Adore: Adaptive object recognition

Adore: Adaptive object recognition (1999)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Bruce A. Draper , Jose Bins , Kyungim Baek

Venue:	Videre
Citations:	29 - 1 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Adore: Adaptive object recognition	INFERENCE
AUTHOR NAME	Bruce A. Draper	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer Science; Colorado State University	SVM HeaderParse 0.2
AUTHOR ADDR	Fort Collins, CO, USA. 80523	SVM HeaderParse 0.2
AUTHOR NAME	Jose Bins	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer Science; Colorado State University	SVM HeaderParse 0.2
AUTHOR ADDR	Fort Collins, CO, USA. 80523	SVM HeaderParse 0.2
AUTHOR NAME	Kyungim Baek	SVM HeaderParse 0.2
AUTHOR AFFIL	Department of Computer Science; Colorado State University	SVM HeaderParse 0.2
AUTHOR ADDR	Fort Collins, CO, USA. 80523	SVM HeaderParse 0.2
ABSTRACT	Abstract. 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 by an ad-hoc combination of programmer’s intuition and trial-and-error. This paper presents a theoretically sound method for constructing object recognition strategies by casting object recognition as a Markov Decision Problem (MDP). The result is a system called ADORE (Adaptive Object Recognition) that automatically learns object recognition control policies 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. 1	SVM HeaderParse 0.2
YEAR	1999	INFERENCE
VENUE	Videre	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	86--99	INFERENCE
VOLUME	1	INFERENCE
CITATIONS	35 found	ParsCit 1.0