Shape based filtering

Non-Local Dual Constrained Total Variation Denoising (NL-DCTV)

Saliency maps

Scene parsing with hierarchical convolutional nets

The Polygonal Path Image (PPI)

Welcome to Laurent Najman Web Site

I am professor of Computer Science at Université Gustave Eiffel, Laboratoire Informatique Gaspard-Monge, Equipe A3SI, ESIEE Paris . A short bio is available here. To (surface) mail me, you can write at ESIEE Paris - 2, boulevard Blaise Pascal - Cité DESCARTES - BP 99 - 93162 Noisy le Grand CEDEX - France. My Google Scholar page is here.

 

Family and friends can have access to the private section, if they have a password.


A fun project is the Mathematics Genealogy Project. According to them, some of my ancestors are quite famous. They are, in chronological order, Jean-Pierre Aubin, Jacques-Louis Lions, Laurent Schwartz, Georges Valiron, Emile Borel, Gaston Darboux, Michel Chasles, Simeon Denis Poisson, Joseph Lagrange, Leonhard Euler, Johann Bernouilli, Jacob Bernouilli, Gottfried Leibniz and Erhard Weigel.

ICPR 2016 Tutorial on Graph-Based Morphology

Survey Graph Morpho paperOn the 4th of December 2016, Hugues Talbot and myself gave a tutorial on graph-based morphology at ICPR. This tutorial follows the outline of the PRL survey paper on Graph-Based Morphology. Slides of the talk and videos are available on a dedicated page.

Shape-Based hierarchical segmentation

Shape-Based morphological framework schemeA second PAMI paper on the shape-based morphological filtering framework, has been accepted. This one is dedicated to the hierchical segmentation. Of course, the first PAMI on the topic is still available.

Featured paper: ultrametric watersheds

My pJMIVaper on ultrametric watersheds is amongst the selected  5 top-cited articles from the Journal of Mathematical Imaging and Vision available free until the end of September.

 

More information in the Springer NewsLetter

 

The paper is avalable here. This HAL version will be forever freely available.

Preprint on TV filtering

Our paper on Dual-Constrained Total Variation on Graphs has been accepted to SIAM Journal on Imaging Siences. Preprint is available, as well as source code.

Discrete curvature - November 18-22, 2013.


With Pascal Romon , we are organizing a colloquium on Discrete Curvature. The aim of this meeting is to bring together researchers from diverse backgrounds (including mathematics and computer science) on the common theme of discrete curvature and to make an update on the many achievements of the last decade. We want to promote interaction between various fields, so topics and participants can and should be varied, as long as they fit under the under the main theme. Prestigious speakers are already programmed.

The meeting will take place at the CIRM, in Luminy, near Marseille (France), from November 18th to the 22nd, 2013.

More information: http://laurentnajman.org/curvature/index.php?p=main

Camille Couprie's short movie

The EADS Foundation made a short animated movie to explain Camille Couprie 's prize-winning PhD thesis work. The video can be seen on Youtube

 

 

 

 

 

 

 

 

 

Shape-based Morphology video available

 

 

Camille Couprie: Accessit GIlles Khan Prize


Another prize for Camille Couprie! She has just been awarded an accessit for the prestigious Gilles Khan prize. 

 

Congratulations, Camille!

Camille Couprie EADS PhD Prize


Prix EADS de la meilleure thèse interdisciplinaireCamille COUPRIE pour ses travaux sur l' « Optimisation variationnelle discrète et applications en vision par ordinateur », ED 532 - MSTIC.

2nd place in a MICCAI challenge


The challenge was held on October 1st, 2012 in Nice Sophia Antipolis, Côte d'Azur, France, at the workshop 3D Cardiovascular Imaging: a MICCAI segmentation challenge at the 15th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI),

Special issue on Mathematical Morphology

Our special issue is now available on IEEE Xplore. You can see this at:

Preprint on scene parsing

The preprint of our upcoming IEEE Trans. PAMI on scene labeling is available. We use a multi-scale convolutional network trained in supervised mode on fully-labeled images in which each pixel is labeled by the category of the object it belongs to. A simple superpixel-based post-processing smoothes out the output labels and lines up the segment boundaries with image contours.

Mathematical Morphology

Morphologie mathématique

Systèmes d'exploitation