Processing poor quality line drawings by local estimation of noise

  • M. E. Dunn
  • S. H. Joseph
Image Segmentation
Part of the Lecture Notes in Computer Science book series (LNCS, volume 301)


The problem of extracting the best data from poor quality line originals at the lowest possible resolution is considered. The form of the grey level histogram from such originals is examined, especially the shape of the peak corresponding to the white background. The viability of deriving a threshold for display from simple measurements of the location and width of this peak is demonstrated. A more accurate method for these measurements is described, and the improvement in thresholding upon its application to originals with variations in background noise level across the image is shown. The accuracy of the methods is quantified.


Grey Level Black Pixel Background Noise Level Noise Standard Deviation Grey Level Histogram 
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.
    T. Pavlidis, Structural pattern recognition, Springer Verlag, 1977.Google Scholar
  2. 2.
    J. S. Weszka and A. Rosenfield, Histogram modification for threshold selection, IEEE Trans. Systems Man Cybernetics, 9, 38–52 (1979).Google Scholar
  3. 3.
    J. Kittler, J. Illingworth and J. Foglein, Threshold selection based on a simple image statistic, Comput. Vision Graphics. Image Process 30, 125–147 (1985).Google Scholar
  4. 4.
    M. R. Bartz, The IBM 1975 Optical Page Reader, Part II: Video thresholding system, IBM J. Res. Develop., 12, 354–363 (1968).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1988

Authors and Affiliations

  • M. E. Dunn
    • 1
  • S. H. Joseph
    • 1
  1. 1.Department of Mechanical EngineeringUniversity of SheffieldSheffield

Personalised recommendations