Difference between revisions of "Publications/fabrizio.14.icip"

From LRDE
 
(10 intermediate revisions by the same user not shown)
Line 6: Line 6:
 
| booktitle = Proceedings of the 21st International Conference on Image Processing (ICIP)
  
| booktitle = Proceedings of the 21st International Conference on Image Processing (ICIP)
 
| address = Paris, France
  
| address = Paris, France
−
| pages = 1 to 4
 +
| pages = 2585 to 2588
−
| project = Image
 +
| lrdeprojects = Olena
−
| urllrde = 201402-ICIPd
  
 
| abstract = In this article, we propose a simple and precise skew estimation algorithm for binarized document images. The estimation is performed in the frequency domain. To get a precise result, the Fourier transform is not applied to the document itself but the document is preprocessed: all regions of the document are clustered using a KNN and contours of grouped regions are smoothed using the convex hull to form more regular shapes, with better orientation. No assumption has been made concerning the nature or the content of the document. This method has been shown to be very accurate and was ranked first at the DISEC'13 contestduring the ICDAR competitions.
  
| abstract = In this article, we propose a simple and precise skew estimation algorithm for binarized document images. The estimation is performed in the frequency domain. To get a precise result, the Fourier transform is not applied to the document itself but the document is preprocessed: all regions of the document are clustered using a KNN and contours of grouped regions are smoothed using the convex hull to form more regular shapes, with better orientation. No assumption has been made concerning the nature or the content of the document. This method has been shown to be very accurate and was ranked first at the DISEC'13 contestduring the ICDAR competitions.
  +
| lrdepaper = http://www.lrde.epita.fr/dload/papers/fabrizio.14.icip.pdf
  +
| lrdeposter = http://www.lrde.epita.fr/dload/papers/fabrizio.14.icip.poster.pdf
 
| lrdekeywords = Image
  
| lrdekeywords = Image
−
| note = Accepted
  
 
| lrdenewsdate = 2014-05-26
  
| lrdenewsdate = 2014-05-26
 
| type = inproceedings
  
| type = inproceedings
 
| id = fabrizio.14.icip
  
| id = fabrizio.14.icip
  +
| identifier = doi:10.1109/ICIP.2014.7025523
 
| bibtex =
 
| bibtex =
 
@InProceedings<nowiki>{</nowiki> fabrizio.14.icip,
  
@InProceedings<nowiki>{</nowiki> fabrizio.14.icip,
 
author = <nowiki>{</nowiki>Jonathan Fabrizio<nowiki>}</nowiki>,
  
author = <nowiki>{</nowiki>Jonathan Fabrizio<nowiki>}</nowiki>,
 
title = <nowiki>{</nowiki>A precise skew estimation algorithm for document images
  
title = <nowiki>{</nowiki>A precise skew estimation algorithm for document images
−
using KNN clustering and Fourier transform<nowiki>}</nowiki>,
 +
using <nowiki>{</nowiki>KNN<nowiki>}</nowiki> clustering and Fourier transform<nowiki>}</nowiki>,
 
booktitle = <nowiki>{</nowiki>Proceedings of the 21st International Conference on Image
  
booktitle = <nowiki>{</nowiki>Proceedings of the 21st International Conference on Image
 
Processing (ICIP)<nowiki>}</nowiki>,
  
Processing (ICIP)<nowiki>}</nowiki>,
 
year = 2014,
  
year = 2014,
 
address = <nowiki>{</nowiki>Paris, France<nowiki>}</nowiki>,
  
address = <nowiki>{</nowiki>Paris, France<nowiki>}</nowiki>,
−
pages = <nowiki>{</nowiki>1--4<nowiki>}</nowiki>,
 +
pages = <nowiki>{</nowiki>2585--2588<nowiki>}</nowiki>,
−
project = <nowiki>{</nowiki>Image<nowiki>}</nowiki>,
  
 
abstract = <nowiki>{</nowiki>In this article, we propose a simple and precise skew
  
abstract = <nowiki>{</nowiki>In this article, we propose a simple and precise skew
 
estimation algorithm for binarized document images. The
  
estimation algorithm for binarized document images. The
Line 38: Line 38:
 
very accurate and was ranked first at the DISEC'13 contest,
  
very accurate and was ranked first at the DISEC'13 contest,
 
during the ICDAR competitions.<nowiki>}</nowiki>,
  
during the ICDAR competitions.<nowiki>}</nowiki>,
−
note = <nowiki>{</nowiki>Accepted<nowiki>}</nowiki>
 +
doi = <nowiki>{</nowiki>10.1109/ICIP.2014.7025523<nowiki>}</nowiki>
 
<nowiki>}</nowiki>
  
<nowiki>}</nowiki>
   

Latest revision as of 17:00, 27 May 2021

Authors
Jonathan Fabrizio
Where
Proceedings of the 21st International Conference on Image Processing (ICIP)
Place
Paris, France
Type
inproceedings
Projects
Olena
Keywords
Image
Date
2014-05-26

Abstract

In this article, we propose a simple and precise skew estimation algorithm for binarized document images. The estimation is performed in the frequency domain. To get a precise result, the Fourier transform is not applied to the document itself but the document is preprocessed: all regions of the document are clustered using a KNN and contours of grouped regions are smoothed using the convex hull to form more regular shapes, with better orientation. No assumption has been made concerning the nature or the content of the document. This method has been shown to be very accurate and was ranked first at the DISEC'13 contestduring the ICDAR competitions.

Documents


Bibtex (lrde.bib)

@InProceedings{	  fabrizio.14.icip,
  author	= {Jonathan Fabrizio},
  title		= {A precise skew estimation algorithm for document images
		  using {KNN} clustering and Fourier transform},
  booktitle	= {Proceedings of the 21st International Conference on Image
		  Processing (ICIP)},
  year		= 2014,
  address	= {Paris, France},
  pages		= {2585--2588},
  abstract	= {In this article, we propose a simple and precise skew
		  estimation algorithm for binarized document images. The
		  estimation is performed in the frequency domain. To get a
		  precise result, the Fourier transform is not applied to the
		  document itself but the document is preprocessed: all
		  regions of the document are clustered using a KNN and
		  contours of grouped regions are smoothed using the convex
		  hull to form more regular shapes, with better orientation.
		  No assumption has been made concerning the nature or the
		  content of the document. This method has been shown to be
		  very accurate and was ranked first at the DISEC'13 contest,
		  during the ICDAR competitions.},
  doi		= {10.1109/ICIP.2014.7025523}
}





Retrieved from "https://www.lrde.epita.fr/index.php?title=Publications/fabrizio.14.icip&oldid=126434"