@InProceedings{Chum-BMVC08,
  IS = { zkontrolovano 18 Jan 2009 },
  UPDATE  = { 2008-12-23 },
  author =      {Chum, Ond{\v r}ej and Philbin, James and
                 Zisserman, Andrew},
  title =       {Near Duplicate Image Detection: min-{H}ash and 
                 tf-idf Weighting},
  authorship =  {90-5-5},
  year =        {2008},
  pages =       {493--502},
  booktitle =   {BMVC 2008: Proceedings of the 19th British
                 Machine Vision Conference},
  volume =      {1},
  editor =      {Everingham, M. and Needham, C.  and Fraille, R.},
  isbn =        {978-1-901725-36-0},
  book_pages =  {1194},
  publisher =   {BMVA},
  address =     {London, UK},
  month =       {September},
  day =         {1--4},
  venue =       {Leeds, UK},
  project =     {GACR 201/06/1821},
  keywords =    {min-Hash,near-duplicates,image retirieval},
  project =     {ICT-215078 DIPLECS, MSM6840770038},
  psurl =       {pdf},
  annote = {This paper proposes two novel image similarity measures
    for fast indexing via locality sensitive hashing. The similarity
    measures are applied and evaluated in the context of near
    duplicate image detection. The proposed method uses a visual
    vocabulary of vector quantized local feature descriptors (SIFT)
    and for retrieval exploits enhanced min-Hash techniques. Standard
    min-Hash uses an approximate set intersection between document
    descriptors was used as a similarity measure. We propose an
    efficient way of exploiting more sophisticated similarity measures
    that have proven to be essential in image / particular object
    retrieval. The proposed similarity measures do not require extra
    computational effort compared to the original measure.  We focus
    primarily on scalability to very large image and video databases,
    where fast query processing is necessary. The method requires only
    a small amount of data need be stored for each image. We
    demonstrate our method on the TrecVid 2006 data set which contains
    approximately 146K key frames, and also on challenging the
    University of Kentucky image retrieval database.},
}