• DocumentCode
    1316241
  • Title

    Scene understanding by rule evaluation

  • Author

    Blaschof, W.F. ; Caelli, Terry

  • Author_Institution
    Dept. of Psychol., Alberta Univ., Edmonton, Alta., Canada
  • Volume
    19
  • Issue
    11
  • fYear
    1997
  • fDate
    11/1/1997 12:00:00 AM
  • Firstpage
    1284
  • Lastpage
    1288
  • Abstract
    We consider how machine learning can be used to help solve the problem of identifying objects or structures composed of parts in complex scenes. We first discuss a conditional rule generation technique that is designed to describe structures using part attributes and their relations. We then show how the resultant rules can be used for region labeling and examine constraint propagation techniques for improving rule-based object classification
  • Keywords
    constraint handling; image classification; learning (artificial intelligence); object recognition; complex scenes; conditional rule generation technique; constraint propagation techniques; machine learning; part attributes; region labeling; rule evaluation; rule-based object classification; scene understanding; Computer vision; Decision trees; Labeling; Layout; Logic programming; Machine learning; Object detection; Object recognition; Pattern recognition; Signal generators;
  • fLanguage
    English
  • Journal_Title
    Pattern Analysis and Machine Intelligence, IEEE Transactions on
  • Publisher
    ieee
  • ISSN
    0162-8828
  • Type

    jour

  • DOI
    10.1109/34.632987
  • Filename
    632987