Improved document image segmentation algorithm using multiresolution morphology

Syed Saqib Bukhari, Faisal Shafait, Thomas Breuel
SPIE Document Recognition and Retrieval XVIII, San Francisco, CA, USA, SPIE, 1/2011

Abstract:

Page segmentation into text and non-text components is an essential preprocessing step before OCR operation. If this is not done properly, an OCR classification engine produces garbage text due to the presence of non-text components. This paper describes improvements to the text/image segmentation algorithm described by Bloomberg,1 which is also available in his open-source Leptonica library.2 The modifications result in significant improvements over Bloomberg's algorithm on UW-III, UNLV, ICDAR 2009 page segmentation competition test images and circuit diagram datasets.

Files:

  Bukhari-text-image-segmentation-DRR11.pdf

BibTex:

@inproceedings{ BUKH2011,
	Title = {Improved document image segmentation algorithm using multiresolution morphology},
	Author = {Syed Saqib Bukhari and Faisal Shafait and Thomas Breuel},
	BookTitle = {SPIE Document Recognition and Retrieval XVIII},
	Month = {1},
	Year = {2011},
	Publisher = {SPIE}
}

     
Last modified:: 30.08.2016