IS = { zkontrolovano 13 Jan 2005 },
  UPDATE  = { 2004-10-01 },
  author =      {{\v S}ochman, Jan and Matas, Ji{\v r}{\'\i}},
  title =       {Inter-stage Feature Propagation in Cascade Building with {AdaBoost}},
  year =        {2004},
  pages =       {236--239},
  booktitle =   {Proceedings of ICPR 2004 17th International Conference on
                 Pattern Recognition},
  editor =      {Josef Kittler, Maria Petrou, Mark Nixon},
  publisher =   {IEEE Computer Society},
  address =     {10662 Los Vaqueros Circle, P.O.Box 3014, Los Alamitos, USA},
  isbn =        {0-7695-2128-2},
  volume =      {1},
  book_pages =  {840},
  month =       {August},
  day =         {23--26},
  venue =       {IAPR, Cambridge, UK},
  organization ={IEEE},
  annote = {A modification of the cascaded detector with the AdaBoost
    trained stage classifiers is proposed and brought to bear on the
    face detection problem. The cascaded detector is a sequential
    classifier with the ability of early rejection of easy
    samples. Each decision in the sequence is made by a separately
    trained classifier, a stage classifier. In proposed modification
    the features from one stage of training are propagated to the next
    stage classifier.  The proposed intra-stage feature propagation is
    shown to be greedily optimal, does not increase computational
    complexity of the stage classifier and leads to shorter stage
    classifiers and accordingly to faster detectors.
    A cascaded face detector is built with the intra-stage feature
    propagation and is compared with the Viola and Jones approach. The
    same detection and false positive rates are achieved with a
    detector that is 25 perc. faster and consists of only two thirds of
    the weak classifiers needed for a cascade trained by the Viola and
    Jones approach. The latter property facilitates hardware
    implementation, the former opens scope for the increase in the
    search space, e.g. the range of scales at which faces are
  keywords =    {AdaBoost, face detection, computer vision},
  authorship =  {50-50},
  project =     {GACR 102/02/1539, CTU 0307313, STINT Dur IG2003-2 062},
  psurl       = {PS.GZ},