About me [Since 2013] Assistant Professor of Computer Sciences, IUT - CS department, University Paris Descartes (France) Researcher, LIPADE (EA 2517) - SIP Lab, University Paris Descartes (France) [2012-2013] Post-doctoral fellow, Quantitative Imaging Laboratory, Stanford University (USA) [2009-2012] PhD in Computer Science, LSIIT (UMR CNRS/UdS 7005), University of Strasbourg (France) [2009-2012] Teaching Assistant, UFR de Mathématique et d'Informatique, University of Strasbourg (France)

Research keywords

Image analysis Data mining Pattern recognition Content-based image retrieval
Multiresolution imaging Background knowledge Hierarchical segmentation
Mathematical morphology Computer vision Remote sensing Medical Imaging

Contact

@ E-mail  camille.kurtz_at_parisdescartes_dot_fr ☏ Phone  +33 (0)1.83.94.58.07 ✉ Address  LIPADE - EA2517, SIP team  University Paris Descartes  45 rue des Saints Pères  75270 Paris Cedex 06  France LinkedIn

News

• [Nov. 2013] Master 2 (Msc) training course subject available here

Research

Principal collaborations

•     Quantitative Imaging Laboratory, Stanford School of Medicine, Stanford University
•     ICube (UMR CNRS 7357), University of Strasbourg
•     CReSTIC (EA 3804), University of Reims

                 

Projects

I am involved (and I have been involved) in different research projects related to medical imaging and remote sensing image analysis. Most of them are funded by the french Agence Nationale de la Recherche.

On going projects

ePAD (since 2012) The ePAD project ("electronic Physician Annotation Device") is a medical imaging project launched at Stanford University School of Medicine in 2012 and supported by the National Institutes of Health [grant number U01CA142555-01]. Medical images contain a wealth of information, such as anatomy and pathology, which is often not explicit and computationally accessible. Information schemes are being developed to describe the semantic content of images, but such schemes can be unwieldy to operationalize because there are few tools to enable users to capture structured information easily as part of the routine research workflow. This projects aims at developing a Web-based semantic annotation tool for radiological images called ePad, an open source tool enabling researchers and clinicians to create semantic annotations that are used to characterize images for classification or image retrieval purpose. ePad enables to describe images and image regions using a graphical interface (developed with cutting-edge features of GWT-P and HTML5) that maps their descriptions to ontologies.

Past projects

ANR Foster (2011 - 2013) The FOSTER project ("Spatio-temporal data mining: application to the understanding and monitoring of soil erosion") is a three-year project launched in January 2011. This computer science project is founded by the French National Research Agency ANR. This project aims at providing to geologists a semi-automatic and complete process for monitoring soil erosion. This process will be based on multi-temporal very high resolution satellite images coupled with digital elevation model (DEM), sensor data and/or expert knowledge. The project will focus more precisely on two important aspects of this process: segmentation of satellite images based on collaborative methods, and construction of descriptive (patterns, clustering, ...) and predictive (decision trees, ...) spatio-temporal models.

ACI Fodomust (2004 - 2008) The FoDoMuSt project ("Multi-Strategic Data Mining") is a four-year project launched in September 2004 and finished in September 2008. FoDoMuSt is a research project about multi-strategic data mining for extraction and characterisation of urban vegetation based on a database of remote sensing images. The main idea is to improve the result of one clustering on some data by using a set of clustering methods and making them collaborate. Multi-strategic clustering methods can then be used to generate thematic maps (with different clusters for different ground occupations/uses). The proposed collaborative approaches proposed during this project have been validated in the context of remote sensing images analysis, with the collaboration of the Laboratoire Image et Ville (UMR CNRS/UDS 7011).

PhD Thesis

General information

• Title: A collaborative region-based approach for the top-down analysis of multiresolution images
• Director: Pierre Gançarski (Professeur, Université de Strasbourg)
• Collaborators: Nicolas Passat (Professeur, Université de Reims) and Anne Puissant (MCF, Université de Strasbourg)
• Funding: French national grant (2009-2012)
• School: University of Strasbourg, Strasbourg (France)
• Laboratory: Image Sciences, Computer Sciences and Remote Sensing Laboratory (LSIIT), Strasbourg (France)

           

Thesis manuscript (in French)

• C. Kurtz
  Approche collaborative segmentation-classification pour l'analyse descendante d'images multirésolutions ,
  Université de Strasbourg, Available on HAL, Septembre 2012.

Publications

My page on scopus and my page on DBLP:

     

Research Articles in International Journals (5)

• C. Kurtz, A. Stumpf, J.P. Malet, P. Gançarski, A. Puissant, N. Passat,
  Hierarchical extraction of landslides from multiresolution remotely sensed optical images,
  ISPRS Journal of Photogrammetry and Remote Sensing, In Press, November 2013.
  

• C. Kurtz, P. Gançarski, N. Passat, A. Puissant,
  A hierarchical semantic-based distance for nominal histogram comparison ,
  Data and Knowledge Engineering, Volume 87, Issue 1, September 2013, pp 206--225.
  

• F. Petitjean, C. Kurtz, N. Passat, P. Gançarski,
  Spatio-temporal reasoning for the classification of satellite image time series ,
  Pattern Recognition Letters, Volume 33, Issue 13, October 2012, pp 1805--1815.
  

• C. Kurtz, N. Passat, P. Gançarski, A. Puissant,
  Extraction of complex patterns from multiresolution remote sensing images: A hierarchical top-down methodology ,
  Pattern Recognition, Volume 45, Issue 2, February 2012, pp 685--706.
  Ranked 2^nd hottest article of the Pattern Recognition journal (July to September 2011)

• C. Kurtz, N. Passat, P. Gançarski, A. Puissant,
  Multiresolution region-based clustering for urban analysis ,
  International Journal of Remote Sensing, Volume 31, Issue 22, July 2010, pp 5941--5973.
  Selected as cover image of the special issue

Research Articles in International Conference or Workshops Proceedings (5)

• C. Kurtz, N. Passat, P. Gançarski, A. Puissant,
  A histogram semantic-based distance for multiresolution image classification ,
  ICIP 2012, IEEE International Conference on Image Processing,
  IEEE Signal Processing Society, pp 1157--1160, Orlando, USA, September 2012.

• C. Kurtz, A. Puissant, N. Passat, P. Gançarski,
  Domain adaptation for the extraction of complex urban patterns from multiresolution satellite images ,
  IGARSS 2012, IEEE International Geoscience and Remote Sensing Symposium,
  IEEE Geoscience and Remote Sensing Society, pp 1773--1776, Munich, Germany, July 2012.

• C. Kurtz, N. Passat, P. Gançarski, A. Puissant,
  Hierarchical segmentation of multiresolution remote sensing images ,
  ISMM 2011, 10th International Symposium on Mathematical Morphology (P. Soille, M. Pesaresi, and G.K. Ouzounis, Eds.), Intra, Lake Maggiore, Italy, July 2011.
  Lecture Notes in Computer Science, Vol. 6671, pp 343--354 (Springer Verlag Berlin Heidelberg).

• C. Kurtz, A. Puissant, N. Passat, P. Gançarski,
  An interactive approach for extraction of urban patterns from multisource images ,
  JURSE 2011, Joint Urban Remote Sensing Event, 6th Joint Workshop on Remote Sensing and Data Fusion over Urban Areas,
  IEEE Geoscience and Remote Sensing Society, pp 321--324, Munich, Germany, April 2011.

• C. Kurtz, F. Petitjean, P. Gançarski,
  A context-based approach for the classification of satellite image time series ,
  IGARSS 2011, IEEE International Geoscience and Remote Sensing Symposium,
  IEEE Geoscience and Remote Sensing Society, pp. 495--498, Vancouver, Canada, July 2011.

Abstracts in International Conference or Workshops Proceedings (1)

• D.L. Rubin, D. Willrett, C. Kurtz,
  ePAD: Enabling Routine Imaging Assessment of Cancer Treatment Response in the Clinical Workflow ,
  RSNA 2013, Scientific Annual Meeting,
  Radiological Society of North America, Chicago, USA, November 2013.

Research Articles in National Conference or Workshops Proceedings (4)

• C. Kurtz, D.L. Rubin
  Utilisation de relations ontologiques pour la comparaison d'images décrites par des annotations sémantiques ,
  EGC 2014, Conférence Internationale Francophone sur l'Extraction et la Gestion de Connaissance, Article court, Rennes, France, Janvier 2014.
  

• C. Kurtz,
  Une distance hiérarchique basée sur la sémantique pour la comparaison d'histogrammes nominaux ,
  EGC 2012, Conférence Internationale Francophone sur l'Extraction et la Gestion de Connaissance, Article long, pp 77--88, Bordeaux, France, Janvier 2012.
  

• C. Kurtz,
  Extraction de connaissances hiérarchisées à partir d'images multirésolutions : application à la télédétection ,
  SFC 2011, 18^èmes Rencontres de la Société Francophone de Classification, Orléans, France, Octobre 2011.
  

• C. Kurtz,
  Classification non supervisée de données satellites multirésolution,
  FDC 2011, Atelier Fouille de données complexes, Journées Francophones Extraction et Gestion des Connaissances (EGC 2011), pp A143--A152, Brest, France, Janvier 2011.
  

Referee

• IEEE Journal of Biomedical and Health Informatics
• IEEE Transactions on Geoscience and Remote Sensing
• IEEE Geoscience and Remote Sensing Letters
• IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
• International Journal of Image and Data Fusion (Taylor and Francis) → Certificate of Appreciation
• Optics and Laser Technology (Elsevier)
• Applied Geography (Elsevier)

Communications

Oral communications (5)

• C. Kurtz,
  Une distance hiérarchique basée sur la sémantique pour la comparaison d'histogrammes nominaux,
  Journée du GDR I3, GT Fouille de Données, Paris, France, 2012.
  

• C. Kurtz,
  Extraction de formes urbaines à partir d'images satellites multirésolutions,
  Colloque Images et Villes, Université Paris-Diderot, Paris, France, 2011.
  

• C. Kurtz,
  Extraction de connaissances hiérarchisées à partir d'images multirésolutions : application à la télédétection,
  Journée GT-EGC Fouille de Données Complexes et de Grands Graphes, Paris, France, 2011.
  

• C. Kurtz,
  Multiresolution region-based clustering for urban analysis,
  Journées thématiques CNES-ORFEO, groupe GT3 cartographie, Paris, France, 2010.
  

• C. Kurtz,
  Analyse multiresolution d'images satellitaires : application à la classification de blocs urbains,
  Journées GDR I3/SIGMA-CASSINI Informations Géographiques et Observation de la Terre, Toulouse, France, 2009.
  

Seminars (6)

• C. Kurtz,
  Semantic features for the retrieval and the classification of radiological images,
  Seminar at SIP meeting, LIPADE EA 2517, Paris, France, 2013.
  

• C. Kurtz,
  Analyse et traitement automatique de médias visuels multisources : intégration de connaissances dans des approches basées régions,
  Seminar at Laboratoire LIPADE EA 2517, Paris, France, 2013.
  

• C. Kurtz,
  Approche collaborative segmentation-classification pour l'analyse descendante d'images multirésolutions,
  Seminar at Laboratoire IRISA UMR CNRS 6074, Vannes, France, 2012.
  

• C. Kurtz,
  Approche collaborative segmentation-classification pour l'analyse descendante d'images multirésolutions,
  Seminar at Laboratoire Gipsa-Lab UMR CNRS 5216, Grenoble, France, 2012.
  

• C. Kurtz,
  Mining complex multiresolution remote sensing images,
  Seminar at Laboratoire Hubert Curien UMR CNRS 5516, Saint-Etienne, France, 2012.
  

• C. Kurtz,
  Extraction of complex urban patterns from multiresolution remote sensing images,
  Seminar at European Commission, Joint Research Centre (JRC), Institute for the Protection and Security of the Citizen (IPSC), Ispra, Italia, 2011.
  

Posters (1)

• C. Kurtz,
  Interactive extraction of urban patterns from multisource images ,
  Pléiades days 2012, CNES workshop, Toulouse, France, 2012.
  

Students supervision

Master (M.Sc.) - Training course

• Marius-Valentin Grigore
  Cursus : Master Informatique ILC (UdS, Strasbourg)
  Subject : Software development (Mustic - Orféo Tool Box). Utilisation du Wrapping Java.
  Director : P. Gançarski (LSIIT)
  Supervisors : C. KURTZ, F. PETITJEAN
  Period : 2011-2012, 1 year
  

Licence (B.Sc.) - Training course

• Marius-Valentin Grigore
  Cursus : Licence Professionnelle Informatique (UdS, Strasbourg)
  Subject : Intégration de la librairie Orféo Tool Box (Analyse d'images satellitaires) dans le logiciel Mustic. Utilisation du Wrapping Java.
  Director : P. Gançarski (LSIIT)
  Supervisors : C. KURTZ, F. PETITJEAN
  Period : 2009-2010, 8 months