• DocumentCode
    2748138
  • Title

    An Improved BP Network Classifier Based on VPRS Feature Reduction

  • Author

    Li, Mengxin ; Wu, Chengdong ; Zhang, Ying ; Yue, Yong

  • Author_Institution
    Sch. of Inf. & Control Eng., Shenyang Jianzhu Univ.
  • Volume
    2
  • fYear
    0
  • fDate
    0-0 0
  • Firstpage
    9677
  • Lastpage
    9680
  • Abstract
    Variable precision rough sets (VPRS), as a extension of rough sets (RS) is adopted to reduce the redundant features for its ability of more useful information adopted compared with RS. The reduced features after VPRS are fed into the improved BP network proposed to inspect the defects of surface quality, which results in short training time and a high classification accuracy with a typical application in defect inspection of wood veneer
  • Keywords
    backpropagation; computer vision; feature extraction; flaw detection; image classification; inspection; neural nets; rough set theory; backpropagation network classifier; defect inspection; image classification; redundant feature reduction; surface quality; variable precision rough sets; wood veneer; Computer networks; Control engineering; Data mining; Humans; Inspection; Production; Productivity; Rough sets; Rough surfaces; Surface roughness; An Improved BP Algorithm; Feature Reduction; VPRS; Wood Veneer;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Intelligent Control and Automation, 2006. WCICA 2006. The Sixth World Congress on
  • Conference_Location
    Dalian
  • Print_ISBN
    1-4244-0332-4
  • Type

    conf

  • DOI
    10.1109/WCICA.2006.1713881
  • Filename
    1713881