Closed-loop object recognition using reinforcement learning

Jing Peng, Bir Bhanu

Research output: Contribution to journalConference articleResearchpeer-review

3 Citations (Scopus)

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 color images with varying external conditions.

Original languageEnglish
Pages (from-to)538-543
Number of pages6
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
StatePublished - 1 Jan 1996
EventProceedings of the 1996 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - San Francisco, CA, USA
Duration: 18 Jun 199620 Jun 1996

Fingerprint

Object recognition
Reinforcement learning
Image segmentation
Function evaluation
Computer vision
Reinforcement
Color
Experiments

Cite this

@article{360b1192eb7841aa84fee4b8d8abed4c,
title = "Closed-loop object recognition using reinforcement learning",
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 color images with varying external conditions.",
author = "Jing Peng and Bir Bhanu",
year = "1996",
month = "1",
day = "1",
language = "English",
pages = "538--543",
journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
issn = "1063-6919",
publisher = "IEEE Computer Society",

}

Closed-loop object recognition using reinforcement learning. / Peng, Jing; Bhanu, Bir.

In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 01.01.1996, p. 538-543.

Research output: Contribution to journalConference articleResearchpeer-review

TY - JOUR

T1 - Closed-loop object recognition using reinforcement learning

AU - Peng, Jing

AU - Bhanu, Bir

PY - 1996/1/1

Y1 - 1996/1/1

N2 - 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 color images with varying external conditions.

AB - 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 color images with varying external conditions.

UR - http://www.scopus.com/inward/record.url?scp=0029714879&partnerID=8YFLogxK

M3 - Conference article

SP - 538

EP - 543

JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SN - 1063-6919

ER -