Content Based Image Retrieval using Bag-Of-Regions: an Efficient Approach

Remi Vieux (1) , Jenny Benois-Pineau (1) , Jean-Philippe Domenger (1)

1 LaBRI - Laboratoire Bordelais de Recherche en Informatique

In this work we introduce the Bag-Of-Regions model, in- spired from the Bag-Of-Visual-Words. Instead of clustering local image patches represented by SIFT or related descriptors, low level descriptors are extracted and clustered from image regions, as given by a segmen- tation algorithm. The Bag-Of-Region model allows to de ne visual dic- tionaries that capture extra information with respect to Bag-Of-Visual- Words. Combined description schemes and ad-hoc incremental clustering for visual dictionnaries are proposed. The results on public datasets are promising.

Mots clés: Content Based Image Retrieval; Bag-Of-Regions; Incremental Clustering; Meta-Search

Domaines: Traitement des images [eess.IV]

Remi Vieux, Jenny Benois-Pineau, Jean-Philippe Domenger. Content Based Image Retrieval using Bag-Of-Regions: an Efficient Approach. International Conference on Multimedia Modeling, Jan 2012, Klagenfurt, Austria. pp.1-11. ⟨hal-00646797⟩