• DocumentCode
    2496750
  • Title

    Delayed reinforcement learning for closed-loop object recognition

  • Author

    Peng, Jing ; Bhanu, Bir

  • Author_Institution
    Coll. of Eng., California Univ., Riverside, CA, USA
  • Volume
    4
  • fYear
    1996
  • fDate
    25-29 Aug 1996
  • Firstpage
    310
  • Abstract
    Object recognition is a multi-level 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 research. A robust closed-loop system based on “delayed” reinforcement learning is introduced in this paper. The parameters of a multi-level 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 2D objects. The approach systematically controls feedback in a multi-level vision system and provides a potential solution to a long-standing problem in the field of computer vision
  • Keywords
    closed loop systems; computer vision; feature extraction; feedback; image segmentation; learning (artificial intelligence); learning systems; object recognition; 2D object recognition; closed-loop system; computer vision; delayed reinforcement learning; feature extraction; feedback; image segmentation; learning system; model-based object recognition; Computer vision; Delay; Feature extraction; Feedback loop; Image recognition; Image segmentation; Learning systems; Object recognition; Output feedback; Robustness;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition, 1996., Proceedings of the 13th International Conference on
  • Conference_Location
    Vienna
  • ISSN
    1051-4651
  • Print_ISBN
    0-8186-7282-X
  • Type

    conf

  • DOI
    10.1109/ICPR.1996.547436
  • Filename
    547436