ADORE: Adaptive Object Recognition

10 years 8 months ago
ADORE: Adaptive Object Recognition
Many modern computer vision systems are built by chaining together standard vision procedures, often in graphical programming environments such as Khoros, CVIPtools or IUE. Typically, these procedures are selected and sequenced based on a programmer’s intuition rather than sound scientific principles. This paper presents a theoretically sound method for constructing object recognition strategies by modeling object recognition as a Markov Decision Problem (MDP). The result is a system called ADORE (Adaptive Object Recognition) that automatically learns object recognition strategies from training data. Experimental results are presented in which ADORE is trained to recognize five types of houses in aerial images, and where its performance can be (and is) compared to optimal.
Bruce A. Draper, José Bins, Kyungim Baek
Added 04 Aug 2010
Updated 04 Aug 2010
Type Conference
Year 1999
Where ICVS
Authors Bruce A. Draper, José Bins, Kyungim Baek
Comments (0)