Difference between revisions of "Publications/huynh.17.ismm"

From LRDE

 
Line 17: Line 17:
 
| type = inproceedings
 
| type = inproceedings
 
| id = huynh.17.ismm
 
| id = huynh.17.ismm
  +
| identifier = doi:10.1007/978-3-319-57240-6_13
 
| bibtex =
 
| bibtex =
 
@InProceedings<nowiki>{</nowiki> huynh.17.ismm,
 
@InProceedings<nowiki>{</nowiki> huynh.17.ismm,
Line 33: Line 34:
 
address = <nowiki>{</nowiki>Fontainebleau, France<nowiki>}</nowiki>,
 
address = <nowiki>{</nowiki>Fontainebleau, France<nowiki>}</nowiki>,
 
publisher = <nowiki>{</nowiki>Springer<nowiki>}</nowiki>,
 
publisher = <nowiki>{</nowiki>Springer<nowiki>}</nowiki>,
  +
doi = <nowiki>{</nowiki>10.1007/978-3-319-57240-6_13<nowiki>}</nowiki>,
 
abstract = <nowiki>{</nowiki>A method of text detection in natural images, to be turn
 
abstract = <nowiki>{</nowiki>A method of text detection in natural images, to be turn
 
into an effective embedded software on a mobile device,
 
into an effective embedded software on a mobile device,

Latest revision as of 12:42, 24 November 2020

Abstract

A method of text detection in natural images, to be turn into an effective embedded software on a mobile deviceshall be both efficient and lightweight. We observed that a simple method based on the morphological Laplace operator can do the trick: we can construct in quasi-linear time a hierarchical image decomposition / simplification based on its 0-crossings, and search for some text in the resulting tree. Yet, for this decomposition to be sound, we need “0-crossings” to be Jordan curves, and to that aim, we rely on some discrete topology tools. Eventually, the hierarchical representation is the morphological tree of shapes of the Laplacian sign. Moreover, we provide an algorithm with linear time complexity to compute this representation. We expect that the proposed hierarchical representation can be useful in some applications other than text detection.

Documents

Bibtex (lrde.bib)

@InProceedings{	  huynh.17.ismm,
  author	= {L\^e Duy {Hu\`ynh} and Yongchao Xu and Thierry G\'eraud},
  title		= {Morphological Hierarchical Image Decomposition Based on
		  {L}aplacian 0-Crossings},
  booktitle	= {Mathematical Morphology and Its Application to Signal and
		  Image Processing -- Proceedings of the 13th International
		  Symposium on Mathematical Morphology (ISMM)},
  year		= {2017},
  editor	= {J. Angulo and S. Velasco-Forero and F. Meyer},
  volume	= {10225},
  series	= {Lecture Notes in Computer Science},
  month		= may,
  pages		= {159--171},
  address	= {Fontainebleau, France},
  publisher	= {Springer},
  doi		= {10.1007/978-3-319-57240-6_13},
  abstract	= {A method of text detection in natural images, to be turn
		  into an effective embedded software on a mobile device,
		  shall be both efficient and lightweight. We observed that a
		  simple method based on the morphological Laplace operator
		  can do the trick: we can construct in quasi-linear time a
		  hierarchical image decomposition / simplification based on
		  its 0-crossings, and search for some text in the resulting
		  tree. Yet, for this decomposition to be sound, we need
		  ``0-crossings'' to be Jordan curves, and to that aim, we
		  rely on some discrete topology tools. Eventually, the
		  hierarchical representation is the morphological tree of
		  shapes of the Laplacian sign. Moreover, we provide an
		  algorithm with linear time complexity to compute this
		  representation. We expect that the proposed hierarchical
		  representation can be useful in some applications other
		  than text detection.}
}