Delayed reinforcement learning for adaptive image segmentation and feature extraction

Jing Peng, Bir Bhanu

Research output: Contribution to journalArticleResearchpeer-review

22 Citations (Scopus)

Abstract

Object recognition is a multilevel process requiring a sequence of algorithms at low, intermediate, and high levels. Generally, such systems are open loop with no feedback between levels and assuring their robustness is a key challenge in computer vision and pattern recognition research. A robust closed-loop system based on "delayed" reinforcement learning is introduced in this paper. The parameters of a multilevel system employed for model-based object recognition are learned. The method improves recognition results over time by using the output at the highest level as feedback for the learning system. It has been experimentally validated by learning the parameters of image segmentation and feature extraction and thereby recognizing 2-D objects. The approach systematically controls feedback in a multilevel vision system and shows promise in approaching a long-standing problem in the fleld of computer vision and pattern recognition.

Original languageEnglish
Pages (from-to)482-488
Number of pages7
JournalIEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews
Volume28
Issue number3
DOIs
StatePublished - 1 Dec 1998

Fingerprint

Object recognition
Reinforcement learning
Image segmentation
Computer vision
Pattern recognition
Feature extraction
Feedback
Open systems
Closed loop systems
Feedback control
Learning systems

Keywords

  • Adaptive feature extraction
  • Adaptive image segmentation
  • Learning for multilevel vision
  • Learning in computer vision
  • Modelbased recognition
  • Multiscenario object recognition
  • Recognition feedback

Cite this

@article{49ce8e97de8d4d72932b92f7115f6c4b,
title = "Delayed reinforcement learning for adaptive image segmentation and feature extraction",
abstract = "Object recognition is a multilevel process requiring a sequence of algorithms at low, intermediate, and high levels. Generally, such systems are open loop with no feedback between levels and assuring their robustness is a key challenge in computer vision and pattern recognition research. A robust closed-loop system based on {"}delayed{"} reinforcement learning is introduced in this paper. The parameters of a multilevel system employed for model-based object recognition are learned. The method improves recognition results over time by using the output at the highest level as feedback for the learning system. It has been experimentally validated by learning the parameters of image segmentation and feature extraction and thereby recognizing 2-D objects. The approach systematically controls feedback in a multilevel vision system and shows promise in approaching a long-standing problem in the fleld of computer vision and pattern recognition.",
keywords = "Adaptive feature extraction, Adaptive image segmentation, Learning for multilevel vision, Learning in computer vision, Modelbased recognition, Multiscenario object recognition, Recognition feedback",
author = "Jing Peng and Bir Bhanu",
year = "1998",
month = "12",
day = "1",
doi = "10.1109/5326.704593",
language = "English",
volume = "28",
pages = "482--488",
journal = "IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews",
issn = "1094-6977",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

Delayed reinforcement learning for adaptive image segmentation and feature extraction. / Peng, Jing; Bhanu, Bir.

In: IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews, Vol. 28, No. 3, 01.12.1998, p. 482-488.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Delayed reinforcement learning for adaptive image segmentation and feature extraction

AU - Peng, Jing

AU - Bhanu, Bir

PY - 1998/12/1

Y1 - 1998/12/1

N2 - Object recognition is a multilevel process requiring a sequence of algorithms at low, intermediate, and high levels. Generally, such systems are open loop with no feedback between levels and assuring their robustness is a key challenge in computer vision and pattern recognition research. A robust closed-loop system based on "delayed" reinforcement learning is introduced in this paper. The parameters of a multilevel system employed for model-based object recognition are learned. The method improves recognition results over time by using the output at the highest level as feedback for the learning system. It has been experimentally validated by learning the parameters of image segmentation and feature extraction and thereby recognizing 2-D objects. The approach systematically controls feedback in a multilevel vision system and shows promise in approaching a long-standing problem in the fleld of computer vision and pattern recognition.

AB - Object recognition is a multilevel process requiring a sequence of algorithms at low, intermediate, and high levels. Generally, such systems are open loop with no feedback between levels and assuring their robustness is a key challenge in computer vision and pattern recognition research. A robust closed-loop system based on "delayed" reinforcement learning is introduced in this paper. The parameters of a multilevel system employed for model-based object recognition are learned. The method improves recognition results over time by using the output at the highest level as feedback for the learning system. It has been experimentally validated by learning the parameters of image segmentation and feature extraction and thereby recognizing 2-D objects. The approach systematically controls feedback in a multilevel vision system and shows promise in approaching a long-standing problem in the fleld of computer vision and pattern recognition.

KW - Adaptive feature extraction

KW - Adaptive image segmentation

KW - Learning for multilevel vision

KW - Learning in computer vision

KW - Modelbased recognition

KW - Multiscenario object recognition

KW - Recognition feedback

UR - http://www.scopus.com/inward/record.url?scp=0032136860&partnerID=8YFLogxK

U2 - 10.1109/5326.704593

DO - 10.1109/5326.704593

M3 - Article

VL - 28

SP - 482

EP - 488

JO - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews

JF - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews

SN - 1094-6977

IS - 3

ER -