aachen, Germany, 2015, pp. 94-102.
  5. M. J. J. Ghrabat, G. Ma, I. Y. Maolood, S. S. Alresheedi, and Z. A. Abduljabbar, "An effective image retrieval based on optimized genetic algorithm utilized a novel SVM-based convolutional neural network classifier," Human-centric Computing and Information Sciences, vol. 9, article no. 31, 2019. https://doi.org/10.1186/s13673-019-0191-8
  6. F. Zhang, T. Y. Wu, J. S. Pan, G. Ding, and Z. Li, "Human motion recognition based on SVM in VR art media interaction environment," Human-centric Computing and Information Sciences, vol. 9, article no. 40, 2019. https://doi.org/10.1186/s13673-019-0203-8
  7. S. Shokat, R. Riaz, S. S. Rizvi, A. M. Abbasi, A. A. Abbasi, S. J. Kwon, "Deep learning scheme for character prediction with position-free touch screen-based Braille input method," Human-centric Computing and Information Sciences, vol. 10, article no. 41, 2020. https://doi.org/10.1186/s13673-020-00246-6
  8. G. Xu and S. Zhang, "Fast leaf recognition and retrieval using multi-scale angular description method," Journal of Information Processing Systems, vol. 16, no. 5, pp. 1083-1094, 2020. https://doi.org/10.3745/JIPS.02.0142
  9. R. E. Fan, P. H. Chen, C. J. Lin, and T. Joachims, "Working set selection using second order information for training support vector machines," Journal of Machine Learning Research, vol. 6, no. 12, pp. 1889-1918, 2005.
  10. M. A. I. Mahmoud and H. & Ren, "Forest fire detection and identification using image processing and SVM," Journal of Information Processing Systems, vol. 15, no. 1, pp. 159-168, 2019. https://doi.org/10.3745/JIPS.01.0038
  11. E. W. Dijkstra, "A note on two problems in connexion with graphs," Numerische Mathematik, vol. 1, p 269-271, 1959. https://doi.org/10.1007/BF01386390
  12. C. Y. Lee, "An algorithm for path connections and its applications," IRE Transactions on Electronic Computers, vol. 10, no. 3, pp. 346-365, 1961. https://doi.org/10.1109/TEC.1961.5219222
  13. H. Gao, W. Wang, and Y. Fan, "Divide and conquer: an efficient attack on Yahoo! CAPTCHA," in Proceedings of 2012 IEEE 11th International Conference on Trust, Security and Privacy in Computing and Communications, Liverpool, UK, 2012, pp. 9-16. https://doi.org/10.1109/TrustCom.2012.131
  14. H. Liu, Z. Wu, D. F. Hsu, B. S. Peterson, and D. Xu, "On the generation and pruning of skeletons using generalized Voronoi diagrams," Pattern Recognition Letters, vol. 33, no. 16, pp. 2113-2119, 2012. https://doi.org/10.1016/j.patrec.2012.07.014
  15. T. Y. Zhang and C. Y. Suen, "A fast parallel algorithm for thinning digital patterns," Communications of the ACM, vol. 27, no. 3, pp. 236-239, 1984. https://doi.org/10.1145/357994.358023
  16. C. C. Chang and C. J. Lin, "LIBSVM: a library for support vector machines," ACM Transactions on Intelligent Systems and Technology (TIST), vol. 2, no. 3, pp. 1-27, 2011. https://doi.org/10.1145/1961189.1961199
  17. J. Chen, X. Luo, J. Hu, D. Ye, and D. Gong, "An attack on hollow captcha using accurate filling and nonredundant merging," IETE Technical Review, vol. 35(sup1), pp. 106-118, 2018. https://doi.org/10.1080/02564602.2018.1520152