Blotch Detection for Film Restoration

  • Alvaro Pardo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7042)

Abstract

Blotches are one of the most common film degradations that must be detected and corrected in the process of film restoration. In this work we will address the problem of blotch detection in the context of digital film restoration. Although there are several methods for blotch detection, in the literature their evaluation is usually subjective. In this work we propose a new method for blotch detection and an objective methodology to evaluate its performance. We show that the proposed method outperforms other existing methods while using this objective metric.

Keywords

Motion Estimation Current Frame Motion Compensation Search Window Pixel Level 
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.
    Bouguet: Pyramidal implementation of the lucas kanade feature tracker description of the algorithm. Technical report, Intel Corporation (2002)Google Scholar
  2. 2.
    Buades, A., Delon, J., Gousseau, Y., Masnou, S.: Adaptive blotches detection for film restoraion. In: ICIP 2010, pp. 3317–3320 (2010)Google Scholar
  3. 3.
    Desolneux, A., Moisan, L., Morel, J.M.: Gestalt Theory and Image Analysis. Springer, Heidelberg (2007)MATHGoogle Scholar
  4. 4.
    Kokaram, A.: Motion Picture Restoration: Digital Algorithms for Artefact Suppression in Degraded Motion Picture Film and Video. Springer, Heidelberg (2001)Google Scholar
  5. 5.
    Lucas, B., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Image Understanding Workshop, pp. 674–679 (1981)Google Scholar
  6. 6.
    Pinz, A., Schallauer, P., Haas, W.: Automatic restoration algorithms for 35mm film. J. Computer Vision Research 1(3), 59–85 (1999)Google Scholar
  7. 7.
    Van Roosmalen, P.M.B.: Restoration of Archvied Film and Video. PhD thesis, Delft University (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Alvaro Pardo
    • 1
  1. 1.School of Engineering and TechnologiesUniversidad Catolica del UruguayUruguay

Personalised recommendations