IEEE Transactions on Pattern Analysis and Machine Intelligence
Hypothesis integration in image understanding systems
Computer Vision, Graphics, and Image Processing
Evidence accumulation & flow of control
AI Magazine
A knowledge-based approach to integration of image processing procedures
CVGIP: Image Understanding
Control of selective perception using Bayes nets and decision theory
International Journal of Computer Vision - Special issue on active vision II
Temporal difference learning and TD-Gammon
Communications of the ACM
Closed-Loop Object Recognition Using Reinforcement Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computer Vision and Image Processing: A Practical Approach Using Cviptools with Cdrom
Computer Vision and Image Processing: A Practical Approach Using Cviptools with Cdrom
The Image Understanding Environment Program
IEEE Expert: Intelligent Systems and Their Applications
Learning to Predict by the Methods of Temporal Differences
Machine Learning
Robust analysis of feature spaces: color image segmentation
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
A reinforcement learning approach to job-shop scheduling
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
MOBSY: Integration of Vision and Dialogue in Service Robots
ICVS '01 Proceedings of the Second International Workshop on Computer Vision Systems
Unsupervised Learning of Biologically Plausible Object Recognition Strategies
BMVC '00 Proceedings of the First IEEE International Workshop on Biologically Motivated Computer Vision
Human-computer interaction for the generation of image processing applications
International Journal of Human-Computer Studies
| Hi-index | 0.00 |
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.