Detection and Removal of Scratches in Images

  • S. Bhuvaneswari
  • T. S. Subashini
  • N. Thillaigovindan
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8284)


In this paper a detection/restoration method to detect and remove line scratches in still images, regardless of their orientation, colour, and shape is presented. In this work the two properties of scratches are considered namely: scratches have high contrast compared with its neighbours and they usually occur vertically and it is more than half of the image in length are taken into account. Firstly a simple thresholding technique is applied for detecting the candidate scratch pixels. The pixels detected in the first step are then used as a mask for removing the scratch during the restoration step. The detected scratch is inpainted using our higher order non-adaptive interpolation approach based on a 13x13 neighbourhood. The experimental result shows that the proposed method works well for both simple and complex scratches that are present in uniform or less complex backgrounds. When experimented with complex backgrounds the interpolation artefact namely blurring becomes pronounced. The proposed work can be effectively used to automatically detect and remove the scratch from uniform and less complex static images without user intervention in any stage of the process.


Scratches detection inpainting mask inpainting algorithm image restoration 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Gonzalaz, R.C., Redwoods: Digital Image Processing, 2nd edn. Pearson Education (2002)Google Scholar
  2. 2.
    Criminisi, A., Perez, P., Toyama, K.: Region Filling and objects removal by exemplar based image inpainting. IEEE Transactions on Image Processing 13(9), 1–7 (2004)CrossRefGoogle Scholar
  3. 3.
    Muller, S., Buhler, J., Weitbruch, S., Thebault, C., Doser, I., Neisse, O.: Scratch Detection Supported By Coherency Analysis of motion Vector Fields. In: ICIP, pp. 89–92 (2009)Google Scholar
  4. 4.
    Kim, K.-T., Kim, E.Y.: Film Line scratch Detection using Neural Network and Morphological Filter. In: CIS, pp. 1007–1011 (2008)Google Scholar
  5. 5.
    Malvia, A.: Scratch Detection and Removal in Motion Picture Images. In: IET International Conference on Visual Information Engineering, pp. 99–104 (2006)Google Scholar
  6. 6.
    Bruni, V., Vitulano, D.: A Generalized Model for Scratch Detection. IEEE Transactions on Image Processing 13(1) (2009)Google Scholar
  7. 7.
    Shiliang, N., Hongying, Z., Liping, Z., Yang, F., Brost, V.: Vertical Scratches Detection based on Edge Detection for Old Film. In: IIS, pp. 257–259 (2010)Google Scholar
  8. 8.
    Kim, K.-T., Kim, B., Kim, E.Y.: Automatic restoration of scratch in old archieve. In: IEEE proceedings on the International Conference on Pattern Recognition, pp. 468–471 (2010)Google Scholar
  9. 9.
    Joyeux, L., Boukir, S., Besserer, B.: Film Line Scratch Removal using Kalmar Filtering and Bayesian Restoration. In: IEEE Workshop on the Application of Computer Vision, pp. 1–6 (2000)Google Scholar
  10. 10.
    Isgro, F., Tegolo, D.: Restoration of vertical line scratches with distributed genetic algorithm. In: IEEE Workshop on Computer Architecture for Machine Perception, pp. 249–254 (2005)Google Scholar
  11. 11.
    Kim, N.-D., Udapa, S.: Nonlinear Operators for Edge Detection and Line Scratch Removal. In: IEEE International Conference on Systems, Man and Cybernetics, pp. 4401–4404 (1998)Google Scholar
  12. 12.
    Qingyue, Z., Youdong, D.: Scratch Line Detection and Restoration Based on Canny Operator. In: IEEE Proceedings on the Asia-Pacific Conference on Information Processing, pp. 148–151 (2009)Google Scholar
  13. 13.
    Ardizzone, E., Dindo, H., Mazzola, G.: Multidirectional Scratch Detection and Restoration in Digitized Old Images. Eurasip Journal on Image and Video Processing 2010:680429, 1–11 (2010)CrossRefGoogle Scholar
  14. 14.
    Yadong, W., Zhonglin, K.: An Efficient Scratches Detection and Inpainting Algorithm for Old Film Restoration. In: IEEE Proceedings on International Conference on Information Technology and Computer Science, vol. 1, pp. 75–78 (2009)Google Scholar
  15. 15.
    J., Shen (Jackie), J.: Inpainting and the Fundamental Problem of Image Processing. SIAM News 36(5) (2003)Google Scholar
  16. 16.
    Chhabra, S., Lalit, R., Saxena, S.K.: An analytical Study of Different Image Inpainting Techniques. Indian Journal of Computer Science and Engineering (IJCSE) 3(3), 487–491 (2012)Google Scholar
  17. 17.
    Sagar, G.V.R., Kashif Hussain, S.: An image inpainting Technique based on 8-neighborhood Fast Sweeping Method. International Journal of Computer Science and Technology (IJCST) 2(3), 100–103 (2011)Google Scholar
  18. 18.
    Muthukumar, S., Krishnan, N., Pasupathi, P., Deepa, S.: Analysis of Image Inpainting Techniques with Exemplar, Poisson. Successive Elimination and 8 pixel neighborhood methods 9(11), 15–18 (2010)Google Scholar
  19. 19.
    Bhuvaneswari, S., Subashini, T.S., Soundharya, S., Ramalingam, V.: A novel and fast exemplar based approach for filling portions in an image. In: IEEE Proceedings on the International Conference on Recent Trends in Information Technology (ICRTIT), pp. 91–96 (2012)Google Scholar
  20. 20.
    Hsu, H.-J., Wang, J.-F., Liao, S.-C.: A Hybrid Algorithm With Artifact Detection Mechanism for Region Filling After Object Removal From a Digital Photograph. IEEE Transactions on Image Processing 16(6), 1611–1622 (2007)CrossRefMathSciNetGoogle Scholar
  21. 21.
    Telea, A.: An image Inpainting Technique Based on the Fast Marching Algorithm. Journal of Graphics Tools 9(1), 25–38 (2004)CrossRefGoogle Scholar
  22. 22.
    Thangavel, K., Manavalan, R., Laurence Aroquiaraj, I.: Removal of Speckle Noise from Ultrasound Medical Image based on Special Filters: Comparative Study. ICGST International Journal on Graphics, Vision and Image Processing (GVIP) 9(3), 25–32 (2009)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • S. Bhuvaneswari
  • T. S. Subashini
  • N. Thillaigovindan

There are no affiliations available

Personalised recommendations