Closed-Loop Object Recognition Using Reinforcement Learning

Authors:
Jing Peng;Bir Bhanu
Affiliations:
Univ. of California, Riverside;Univ. of California, Riverside
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
1998

Citing 2
Cited 26

Computational strategies for object recognition

ACM Computing Surveys (CSUR)
Performance characterization of image understanding algorithms

Performance characterization of image understanding algorithms

Supervised Learning of Large Perceptual Organization: Graph Spectral Partitioning and Learning Automata

IEEE Transactions on Pattern Analysis and Machine Intelligence
Statistical Edge Detection: Learning and Evaluating Edge Cues

IEEE Transactions on Pattern Analysis and Machine Intelligence
ADORE: Adaptive Object Recognition

ICVS '99 Proceedings of the First International Conference on Computer Vision Systems
Adapting Object Recognition across Domains: A Demonstration

ICVS '01 Proceedings of the Second International Workshop on Computer Vision Systems
A Probabilistic Approach to Simultaneous Segmentation, Object Recognition, 3D Localization, and Tracking Using Stereo

Proceedings of the 23rd DAGM-Symposium on Pattern Recognition
Integrating Relevance Feedback Techniques for Image Retrieval Using Reinforcement Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning-based algorithm selection for image segmentation

Pattern Recognition Letters
A situated model for sensory-motor coordination in gaze control

Pattern Recognition Letters - Special issue: Evolutionary computer vision and image understanding
Stand-alone embedded vision system based on fuzzy associative database

Image and Vision Computing
Performance measure as feedback variable in image processing

EURASIP Journal on Applied Signal Processing
Learning to Select Object Recognition Methods for Autonomous Mobile Robots

Proceedings of the 2008 conference on ECAI 2008: 18th European Conference on Artificial Intelligence
Closed-loop learning of visual control policies

Journal of Artificial Intelligence Research
Reinforcement learning combined with a fuzzy adaptive learning control network (FALCON-R) for pattern classification

Pattern Recognition
Coevolutionary feature learning for object recognition

MLDM'03 Proceedings of the 3rd international conference on Machine learning and data mining in pattern recognition
Coevolution and linear genetic programming for visual learning

GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartI
A multiple instance learning based framework for semantic image segmentation

Multimedia Tools and Applications
From region based image representation to object discovery and recognition

SSPR&SPR'10 Proceedings of the 2010 joint IAPR international conference on Structural, syntactic, and statistical pattern recognition
Face authentication using the trace transform

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Software agent with reinforcement learning approach for medical image segmentation

Journal of Computer Science and Technology
Sensory-Motor coordination in gaze control

EC'05 Proceedings of the 3rd European conference on Applications of Evolutionary Computing
Robust camera pose and scene structure analysis for service robotics

Robotics and Autonomous Systems
Incorporating shape into spatially-aware adaptive object segmentation algorithm

Proceedings of the Fifth International C* Conference on Computer Science and Software Engineering
Learning-based object segmentation using regional spatial templates and visual features

ICCVG'12 Proceedings of the 2012 international conference on Computer Vision and Graphics
Reinforcement Learning for Improving Gene Identification Accuracy by Combination of Gene-Finding Programs

International Journal of Applied Metaheuristic Computing
Design with shape grammars and reinforcement learning

Advanced Engineering Informatics
Reinforcement learning algorithms with function approximation: Recent advances and applications

Information Sciences: an International Journal

Quantified Score

Hi-index	0.14

Visualization

Abstract

Current computer vision systems whose basic methodology is open-loop or filter type typically use image segmentation followed by object recognition algorithms. These systems are not robust for most real-world applications. In contrast, the system presented here achieves robust performance by using reinforcement learning to induce a mapping from input images to corresponding segmentation parameters. This is accomplished by using the confidence level of model matching as a reinforcement signal for a team of learning automata to search for segmentation parameters during training. The use of the recognition algorithm as part of the evaluation function for image segmentation gives rise to significant improvement of the system performance by automatic generation of recognition strategies. The system is verified through experiments on sequences of indoor and outdoor color images with varying external conditions.