Context-Dependent Logo Matching and Recognition

The availability of measures of appearance of trademarks and logos in a video is important in fields of marketing and sponsoring. These statistics can, in fact, be used by the sponsors to estimate the number TV viewers that noticed them and then evaluate the effects of the sponsorship.

 

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 image archives.
Reference logos as well as test images, are seen as constellations of local feature (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 MICC-Logos dataset overtaking, by 20%, baseline as well as state-of-the-art matching/recognition procedures. We present also results on another public dataset, the FlickrLogos-27 image collection, to demonstrate the generality of our method.

Related publications:

Dataset:

  • MICC-Logos: this dataset is composed by 720 images downloaded from the web in January 2010; it contains 13 logo classes each one represented with 15-87 real world pictures.

If you use this dataset, please cite the paper: H. Sahbi, L. Ballan, G. Serra, and A. Del Bimbo, “Context-Dependent Logo Matching and Recognition”, IEEE Transactions on Image Processing, vol. 22, iss. 3, pp. 1018-1031, 2013.