CFP last date
20 January 2025
Reseach Article

Crack Detection and Restoration in Digitized Paintings by using Top Hat Transform Method and Median Filter

Published on November 2011 by Prateeksha Chouksey, Pratik Chouksey, Pranali Dandekar
2nd National Conference on Information and Communication Technology
Foundation of Computer Science USA
NCICT - Number 4
November 2011
Authors: Prateeksha Chouksey, Pratik Chouksey, Pranali Dandekar
89f92b67-a12c-4f64-bc57-35528a7e2c1c

Prateeksha Chouksey, Pratik Chouksey, Pranali Dandekar . Crack Detection and Restoration in Digitized Paintings by using Top Hat Transform Method and Median Filter. 2nd National Conference on Information and Communication Technology. NCICT, 4 (November 2011), 19-21.

@article{
author = { Prateeksha Chouksey, Pratik Chouksey, Pranali Dandekar },
title = { Crack Detection and Restoration in Digitized Paintings by using Top Hat Transform Method and Median Filter },
journal = { 2nd National Conference on Information and Communication Technology },
issue_date = { November 2011 },
volume = { NCICT },
number = { 4 },
month = { November },
year = { 2011 },
issn = 0975-8887,
pages = { 19-21 },
numpages = 3,
url = { /proceedings/ncict/number4/4299-ncict029/ },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Proceeding Article
%1 2nd National Conference on Information and Communication Technology
%A Prateeksha Chouksey
%A Pratik Chouksey
%A Pranali Dandekar
%T Crack Detection and Restoration in Digitized Paintings by using Top Hat Transform Method and Median Filter
%J 2nd National Conference on Information and Communication Technology
%@ 0975-8887
%V NCICT
%N 4
%P 19-21
%D 2011
%I International Journal of Computer Applications
Abstract

Digital Restoration is an integrated methodology for the detection and removal of cracks from digitized paintings. The older paintings suffer from breaks in the substrate, the paint, or the varnish. When we digitized these paintings, they can be modified using mathematical algorithms and cracks are eliminated soas to maintain the quality. The cracks are detected by thresholding the output of the morphological top hat transform. Cracks usually have low luminance and, thus, can be considered as local intensity minima with rather elongated structural characteristics. A crack detector can be applied on the luminance component of an image to identify such minima. Afterwards, the thin dark brush strokes which have been misidentified as cracks are removed using either a median radial basis function neural network on hue and saturation data or a semi-automatic procedure based on region growing. Finally, crack filling using order statistics filters such as median filter is performed. The methodology has been shown to perform very well on digitized paintings suffering from cracks, thereby ensuring its originality.

References
  1. M. Barni, F. Bartolini, and V. Cappellini, “Image processing for virtual restoration of artworks,”IEEE Multim dia, vol. 7,no. 2,pp. 34–37,Jun. 2000.
  2. F. Abas and K. Martinez, “Craquelure analysis for content - based retrieval,” in Proc. 14th Int. Conf. Digital Signal Processing, vol. 1, 2002, pp. 111–114.
  3. L. Joyeux, O. Buisson, B. Besserer, and S. Boukir, “Detection and removal of line scratches in motion picture films,” in Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, 1999, pp. 548–553.
  4. A. Kokaram, R. Morris, W. Fitzgerald, and P. Rayner, “Detection of missing data in image sequences,” IEEE Trans. Image Process., vol. 4, no. 11, pp. 1496–1508, Nov. 1995.
  5. “Interpolation of missing data in image sequences,” IEEE Trans. Image Process., vol. 4, no. 11, pp. 1509–1519, Nov.1995.
  6. M. Bertalmio, G. Sapiro, V. Caselles, and C. Ballester, “Image in painting,” in Proc. SIGGRAPH, 2000, pp. 417–424.
  7. C. Ballester, M. Bertalmio, V. Caselles, G. Sapiro, and J. Verdera.
Index Terms

Computer Science
Information Sciences

Keywords

Top Hat Transform Method Median Filter