@InProceedings{sulc-ivcnz14,
  IS = { zkontrolovano 12 Jan 2014 },
  UPDATE  = { 2014-01-06 },
  key =         {sulc-ivcnz14},
  author =      {{\v S}ulc, Milan and Matas, Ji{\v r}{\'\i}},
  title =       {Kernel-mapped Histograms of Multi-scale LBPs for Tree Bark Recognition},
  year =        {2013},
  pages =       {88-93},
  booktitle =   {2013 28th International Conference of Image and Vision Computing New Zealand (IVCNZ 2013)},
  editor =      {Taehyun Rhee, Ramesh Rayudu, Christopher Hollitt, John Lewis, Mengjie Zhang},
  publisher =   {IEEE},
  address =     {IEEE Operations Center, 445 Hoes Lane, Piscataway, USA},
  isbn =        {978-1-4799-0882-0},
  book_pages =  {517},
  month =       {November},
  day =         {27-29},
  venue =       {Wellington, New Zealand},
  annote =      {We propose a novel method for tree bark
                  identification by SVM classification of
                  feature-mapped multi-scale descriptors formed by
                  concaatenated histograms of Local Binary Patterns
                  (LBPs). A feature map approximating the histogram
                  intersection kernel significantly improves the
                  methods accuracy.  Contrary to common practice, we
                  use the full 256 bin LBP histogram rather than the
                  standard 59 bin histogram of uniform LBPs and obtain
                  superior results. Robustness to scale changes is
                  handled by forming multiple multi-scale descriptors.
                  Experiments conducted on a standard dataset show
                  96.5% accuracy using ten-fold cross
                  validation. Using the standard 15 training examples
                  per class, the proposed method achieves a
                  recognition rate of 82.5% and significantly
                  outperforms both the state-of-the-art automatic
                  recognition rate of 64.2% and human experts with
                  recognition rates of 56.6% and 77.8%.  Experiments
                  on standard texture datasets confirm that the
                  proposed method is suitable for general texture
                  recognition.},
  keywords =    {texture recognition, bark, plant identification, LBP},
  project =     {GACR P103/12/G084, SGS13/142/OHK3/2T/13, TACR TE01020415 V3C},
}