Université d'Auvergne Clermont1 | CNRS



3 years funding project, FUI (AAP14) - on-going project

Overall project's funding: 3 300k€

Partner's funding: 346k€


The aim of the 3DCI project (FUI AAP14) consists in developping an original and innovative system for default detection during the inspection phase of electronic components of electronic board manufacturing.

In the 3DCI project, ISIT is involved as a public research laboratory to design new segmentation methods driven by expert knowledge and using abstract descriptions (such as graphs). The two application contexts are the present project and the medical imaging segmentation.







Slicer3D improvement

Improvement of Slicer integrating the manual labelling from multiple MRIs: https://github.com/ArashAkbarinia/Slicer

Motivation in 3DCI context: facilitate manual labelling of MRIs in the medical application, with the aim of providing 3D shapes from the original MRIs used in clinic routine.

ODDS: Segmentation and Semantic Annotation

A C++ and java prototype for automatic segmentation and semantic annotation driven by expert knowledge has been developped as a proof of concept.

The source code will be released under Open Source license once the final step of blind review will be achieved (end of November 2015).

Geometric texture segmentation

A C++ prototype for geometric texture segmentation has been developped as a proof of concept. 

The source code will be released under Open Source license once the publication will be accepted in a blind review process (end of November 2015).


Institut Pascal, ISPR/ComSee Team, September 2014

Title: Geometric Texture Segmentation on 3D Meshes

Extraction et gestion des connaissances (EGC'2015), Luxembourg, January 2015

Title:  A Framework for Mesh Segmentation and Annotation using Ontologies (slides)