Resolution Independent Skew and Orientation Detection for Document Images

Joost van Beusekom, Faisal Shafait, Thomas Breuel
In: Kathrin Berkner, Lawrence Likforman-Sulem (eds.) Document Recognition and Retrieval XVI. Proceedings of SPIE volume 7247, San Jose, CA, USA, SPIE Electronic Imaging, 1/2009
(C) SOCIETY OF PHOTO-OPTICAL INSTRUMENTATION ENGINEERS (SPIE)


Abstract:

In large scale scanning applications, orientation detection of the digitized page is necessary for the following procedures to work correctly. Several existing methods for orientation detection use the fact that in Roman script text, ascenders are more likely to occur than descenders. In this paper, we propose a different approach for page orientation detection that uses this information. The main advantage of our method is that it is more accurate than compared widely used methods, while being scan resolution independent. Another interesting aspect of our method is that it can be combined with our previously published method for skew detection to have a single-step skew and orientation estimate of the page image. We demonstrate the effectiveness of our approach on the UW-I dataset and show that our method achieves an accuracy of above 99% on this dataset. We also show that our method is robust to different scanning resolutions and can reliably detect page orientations for documents rendered at 150, 200, 300, and 400 dpi.

Files:

  x648.html
  beusekom--resolution-independent-skew-and-orientation-detection-for-document-images--SPIE--2009.pdf

BibTex:

@inproceedings{ BEUS2009,
	Title = {Resolution Independent Skew and Orientation Detection for Document Images},
	Author = {Joost van Beusekom and Faisal Shafait and Thomas Breuel},
	Editor = {Kathrin Berkner, Lawrence Likforman-Sulem},
	BookTitle = {Document Recognition and Retrieval XVI. Proceedings of SPIE},
	Note = {(C) SOCIETY OF PHOTO-OPTICAL INSTRUMENTATION ENGINEERS (SPIE)},
	Month = {1},
	Year = {2009},
	Publisher = {SPIE Electronic Imaging},
	Publisher = {7247}
}

     
Last modified:: 30.08.2016