@Article{Sochman-IJCV2009,
  IS = { zkontrolovano 29 Sep 2009 },
  UPDATE  = { 2009-09-29 },
  author =     {Jan {\v S}ochman and Ji{\v r}{\'\i} Matas},
  title =      {Learning Fast Emulators of Binary Decision Processes},
  year =       {2009},
  month =      {June},
  pages =      {149--163},
  journal =    {International Journal of Computer Vision},
  publisher =  {Springer},
  address =    {New York, USA},
  issn =       {0920-5691},
  volume =     {83},
  number =     {2},
  authorship = {50-50},
  annote = {Computation time is an important performance
    characteristic of computer vision algorithms. The paper shows how
    existing (slow) binary decision algorithms can be approximated by
    a (fast) trained WaldBoost classifier.  WaldBoost learning
    minimises the decision time of the classifier while guaranteeing
    predefined precision. We show that the WaldBoost algorithm
    together with bootstrapping is able to efficiently handle an
    effectively unlimited number of training examples provided by the
    implementation of the approximated algorithm.  Two interest point
    detectors, the Hessian-Laplace and the Kadir-Brady saliency
    detectors, are emulated to demonstrate the approach. Experiments
    show that while the repeatability and matching scores are similar
    for the original and emulated algorithms, a 9-fold speed-up for
    the Hessian-Laplace detector and a 142-fold speed-up for the
    Kadir-Brady detector is achieved. For the Hessian-Laplace
    detector, the achieved speed is similar to SURF, a popular and
    very fast handcrafted modification of Hessian-Laplace; the
    WaldBoost emulator approximates the output of the Hessian-Laplace
    detector more precisely.},
  keywords =   {Boosting, AdaBoost, Sequential probability ratio test, 
    Sequential decision making, WaldBoost, Interest point detectors, 
    Machine learning},
  project =    {FP6-IST-027113, GACR 102/07/1317},
psurl       = {[Sochman-ijcv2009.pdf]},
}