Closed-loop object recognition using reinforcement learning

Jing Peng, Bir Bhanu

Research output: Contribution to journalArticle

82 Scopus citations

Abstract

Current computer vision systems whose basic methodology is open-loop or fi'/tertype 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.

Original languageEnglish
Pages (from-to)139-154
Number of pages16
JournalIEEE Transactions on Pattern Analysis and Machine Intelligence
Volume20
Issue number2
DOIs
StatePublished - 1 Dec 1998

Keywords

  • Adaptive color image segmentation
  • Function optimization
  • Generalized learning automata
  • Learning in computer vision
  • Model-based object recognition
  • Multiscenario recognition
  • Parameter learning
  • Recognition feedback
  • Segmentation evaluation

Fingerprint Dive into the research topics of 'Closed-loop object recognition using reinforcement learning'. Together they form a unique fingerprint.

  • Cite this