Content Based Detection of Popular Images in Large Image Databases

Martin Solli, Reiner Lenz
Proceedings of the 17th Scandinavian conference on Image analysis (SCIA), page 218--227 - 2011
Download the publication : fulltext.pdf [654Ko]  
We investigate the use of standard image descriptors and a supervised learning algorithm for estimating the popularity of images. The intended application is in large scale image search engines, where the proposed approach can enhance the user experience by improving the sorting of images in a retrieval result. Classification methods are trained and evaluated on real-world user statistics recorded by a major image search engine. The conclusion is that for many image categories, the combination of supervised learning algorithms and standard image descriptors results in useful popularity predictions.

Images and movies

 

BibTex references

@InProceedings\{SL11,
  author       = "Solli, Martin and Lenz, Reiner",
  title        = "Content Based Detection of Popular Images in Large Image Databases",
  booktitle    = "Proceedings of the 17th Scandinavian conference on Image analysis (SCIA)",
  series       = "Lecture Notes in Computer Science, ISSN 0302-9743; 6688",
  pages        = "218--227",
  year         = "2011",
  editor       = "A. Heyden, F. Kahl",
  publisher    = "Springer-Verlag"
}

Author publication list