@InProceedings{ Cevikalp-FaceAndLandmarks-FG2013,
  IS = { zkontrolovano 24 Jan 2014 },
  UPDATE  = { 2013-09-19 },
  author =      {Cevikalp, Hakan and Triggs, Bill and Franc, Vojt{\v{e}}ch},
  title =       {Face and Landmark Detection by Using Cascade of Classifiers},
  c_title =     {Detekce tv{\' a}{\v r}{\'{\i}} a v{\' y}znamn{\'{y}}ch bod{\accent23 u} 
                 pomoc{\'{\i}} kask{\'{a}}dy klasifik{\'{a}}tor{\accent23 u}},
  year =        {2013},
  pages =       {1-7},
  booktitle =   {Automatic Face and Gesture Recognition (FG), 
                 2013 10th IEEE International Conference and Workshops on},
  editor =      {Chellappa, Rama and Xilin, Chen and Qiang, Ji and 
                 Pantic, Maja and Sclaroff, Stan and Lijun Yin},
  publisher =   {IEEE},
  address =     {Piscataway, USA},
  volume =      {1},
  isbn =        {978-1-4673-5545-2},
  book_pages =  {861},
  month =       {April},
  day =         {22-26},
  venue =       {Shanghai, China},
  annote = {In this paper, we consider face detection along with
    facial landmark localization inspired by the recent studies
    showing that incorporating object parts improves the detection
    accuracy. To this end, we train roots and parts detectors where
    the roots detector returns candidate image regions that cover the
    entire face, and the parts detector searches for the landmark
    locations within the candidate region. We use a cascade of binary
    and one-class type classifiers for the roots detection and SVM
    like learning algorithm for the parts detection. Our proposed face
    detector outperforms the most of the successful face detection
    algorithms in the literature and gives the second best result on
    all tested challenging face detection databases.  Experimental
    results show that including parts improves the detection
    performance when face images are large and the details of eyes and
    mouth are clearly visible, but does not introduce any improvement
    when the images are small.},
  c_annote = {Clanek se zabyva detekci tvari a localizaci vyznamnych
    bodu na tvari (oci, pusa, nos). Navrzena metoda je slozena z
    korenoveho detektoru, ktery v obrazku vyhledava cele tvare, a
    detektoru casti, ktery v oblasti nalezene korenovym detektorem
    lokalizuje vyznamne body na tvari. Korenovy detektor je realizovan
    jako kaskada klasifikatoru s roustouci slozitosti.  Detektor casti
    je zalozen na "deformable part" modelu, kdy se tvar popisuje
    mnozinou casti a vztahu mezi nimi. Parametry vsech klasifikatoru
    se uci z prikladu algoritmem SVM. Experimenty provedene na tezke
    databazi obrazku ukazuji, ze navrzeny detektor dosahuje vybornych
    vysledku v porovnani s existujicimi metodami. Dale se ukazuje, ze
    pouziti casti pri modelovani tvare zlepsuje presnost detekce na
    tvarich s velkym rozlisenim, ale temer nepomaha pri nizkych
    rozlisenich.},
  keywords =    {Face detection, Landmark Detection, Support Vector Machines},
  prestige =    {important},
  authorship =  {80-10-10},
doi = {10.1109/FG.2013.6553705},
  project =     {FP7-ICT-247525 HUMAVIPS},
  psurl = {ftp://cmp.felk.cvut.cz/pub/cmp/articles/franc/Cevilkalp-FaceDetector-FG2013.pdf},
  www = {http://http://fg2013.cse.sc.edu},
  acceptance_ratio = {0.35},
}