Application of Wavelet Decomposition to Document Line Segmentation

Laskov, Lasko. "Application of Wavelet Decomposition to Document Line Segmentation." Serdica Journal of Computing 6.2 (2012): 149-162. <http://eudml.org/doc/219585>.

@article{Laskov2012,
abstract = {ACM Computing Classification System (1998): I.7, I.7.5.In this paper an approach to document line segmentation is presented. The algorithm is based on a wavelet transform of the horizontal projective profile of the document image. The projective profile is examined as a one-dimensional discrete signal which is decomposed using the pyramidal wavelet algorithm up to a precise scale, where local minima and maxima are discovered. These local extrema, projected into the input signal, correspond to the spacing between document lines and to the pivots of the lines. The method has been tested on a broad set of printed and handwritten documents and proven to be stable and efficient.},
author = {Laskov, Lasko},
journal = {Serdica Journal of Computing},
keywords = {Document Image Processing; Document Segmentation; Wavelets},
language = {eng},
number = {2},
pages = {149-162},
publisher = {Institute of Mathematics and Informatics Bulgarian Academy of Sciences},
title = {Application of Wavelet Decomposition to Document Line Segmentation},
url = {http://eudml.org/doc/219585},
volume = {6},
year = {2012},
}

TY - JOUR
AU - Laskov, Lasko
TI - Application of Wavelet Decomposition to Document Line Segmentation
JO - Serdica Journal of Computing
PY - 2012
PB - Institute of Mathematics and Informatics Bulgarian Academy of Sciences
VL - 6
IS - 2
SP - 149
EP - 162
AB - ACM Computing Classification System (1998): I.7, I.7.5.In this paper an approach to document line segmentation is presented. The algorithm is based on a wavelet transform of the horizontal projective profile of the document image. The projective profile is examined as a one-dimensional discrete signal which is decomposed using the pyramidal wavelet algorithm up to a precise scale, where local minima and maxima are discovered. These local extrema, projected into the input signal, correspond to the spacing between document lines and to the pivots of the lines. The method has been tested on a broad set of printed and handwritten documents and proven to be stable and efficient.
LA - eng
KW - Document Image Processing; Document Segmentation; Wavelets
UR - http://eudml.org/doc/219585
ER -