Difference between revisions of "Affiche-these-MOVN"

From LRDE

(Created page with "{{DISPLAYTITLE:PhD Defense Minh Ôn Vũ Ngọc}} <div class="center" style="width: auto; margin-left: auto; margin-right: auto;"> File:Logo of Sorbonne University.png|250px...")
 
 
(4 intermediate revisions by one other user not shown)
Line 12: Line 12:
 
</div>
 
</div>
   
<div class="center" style="width: auto; margin-left: auto; margin-right: auto;"><big>'''Mardi 17 Décembre 2019 '''</big>
+
<div class="center" style="width: auto; margin-left: auto; margin-right: auto;"><big>'''Mardi 18 Février 2020 '''</big>
 
</div>
 
</div>
   
Line 20: Line 20:
 
<div class="center" style="width: auto; margin-left: auto; margin-right: auto;"><big>'''EPITA, 14-16 Rue Voltaire, 94270 Le Kremlin-Bicêtre'''</big>
 
<div class="center" style="width: auto; margin-left: auto; margin-right: auto;"><big>'''EPITA, 14-16 Rue Voltaire, 94270 Le Kremlin-Bicêtre'''</big>
 
</div>
 
</div>
<div class="center" style="width: auto; margin-left: auto; margin-right: auto;"><big>''' salle KB604 '''</big>
+
<div class="center" style="width: auto; margin-left: auto; margin-right: auto;"><big>''' Amphi Master '''</big>
 
</div>
 
</div>
   
Line 34: Line 34:
   
   
<div class="center" style="width: auto; margin-left: auto; margin-right: auto;"><big>'''A new minimum barrier distance for�multivariate images with applications to�salient object detection, shortest path�finding, and segmentation.'''</big>
+
<div class="center" style="width: auto; margin-left: auto; margin-right: auto;"><big>'''A new minimum barrier distance for multivariate images with applications to salient object detection, shortest path finding, and segmentation.'''</big>
 
</div>
 
</div>
   
Line 70: Line 70:
   
   
'''Keywords: Tree of shapes, mathematical morphology, hierarchical representation, multivariate images, Dahu pseudo-distance, minimum barrier distance,visual
+
'''Keywords: Tree of shapes, mathematical morphology, Dahu pseudo-distance, minimum barrier distance, visual saliency, Document detection. '''
saliency, Document detection, image segmentation. '''
 
   
   
Line 85: Line 84:
 
* Béatriz MARCOTEGUI, Pr., Mines ParisTech, CMM
 
* Béatriz MARCOTEGUI, Pr., Mines ParisTech, CMM
   
  +
Encadrants :
Directeurs de thèse :
 
 
* Thierry GÉRAUD, Pr., EPITA, LRDE
 
* Thierry GÉRAUD, Pr., EPITA, LRDE
 
* Jonathan FABRIZIO, MdC, EPITA, LRDE
 
* Jonathan FABRIZIO, MdC, EPITA, LRDE

Latest revision as of 16:19, 13 February 2020


Logo of Sorbonne University.png EDITE Logo.png Epita-logo-2.png Lrde.png


SOUTENANCE de THÈSE
Minh ON VU NGOC
Mardi 18 Février 2020
à 14h
EPITA, 14-16 Rue Voltaire, 94270 Le Kremlin-Bicêtre
Amphi Master
Plan d’accès :


A new minimum barrier distance for multivariate images with applications to salient object detection, shortest path finding, and segmentation.


Abstract:

Hierarchical image representations are widely used in image processing to model the content of an image in the multi-scale structure. A well-known hierarchical representation is the tree of shapes (ToS) which encodes the inclusion relationship between connected components from different thresholded levels. This kind of tree is self-dual, contrast-change invariant and popular in computer vision community. Typically, in our work, we use this representation to compute the new distance which belongs to the mathematical morphology domain.

Distance transforms and the saliency maps they induce are generally used in image processing, computer vision, and pattern recognition. One of the most commonly used distance transforms is the geodesic one. Unfortunately, this distance does not always achieve satisfying results on noisy or blurred images. Recently, a new pseudo-distance, called the minimum barrier distance (MBD), more robust to pixel fluctuation, has been introduced. Some years after, Géraud et al. have proposed a good and fast-to-compute approximation of this distance: the Dahu pseudodistance. Since this distance was initially developed for grayscale images, we propose here an extension of this transform to multivariate images; we call it vectorial Dahu pseudo-distance. This new distance is easily and efficiently computed thanks to the multivariate tree of shapes (MToS). We propose an efficient way to compute this distance and its deduced saliency map in this thesis. We also investigate the properties of this distance in dealing with noise and blur in the image. This distance has been proved to be robust for pixel invariant.

To validate this new distance, we provide benchmarks demonstrating how the vectorial Dahu pseudo-distance is more robust and competitive compared to other MB-based distances. This distance is promising for salient object detection, shortest path finding, and object segmentation. Moreover, we apply this distance to detect the document in videos. Our method is a region-based approach which relies on visual saliency deduced from the Dahu pseudo-distance. We show that the performance of our method is competitive with state-of-the-art methods on the ICDAR Smartdoc 2015 Competition dataset.


Keywords: Tree of shapes, mathematical morphology, Dahu pseudo-distance, minimum barrier distance, visual saliency, Document detection.


Composition du Jury :

Rapporteurs :

  • Nicole VINCENT, Pr., Université Paris Descartes, LIPADE
  • Jean-Christophe BURIE, Pr., Université La Rochelle, L3I

Examinateurs :

  • Benoît NAEGEL, MdC, Université de Strasbourg, ICube
  • Béatriz MARCOTEGUI, Pr., Mines ParisTech, CMM

Encadrants :

  • Thierry GÉRAUD, Pr., EPITA, LRDE
  • Jonathan FABRIZIO, MdC, EPITA, LRDE