Advertisement

Document Image Watermarking Based on Weight-Invariant Partition Using Support Vector Machine

  • Shiyan Hu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3163)

Abstract

Security concern about document images is important since document images are distributed in large amount both electronically and physically. They are easily copied and the copyright information is difficult to identify. In this paper, we present a new algorithm for document image watermarking, which is based on weight-invariant partition of the document in the spatial domain, where the weight of a partition is the average number of pixels in lines within the partition. We discuss the issues of robustness, security, capacity and fault-tolerance related to the watermarking method. In order to simultaneously achieve high capacity and security, the partition method is further improved using the support vector machine technique. The experiments indicate the soundness of our method.

Keywords

Support Vector Machine Image Watermark Document Image Watermark Scheme Text Line 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Amano, T., Misaki, D.: A Feature Calibration Method for Watermarking of Document Images. In: Proc. 5th Int. Conf. Document Analysis and Recognition, September 1999, pp. 91–94 (1999)Google Scholar
  2. 2.
    Barabino, N., Pallavicini, M., Petrolini, A., Pontil, M., Verri, A.: Support Vector Machines vs Multi-layer Perceptrons in Particle Identification. In: Proc. Euro. Symp. Artifical Neural Networks, pp. 257–262 (1999)Google Scholar
  3. 3.
    Brassil, J., Low, S., Maxemchuk, N.: Copyright Protection for the Electronic Distribution of Text Documents. Proc. IEEE 87, 1181–1196 (1999)CrossRefGoogle Scholar
  4. 4.
    Brassil, J., O’Gorman, L.: Watermarking Document Images with Bounding Box Expansion. In: Proc. Info Hiding, pp. 227–235 (1996)Google Scholar
  5. 5.
    Cortes, C., Vapnik, V.: Support Vector Networks. Machine Learning 20, 273–297 (1995)zbMATHGoogle Scholar
  6. 6.
    Dumais, S., Plat, J., Heckerman, D., Sahami, M.: Inductive Learning Algorithms and Representation for Text Categorization. In: Proc. 7th ACM Int. Conf. Information and Knowledge Management, pp. 148–155 (1998)Google Scholar
  7. 7.
    Fridrich, J., Goljan, M., Baldoza, A.C.: New Fragile Authentication Watermark for Images. In: Proc. IEEE Int. Conf. Image Processing, September 2000, vol. 1, pp. 446–449 (2000)Google Scholar
  8. 8.
    Furey, T.S., Christianini, N., Duffy, N., Bednarski, D.W., Schummer, M., Hauessler, D.: Support Vector Machine Classification and Validation of Cancer Tissue Samples using Microarray Expression Data. Bioinformatics 16(10), 906–914 (2000)CrossRefGoogle Scholar
  9. 9.
    Guo, G., Li, S., Chan, K.: Face Recognition by Support Vector Machines. In: Proc. Int. Conf. Automatic Face and Gesture Recognition, pp. 196–201 (2000)Google Scholar
  10. 10.
    Guo, H., Georganas, N.D.: A Novel Approach to Digital Image Watermarking Based on A Generalized Secret Sharing Scheme. ACM/Springer Multimedia Systems J. (to appear)Google Scholar
  11. 11.
    Holliman, M., Memon, N.: Counterfeiting Attacks on Oblivious Block-wise Independent Invisible Watermarking Schemes. IEEE Trans. Image Processing 9, 432–441 (2000)CrossRefGoogle Scholar
  12. 12.
    Jiang, G., Yu, M., Shi, S., Liu, X., Kim, Y.: New Blind Image Watermarking in DCT Domain. In: Proc. 6th Int. Conf. Signal Processing, vol. 2, pp. 1580–1583 (August 2002)Google Scholar
  13. 13.
    Low, S., Maxemchuk, N.: Capacity of Text Marking Channel. IEEE Signal Processing Letters 7(12), 345–347 (2000)CrossRefGoogle Scholar
  14. 14.
    Low, S., Maxemchuk, N., Lapone, A.: Document Identification for Copyright Protection using Centroid Detection. IEEE Trans. Communications 46, 372–383 (1998)CrossRefGoogle Scholar
  15. 15.
    Lu, H., Shen, R., Chung, F.: Fragile Watermarking Scheme for Image Authentication. Electronics Letters 39, 898–900 (2003)CrossRefGoogle Scholar
  16. 16.
    Mayer, J., Silva, R.A.: Efficient Informed Embedding of Multi-bit Watermark. In: International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. III, pp. 399–402 (2004)Google Scholar
  17. 17.
    Moulin, P., Mihcak, M., Lin, G.: An Information-Theoretic Model for Image Watermarking and Data Hiding. In: Proc. Int. Conf. Image Processing, September 2000, vol. 3, pp. 667–670 (2000)Google Scholar
  18. 18.
    Pontil, M., Verri, A.: Support Vector Machines for 3D Object Recognition. IEEE Trans. Pattern Analysis and Machine Intelligence, 637–646 (1998)Google Scholar
  19. 19.
    Qi, X., Qi, J.: Improved Affine Resistant Watermarking by using Robust Templates. In: International Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. III, pp. 405–408 (2004)Google Scholar
  20. 20.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)zbMATHGoogle Scholar
  21. 21.
    Wong, P.W., Memon, N.: Secret and Public Key Image Watermarking Schemes for Image Authentication and Ownership Verification. IEEE Trans. Image Processing 10, 153–1601 (2001)Google Scholar
  22. 22.
    Yeung, M., Mintzer, F.: An Invisible Watermark Technique for Image Verification. In: Proc. Int. Conf. Image Processing, vol. 1, pp. 680–683 (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Shiyan Hu
    • 1
  1. 1.Department of Computer and Information SciencePolytechnic UniversityBrooklynUSA

Personalised recommendations