Context-dependent logo matching and retrieval Recherche et localisation des logos

We contribute through this work to the design of a novel variational framework able to match and recognize multiple instances of multiple reference logos in large scale images. Reference logos as well as test images, are seen as constellations of local features (interest points, regions, etc.) and matched by minimizing an energy function mixing (i) a fidelity term that measures the quality of feature matching (ii) a neighborhood criterion which captures feature co-occurrence/geometry and (iii) a regularization term that controls the smoothness of the matching solution. We also introduce a detection/recognition procedure and we study its theoretical consistency. Finally, we show the validity of our method through extensive experiments on the challenging ”Trademark-720” logo database overtaking, by 20%, baseline as well as standard matching/recognition procedures; furthermore, our method is able to process images of 1500× 1500 pixels and checks for the existence of 13 reference logos in less than 1(s) using a standard 2 GHz PC.