RETIN: a smart interactive digital media retrieval system

This demonstration presents a digital media retrieval system for searching large categories in different media databases. The core of our system is an interactive online classification based on user labeling. The classification is obtained with a statistical learning method: kernels for similarity representation and SVM (Support Vector Machine) using binary user annotations. RETIN applies also an active learning strategy for proposing documents to the user for labeling. The system can deal with images, 3D objects and videos and other media can be added to. A graphical user interface allows easy browsing of different media, simple and user-friendly interaction and fast retrieval.

[1]  Matthieu Cord,et al.  Image Retrieval using Long-Term Semantic Learning , 2006, 2006 International Conference on Image Processing.

[2]  Matthieu Cord,et al.  Feature-based approach to semi-supervised similarity learning , 2006, Pattern Recognit..

[3]  Matthieu Cord,et al.  Stochastic exploration and active learning for image retrieval , 2007, Image Vis. Comput..

[4]  Frédéric Precioso,et al.  Robust scene cut detection by supervised learning , 2006, 2006 14th European Signal Processing Conference.

[5]  Matthieu Cord,et al.  CBIR in Distributed Databases using a Multi-Agent System , 2006, 2006 International Conference on Image Processing.

[6]  Sylvie Philipp-Foliguet.  FReBIR : Fuzzy Region-Based Image Retrieval , 2006 .

[7]  Matthieu Cord,et al.  A comparison of active classification methods for content-based image retrieval , 2004, CVDB '04.

[8]  F. Precioso,et al.  3D Content-Based Retrieval in Artwork Databases , 2007, 2007 3DTV Conference.