<?xml version="1.0" encoding="ISO-8859-1" ?>
<feed xmlns="http://www.w3.org/2005/Atom">

	<title>RECITE - REConnaissance de texte InTeractive et Embarquee/Interactive text recognition</title>
	<id>http://tcts.fpms.ac.be/~recite/</id>
	<description>REConnaissance de texte InTeractive et Embarquee/Interactive text recognition</description>
	<updated></updated>



  <entry>
	<title>Partners/Contacts</title> 
	<link href="http://tcts.fpms.ac.be/~recite/?5-partners-contacts" /> 
	<update>2007-06-27T17:32:09+00:00</update>
	<summary><![CDATA[
		


Dr
C&eacute;line Mancas-Thillou, senior researcher
Prof. Bernard Gosselin

Scientific
collaborators and industrial partners:

  MUWAC
  FN Herstal







	]]></summary> 
  </entry>
  <entry>
	<title>Funds</title> 
	<link href="http://tcts.fpms.ac.be/~recite/?4-funds" /> 
	<update>2007-06-27T17:30:17+00:00</update>
	<summary><![CDATA[
		
This
project (2007-2008) is a post-doctoral contract funded by 
R&eacute;gion Wallonne 
in the framework of FIRST Post-doc Contract.







	]]></summary> 
  </entry>
  <entry>
	<title>Related Publications</title> 
	<link href="http://tcts.fpms.ac.be/~recite/?3-related-publications" /> 
	<update>2007-06-27T17:26:39+00:00</update>
	<summary><![CDATA[
		

C. MANCAS-THILLOU, M. MANCAS, 2007, "Comparison between Pen-scanner and Digital Camera Acquisition for Engraved Character Recognition", 
    Proc. of Camera-based Document Analysis and Recognition (CBDAR 2007), Curitiba (Brasil), pp 889-893.,
Louvain.  
C. MANCAS-THILLOU, 2006, "Natural
Text Scene Understanding",
    ISBN: 978-2-8746-3059-4,
Louvain. 







	]]></summary> 
  </entry>
  <entry>
	<title>Different steps for RECITE</title> 
	<link href="http://tcts.fpms.ac.be/~recite/?2-different-steps-for-recite" /> 
	<update>2007-06-27T17:00:26+00:00</update>
	<summary><![CDATA[
		
Different steps of RECITE are:


  Data acquisition especially for engraved characters
  Listing of independent degradations and classification for
human-machine dialogue
  Design of a robust recognizer, taking into account possible
errors during man-machine communication (wrong description of a
degradation)
  Automatic (or partially automatic) of a training database
with the user and image analogies methods
  Addition of a priori information and modelization
  Test and Validation





	]]></summary> 
  </entry>
  <entry>
	<title>RECITE, what is it?</title> 
	<link href="http://tcts.fpms.ac.be/~recite/?1-" /> 
	<update>2007-06-27T16:36:11+00:00</update>
	<summary><![CDATA[
		
OCR tools, extensively used for
administrative purposes for adress, forms, checks reading,
&nbsp;properly works with rather clean, flat and paper documents.
RECITE aims at extending OCR application fors machine vision for
objects &nbsp;with different surfaces (metal and so on) and with
very various characters. Close to natural scene text understanding,
this project focuses on interactively configurable recognition software
in order to give access to non-experts people (in SMEs for instance).
Hence, the main goal is to enable the creation of dedicated recognizers
for particular applications. Very general OCR may be applied but we are
convinced that performance will be lower. &nbsp;
Based on smart dialogues
between the computer and the end-user, particularities of &nbsp;the
application, degradations embedded into images will be
semi-automatically defined in order to build an efficient recognizer.
Additionally, some challenges
are met such as extraction and recognition of engraved/embossed
characters, which are limitations of systems dealing with natural scene
text. In that context, one example is first taken in order to make
further the model more versatile: the recognition of engraved
characters into metallic and reflective surfaces in uncontrolled
environment.&nbsp;&nbsp;
Keywords:
Text recognition, Natural Scene, Auto-configurable Systems


&nbsp; &nbsp; &nbsp; 
	]]></summary> 
  </entry>
</feed>

