Machine Vision and Applications

, Volume 21, Issue 5, pp 767–777 | Cite as

Trainable blotch detection on high resolution archive films minimizing the human interaction

  • Attila LicsárEmail author
  • Tamás Szirányi
  • László Czúni
Original Paper


Film archives are continuously in need of automatic restoration tools to accelerate the correction of film artifacts and to decrease the costs. Blotches are a common type of film degradation and their correction needs a lot of manual interaction in traditional systems due to high false detection rates and the huge amount of data of high resolution images. Blotch detectors need reliable motion estimation to avoid the false detection of uncorrupted regions. In case of erroneous detection, usually an operator has to remove the false alarms manually, which significantly decreases the efficiency of the restoration process. To reduce manual intervention, we developed a two-step false alarm reduction technique including pixel- and object-based methods as post-processing. The proposed pixel-based algorithm compensates motion, decreasing false alarms at low computational cost, while the following object based method further reduces the residual false alarms by machine learning techniques. We introduced a new quality metric for detection methods by measuring the required amount of manual work after the automatic detection. In our novel evaluation technique, the ground truth is collected from digitized archive sequences where defective pixel positions are detected in an interactive process.


Digital film restoration Blotch detection Object classification Motion estimation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Delaney, B., Hoomans, B.: Prestospace user requirements feedback meeting in London. In: An Integrated Solution for Audio-Visual Preservation and Access (2004)Google Scholar
  2. 2.
    Czúni L., Hanis A., Kovács L., Kránicz B., Licsár A., Szirányi T., Kas I., Kovács Gy. and Manno S. (2004). Digital motion picture restoration system for film archives (DIMORF). SMPTE Motion Imaging J. 113: 170–176 Google Scholar
  3. 3.
    Kokaram A.C. (2004). On missing data treatment for degraded video and film archives: a survey and a new Bayesian approach. IEEE Trans. Image Process. 13(3): 397–415 CrossRefGoogle Scholar
  4. 4.
    Ghaderi, M., Kasaei, S.: Novel post-processing methods used in detection of blotches in image sequences. AEÜ Int. J. Electron. Commun. (58), 58–64 (2004)Google Scholar
  5. 5.
    Kokaram A.C., Morris R., Fitzgerald W. and Rayner P. (1995). Detection of missing data in image sequences. IEEE Trans. Image Process. 4(11): 1496–1508 CrossRefGoogle Scholar
  6. 6.
    Gangal, A., Kayikçioglu, T., Dizdaroglu, B.: An improved motion-compensated restoration method for damage color motion picture film. Signal Proc. Image Commun. (19), 353–368 (2004)Google Scholar
  7. 7.
    Nadenau, M.J., Mitra, S.K.: Blotch and scratch detection in image sequences based on rank ordered differences. In: Time-Varying Image Processing and Moving Object Recognition, pp. 27–35. Elsevier, Amsterdam (1997)Google Scholar
  8. 8.
    Tilie, S., Laborelli, L.: Blotch detection for digital archives restoration based on the fusion of spatial and temporal detectors. In: The 9th International Conference on Information Fusion, Florence, Italy, pp. 1–8 (2006)Google Scholar
  9. 9.
    Ren, J., Vlachos, T.: Segmentation-assisted dirt detection for the restoration of archived films. Proceedings of BMVC, vol. 1, Oxford, England, pp. 359–368 (2005)Google Scholar
  10. 10.
    Licsár, A., Czúni, L., Szirányi, T.: Trainable post-processing method to reduce false alarms in the detection of small blotches of archive films. IEEE International Conference on Image Processing (ICIP), Italy, pp. 562–565 (2005)Google Scholar
  11. 11.
    Naranjo, V., Albiol, A., Mossi, J.M., Albiol, A.: Morphological Lambda Reconstruction Applied to Restoration of Blotches in Old Films. Proceedings of the 4th IASTED International Conference on Visualisation, Imaging and Image Processing, Spain (2004)Google Scholar
  12. 12.
    Tenze, L., Ramponi, G., Carrato, S.: Robust detection and correction of blotches in old films using spatio-temporal information. Proceedings of SPIE International Symp. Electronic, San Jose, pp. 348–357 (2002)Google Scholar
  13. 13.
    Joyeux L., Boukir S., Besserer B. and Buisson O. (2001). Reconstruction of degraded image sequences. Application to film restoration. Image and Vision Computing (MAVIS) 19(8): 503–516 Google Scholar
  14. 14.
    Tenze, L., Ramponi, G., Carrato, S.: Blotches Correction and Contrast Enhancement for Old Film Pictures. Proceedings of the International Conference on Image Processing, ICIP, Canada, pp. 660–663 (2000)Google Scholar
  15. 15.
    Kokaram A.C. (1998). Motion Picture Restoration: Digital Algorithms for Artefact Suppression in Degraded Motion Picture Film and Video. Springer, Heidelberg Google Scholar
  16. 16.
    Lagendijk, R.L., van Roosmalen, P.M.B., Biemond, J.: Video enhancement and restoration. Handbook of Image& Video Processing, Academic Press, San Diego, pp. 227–242 (2000)Google Scholar
  17. 17.
    Hamid M.S., Harvey N.R. and Marshall S. (2003). Genetic algorithm optimization of multidimensional grayscale soft morphological filters with applications in film archive restoration. IEEE Trans. Circuits Syst. Video Technol. 13(5): 406–416 CrossRefGoogle Scholar
  18. 18.
    Buisson, O., Boukir, S., Besserer, B.: Motion Compensated Film Restoration. Machine Vision and Applications, Vol 13, Issue 4, pp. 201–212 Springer, Heidelberg (2003)Google Scholar
  19. 19.
    Schallauer P., Pinz A. and Haas W. (1999). Automatic restoration algorithms for 35 mm film. Videre J. Comput. Vis. Res. 1(3): 60–85 Google Scholar
  20. 20.
    Licsár, A., Czúni, L., Szirányi, T.: Adaptive Stabilization of Vibration on Archive Films. Lecture Notes in C.S, LNCS 2756 pp. 230–237. Springer, Heidelberg (2003)Google Scholar
  21. 21.
    Bergen J.R., Burt P.J., Hingorani R. and Peleg S. (1992). A three-frame algorithm for estimating two-component image motion. IEEE Trans. Pattern Anal. Mach. Intell. 14(9): 886–896 CrossRefGoogle Scholar
  22. 22.
    Burt P.J. and Adelson E.H. (1983). The Laplacian pyramid as a compact image code. IEEE Trans. Commun. 31(4): 532–540 CrossRefGoogle Scholar
  23. 23.
    Fukushima K. (1975). Cognitron: a self-organizing multilayered neural network. Biol. Cybern. 20: 121–136 CrossRefGoogle Scholar
  24. 24.
    Cortes C. and Vapnik V. (1995). Support-vector network. Mach. Learn. 20: 273–297 zbMATHGoogle Scholar
  25. 25.
    Rumelhart, D., Hinton, G., Williams, R.: Learning internal representations by error propagation. Parallel Distributed Processing, MIT Press, Cambridge, pp. 318–362 (1986)Google Scholar
  26. 26.
    Czúni, L., Császár, G., Hanis, A., Kovács, L., Licsár, A., Szirányi, T.: Semi automatic digital motion picture restoration system with learning capabilities. In: Learning for Adaptable Visual Systems (LAVS), Cambridge, UK, 2004Google Scholar
  27. 27.
    Cybenko G. (1989). Approximation by Superposition of a Sigmoidal Function. Math. Control Signals Syst. 2: 303–314 zbMATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag 2007

Authors and Affiliations

  • Attila Licsár
    • 1
    Email author
  • Tamás Szirányi
    • 2
  • László Czúni
    • 1
  1. 1.Department of Image Processing and NeurocomputingUniversity of PannoniaVeszprémHungary
  2. 2.Distributed Events Analysis Research Group, Computer and Automation Research InstituteHungarian Academy of SciencesBudapestHungary

Personalised recommendations