Abstract

Estimating geometric parameters can play an important role in different applications of pattern recognition algorithms. The purpose of this tutorial is to present new efficient and easy to reproduce algorithms dedicated to the robust extraction of geometric features on digital objects. The tutorial will consist of a rapid overview of the theoretical description of recent estimators (like tangent, curvature or noise estimators) followed by the implementation details given through the DGtal library. To introduce this library, a quick look of the main features will be presented with preliminary exercises available online before the tutorial.

To simplify interaction and demonstration like in teaching activities, the use of the {\dgtal} library will be embedded in a \textit{Jupyter} notebook allowing online demonstration from a single web browser. In the continuity and complement of this online notebook, we will propose to the audience to construct its own online demonstration by using the new automatic demonstration kernel recently proposed in the Image Processing On Line journal.

Time and location

26th November at Hunua Room 1 14:00pm-17:00pm

Lecturers

Jacques-Olivier Lachaud

PhD thesis in Computer Science, HDR, Professor

LAMA, University of Savoie Mont Blanc

email: jacques-olivier(.dot.)lachaud(.@at.)univ-smb.fr

Jacques-Olivier Lachaud is a professor in Computer Science at Université Savoie Mont Blanc and a member of LAMA (LAboratoire de MAthématiques (UMR 5127, CNRS)) since 2007. His research interests include digital and computational geometry, digital topology, and variational approaches for image analysis. In 2003, he co-organized the international conference DGCI in Bordeaux. He is a member of the Steering Committee of this conference since 2016. From 2010 to 2016, he was the leader of the workgroup Géométrie Discrète (digital geometry), which is part of the GDR-IM and IGRV. From 2012 to 2014, he was a member of the jury for the Gilles Kahn Prize (SIF, Académie des Sciences). Since 2017, he is member of the IGRV PhD prize. He has written 27 articles in the main international journals of the field (PAMI, CVIU, PR, JMIV, MedIA, DAM, CGTA, SIIMS, C&G, CGf, IVC), and more than 55 papers in peer-reviewed international conferences (DGCI, ECCV, ICPR, IWCIA). He has supervised or co-supervised 8 PhD theses, and he is currently supervising two PhD students. In 2010, he co-created DGtal and he is now one of the main editors of the library.

Bertrand Kerautret

PhD thesis in Computer Science, HDR, Professor

LIRIS, University of Lyon 2

email: bertrand(.dot.)kerautret(.@at.)univ-lyon2.fr

Bertrand Kerautret is currently Professor in Computer Science at Lyon 2 University (ICOM department, France) and works in the LIRIS laboratory (Laboratoire d'InfoRmatique en Image et Systèmes d'information,(UMR 5205, CNRS)). He was previously assistant professor at the LORIA (Nancy). He received a PhD degree in Computer Science from Universit\'e Bordeaux in 2004. His research deals with digital geometry, image processing and its applications. In 2011, he co-organized the international conference DGCI in Nancy. He is also interested in reproducible research -- he is an active member of the IPOL Editorial Board and was at the initiative of the first workshop on Reproducible Research in Pattern Recognition in 2016. Since 2017, he chairs the Technical Committee TC 18 "Discrete Geometry and Mathematical Morphology" of IAPR. He has written about 40 papers in international journals or conferences on these topics. He actively contributes to DGtal library and he is the manager of the DGtalTools project. In december 2017, he defended his habilitation thesis to supervise research.

The program schedule

First Part 14h45 - 16:15

Cofee Break (16h15 - 16h30)

Second Part 16h30 - 18:00