Robust reconstruction of low-resolution document images by exploiting repetitive character behaviour

  • Hiêp Q. LuongEmail author
  • Wilfried Philips
Original Paper


In this paper, we present a new approach for reconstructing low-resolution document images. Unlike other conventional reconstruction methods, the unknown pixel values are not estimated based on their local surrounding neighbourhood, but on the whole image. In particular, we exploit the multiple occurrence of characters in the scanned document. In order to take advantage of this repetitive behaviour, we divide the image into character segments and match similar character segments to filter relevant information before the reconstruction. A great advantage of our proposed approach over conventional approaches is that we have more information at our disposal, which leads to a better reconstruction of the high-resolution (HR) image. Experimental results confirm the effectiveness of our proposed method, which is expressed in a better optical character recognition (OCR) accuracy and visual superiority to other traditional interpolation and restoration methods.


Repetition Restoration Interpolation Character segmentation Bimodal distribution OCR 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Allier B., Bali N., Emptoz H.: Automatic accurate broken character restoration for patrimonial documents. Int. J. Document Anal 8(4), 246–261 (2006)CrossRefGoogle Scholar
  2. 2.
    Bern, M., Goldberg, D.: Scanner-model-based document image improvement. In: Proceedings of IEEE International Conference of Image Processing, pp. 582–585 (2000)Google Scholar
  3. 3.
    Buades A., Coll B., Morel J.: Image denoising by non-local averaging. Proc. IEEE Int. Conf. Acoust. Speech Signal Process. 2, 25–28 (2005)CrossRefGoogle Scholar
  4. 4.
    Cannon M., Hochberg J., Kelly P.: Quality assessment and restoration of typewritten document images. Int. J. Document Anal. Recognit. 2(2–3), 80–89 (1999)CrossRefGoogle Scholar
  5. 5.
    Capel, D.P., Zisserman, A.: Super-resolution enhancement of text image sequences. In: Proceedings of International Conference on Pattern Recognition, pp. 600–605 (2000)Google Scholar
  6. 6.
    Casey R.G., Lecolinet E.: A survey of methods and strategies in character segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 18(7), 690–706 (1996)CrossRefGoogle Scholar
  7. 7.
    Chiandussi S., Ramponi G.: Nonlinear unsharp masking for the enhancement of document images. Proc. Eighth Eur. Signal Process. Conf. 1, 575–578 (1996)Google Scholar
  8. 8.
    Dalley, G., Freeman, W., Marks, J.: Single-frame text super-resolution: a Bayesian approach. In: Proceedings of IEEE International Conference of Image Processing, pp. 3295–3298 (2004)Google Scholar
  9. 9.
    Datsenko D., Elad M.: Example-based single image super-resolution: a global MAP approach with outlier rejection. J. Multidimensional Syst Signal Process 18(2–3), 103–121 (2007)zbMATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Dempster A.P., Lairde N.M., Rubin D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Ser. B (Methodological) 39(1), 1–38 (1977)zbMATHGoogle Scholar
  11. 11.
    Donaldson K., Myers G.: Bayesian super-resolution of text in video with a text-specific bimodal prior. Int. J. Document Anal. Recognit. 7, 159–167 (2005)CrossRefGoogle Scholar
  12. 12.
    Farsiu S., Robinson M.D., Elad M., Milanfar P.: Fast and robust multiframe super resolution. IEEE Trans. Image Process. 13, 1327–1344 (2004)CrossRefGoogle Scholar
  13. 13.
    Forney G.D.: The viterbi algorithm. Proc. IEEE 61(3), 268–278 (1973)CrossRefMathSciNetGoogle Scholar
  14. 14.
    Freeman W.T., Jones T.R., Pasztor E.C.: Example-based super-resolution. IEEE Comput. Graph. Appl. 22(2), 55–65 (2002)CrossRefGoogle Scholar
  15. 15.
    Hobby, J., Ho, T.K.: Enhancing degraded document images via bitmap clustering and averaging. In: Proceedings of the 4th International Conference on Document Analysis and Recognition, pp. 394–400 (1997)Google Scholar
  16. 16.
    Kia O.E., Doermann D.S., Rosenfeld A., Chellappa R.: Symbolic compression and processing of document images. J. Comput. Vision Image Underst. 70(3), 335–349 (1998)CrossRefGoogle Scholar
  17. 17.
    Lange K., Little R., Taylor J.: Robust statistical modeling using the t-distribution. J. Am. Stat. Assoc. 84(408), 881–896 (1989)CrossRefMathSciNetGoogle Scholar
  18. 18.
    Ledda, A., Luong, H.Q., Philips, W., De Witte, V., Kerre, E.E.: Greyscale image interpolation using mathematical morphology. Lecture Notes in Computer Science, vol. 4179 (Advanced Concepts For Intelligent Vision Systems), pp. 78–90 (2006)Google Scholar
  19. 19.
    Lee S.W., Lee D.J., Park H.S.: A new methodology for gray-scale character segmentation and recognition. IEEE Trans. Pattern Anal. Mach. Intell. 18(10), 1045–1050 (1996)CrossRefGoogle Scholar
  20. 20.
    Lehmann T., Gönner C., Spitzer K.: Survey: interpolations methods in medical image processing. IEEE Trans. Med. Imaging 18, 1049–1075 (1999)CrossRefGoogle Scholar
  21. 21.
    Li H., Doermann D.: Text enhancement in digital video using multiple frame integration. Proc. ACM Multimed. 99, 19–22 (1999)Google Scholar
  22. 22.
    Li X., Orchard M.T.: New edge-directed interpolation. IEEE Trans. Image Process. 10, 1521–1527 (2001)CrossRefGoogle Scholar
  23. 23.
    Liang J., Doermann D., Li H.: Camera-based analysis of text and documents: a survey. Int. J. Document Anal. Recognit. 7, 84–104 (2005)CrossRefGoogle Scholar
  24. 24.
    Liu C., Rubin D.B., Wu Y.N.: Parameters expansion to accelerate EM: the PX-EM algorithm. Biometrika 85(4), 755–770 (1998)zbMATHCrossRefMathSciNetGoogle Scholar
  25. 25.
    Luong H.Q., De Smet P., Philips W.: Image interpolation using constrained adaptive contrast enhancement techniques. Proc. IEEE Int. Conf. Image Process. 2, 998–1001 (2005)Google Scholar
  26. 26.
    Luong, H.Q., Ledda, A., Philips, W.: Non-local interpolation. In: Proceedings of IEEE International Conference of Image Processing, pp. 693–696 (2006)Google Scholar
  27. 27.
    Mancas-Thillou, C., Mirmehdi, M.: An introduction to super-resolution text. Digital Document Processing: Major Directions and Recent Advances (Advances in Pattern Recognition), pp. 305–327. Springer, Berlin (2007)Google Scholar
  28. 28.
    Meijering E.H.W., Niessen W.J., Viergever M.A.: Quantitative evaluation of convolution-based methods for medical image interpolation. Med. Image Anal. 5, 111–126 (2001)CrossRefGoogle Scholar
  29. 29.
    Morse, B.S., Schwartzwald, D.: Isophote-based interpolation. In: Proceedings of IEEE International Conference on Image Processing, pp. 227–231 (1998)Google Scholar
  30. 30.
    Muresan D.: Fast edge directed polynomial interpolation. Proc. IEEE Int. Conf. Image Process. 2, 990–993 (2005)Google Scholar
  31. 31.
    Navarro G.: A guided tour to approximate string matching. ACM Comput. Surv. 33(1), 31–88 (2001)CrossRefGoogle Scholar
  32. 32.
    Pižurica, A., Vanhamel, I., Sahli, H., Philips, W., Katartzis, A.: A Bayesian approach to nonlinear diffusion based on a Laplacian prior for ideal image Gradient. In: Proceedings of IEEE Workshop On Statistical Signal Processing (2005)Google Scholar
  33. 33.
    Rice, S.V.: Measuring the accuracy of page-reading systems. Ph.D. dissertation, University of Nevada (1996)Google Scholar
  34. 34.
    Serra J.: Image Analysis and Mathematical Morphology, vol. 1. Academic Press, New York (1982)Google Scholar
  35. 35.
    Taylor M.J., Dance C.R.: Enhancement of document images from cameras. Proc. SPIE Document Recognit. 3305, 230–241 (1998)CrossRefGoogle Scholar
  36. 36.
    Thouin P., Chang C.: A method for restoration of low-resolution document images. Int. J. Document Anal. Recognit. 2, 200–210 (2000)CrossRefGoogle Scholar
  37. 37.
    Tonazzini A., Vezzosi S., Bedini L.: Analysis and recognition of highly degraded printed characters. Int. J. Document Anal. Recognit. 6, 236–247 (2004)CrossRefGoogle Scholar
  38. 38.
    Ukkonen E.: On-Line construction of suffix trees. Algorithmica 14(3), 249–260 (1995)zbMATHCrossRefMathSciNetGoogle Scholar
  39. 39.
    Yang Y., Yan H.: An adaptive logical method for binarization of degraded document images. Pattern Recognit. 33, 787–807 (2000)CrossRefGoogle Scholar
  40. 40.
    Yang Y., Yan H., Yu D.: Content-lossless document image compression. Based Struct. Anal. Pattern Matching Pattern Recognit. 33, 1277–1293 (2000)Google Scholar
  41. 41.
    Zheng Q., Kanungo T.: Morphological degradation models and their use in document image restoration. Proc. IEEE Int. Conf. Image Process. 1, 193–196 (2001)Google Scholar

Copyright information

© Springer-Verlag 2008

Authors and Affiliations

  1. 1.Department of Telecommunications and Information Processing, IPI, IBBTGhent UniversityGhentBelgium

Personalised recommendations