A Spatiotemporal Algorithm for Detection and Restoration of Defects in Old Color Films

  • Bekir Dizdaroglu
  • Ali Gangal
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4678)


A spatiotemporal method is presented for detection and concealment of local defects such as blotches in old color films. Initially, non-local means (NL-means) method which does not require motion estimation is used for noise removal in image sequences. Later, the motion vectors that are incorrectly estimated within defect regions are repaired by taking account of the temporal continuity of motion trajectory. The defects in films are detected by spike detection index (SDI) method, which are easily adapted to color image sequences. Finally, the proposed inpainting algorithm fills in detected defect regions, which is not required to estimate true motion like other approaches. The method is presented on synthetic and real image sequences, and efficient concealment results are obtained.


Motion Vector Motion Estimation Normalize Mean Square Error Color Film Inpainting Method 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kokaram, A.C., Morris, R.D., Fitzgerald, W.J., Rayner, P.J.W.: Detection of Missing Data in Image Sequences. IEEE Transactions on Image Processing 4(11), 1496–1508 (1995)CrossRefGoogle Scholar
  2. 2.
    Bornand, R., Lecan, E., Laborelli, L., Chenot, J.: Missing Data Correction in Still Images and Image Sequences. In: Proceedings of ACM Multimedia, ACM, New York (2002)Google Scholar
  3. 3.
    Efros, A., Freeman, W.: Image Quilting for Texture Synthesis and Transfer. In: Proceedinds of ACM Conference on Computer Graphics, Eugene Fiume, pp. 341–346. ACM, New York (2001)Google Scholar
  4. 4.
    Criminisi, A., Perez, P., Toyama, K.: Region Filling and Object Removal by Exampler-Based Inpainting. IEEE Trans. Image Proc. 13(9), 1200–1212 (2004)CrossRefGoogle Scholar
  5. 5.
    Gangal, A., Kayikcioglu, T., Dizdaroglu, B.: An improved motion-compensated restoration method for damaged color motion picture films. Signal Proc. Image Comm. 19, 353–368 (2004)CrossRefGoogle Scholar
  6. 6.
    Gangal, A., Dizdaroglu, B.: Automatic Restoration of Old Motion Picture Films Using Spatio-Temporal Exemplar-Based Inpainting. In: Blanc-Talon, J., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2006. LNCS, vol. 4179, pp. 55–66. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  7. 7.
    Buades, A., Coll, B., Morel, J.M.: Denoising Image Sequences Does not Require Motion Estimation. In: CMLA 2005-18 (2005)Google Scholar
  8. 8.
    Tourapis, A.M., Shen, G., Liou, M.L., Au, O.C., Ahmad, I.: A New Predictive Diamond Search Algorithm for Block Based Motion Estimation. In: Proc. of Visual Comm. and Image Proc. (2000)Google Scholar
  9. 9.
    Boyce, J.: Noise Reduction of Image Sequences Using Adaptive Motion Compensated Frame Averaging. Proceedings of the IEEE ICASSP 3, 461–464 (1992)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Bekir Dizdaroglu
    • 1
  • Ali Gangal
    • 1
  1. 1.Department of Electrical and Electronics Engineering, Karadeniz Technical University, 61080, TrabzonTurkey

Personalised recommendations