Abstract Computation time is an important performance characteristic of computer vision algorithms. This paper shows how existing (slow) binary-valued decision algorithms can be approximated by a trained WaldBoost classifier, which minimises the decision time while guaranteeing predefined approximation precision. The core idea is to take an existing algorithm as a black box performing some useful binary decision task and to train the WaldBoost classifier as its emulator. Two interest point detectors, Hessian-Laplace and Kadir-Brady saliency detector, are emulated to demonstrate the approach. The experiments show similar repeatability and matching score of the original and emulated algorithms while achieving a 70-fold speed-up for Kadir-Brady detector.
Learning a Fast Emulator of a Binary Decision Process
Computer Vision – ACCV 2007 ; 4 ; 236-245
Lecture Notes in Computer Science ; 4844 , 4
2007-01-01
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Interest Point , Saliency Detector , Sequential Probability Ratio Test , Interest Point Detector , Computer Vision Algorithm Computer Science , Image Processing and Computer Vision , Computer Imaging, Vision, Pattern Recognition and Graphics , Pattern Recognition , Artificial Intelligence (incl. Robotics) , Biometrics , Algorithm Analysis and Problem Complexity
Learning Fast Emulators of Binary Decision Processes
British Library Online Contents | 2009
|Battery emulator and method for controlling the battery emulator
Europäisches Patentamt | 2020
|