Multimédia indexing (HTI 5)

Catalogue des cours de Télécom SudParis

Code

IMA 5001

Niveau

Graduate (M2)

Période

Fall (P1)

Domaine

Image

Langue d'enseignement

Anglais

Crédits ECTS

4

Heures programmées / Charge de travail

45 / 90

Responsable(s)

  • ZAHARIA Titus

Département

- Advanced Research and Techniques for Multidimensional Imaging Systems

Equipe pédagogique

  • ZAHARIA Titus

Objectif

-To be to able to exploit the content-based representations and access paradigms for approaching indexing, searching and enriching heterogeneous content problems in a unitary way.
-To Know how to take advantage of relevance feedback and user profiling in order to design customised and interactive services.
-To master data mining key techniques for implementing real time searching engines in huge databases (Internet).
-To be able to deploy interoperable indexing tools based on multimedia standards and description languages (MPEG-7, XML…).

Contenu

•2D/3D shape extraction
•Colour segmentation
•Extraction of texture primitives
•Motion analysis
•Scene 3D structure estimation
•Audio segmentation
•The metadata era: a new multimedia consumption
•Low-level descriptors for content indexing and content-based access : audio descriptors, (2D, 3D and 2D/3D) shape descriptors, motion descriptors, texture descriptors
•Query by example and similarity metrics
•Towards high-level descriptions: description schemes, hierarchical and multigranular representations
•Structural and semantic descriptions of multimedia documents
•Training, profiles and relevance feedback
•Search engines and data mining
•Description languages: XML, XML-schema, RDF, MPEG-7
•Applications (video archiving, sign language, face recognition

Prérequis

None

Mots-clés

Multimedia indexation, visual descriptors, shape, color, motion, texture, description scheme, description languages, MPEG-7standard

Evaluation

Continuous evaluation based on lab assignments (BE) and personal supervised project (P) linked to real industrial applications or to national/European research projects.
Final mark = Average (BE, P)

Approches pédagogiques

 

Programme

Programme Ingénieur

Fiche mise à jour : 09/04/2014 16:39:07