• DocumentCode
    2897915
  • Title

    Design for Robustness Contour Detection CNN

  • Author

    Li, Guo-dong ; Zhao, Zhen-Yu ; Chen, De-gang ; Ye, Zhen-jun

  • Author_Institution
    Sch. of Math. & Phys., North China Electr. Power Univ., Beijing
  • fYear
    2006
  • fDate
    13-16 Aug. 2006
  • Firstpage
    3721
  • Lastpage
    3724
  • Abstract
    The cellular neural nonlinear network (CNN) is a powerful tool for image and video signal processing, robotic and biological visions. This paper sets up a theorem to design robustness template CNN for contour detection in images, which provides parameter inequalities for determining parameter intervals for implementing the corresponding tasks. The contour CNN has successfully detected edges in three gray-scale images
  • Keywords
    cellular neural nets; edge detection; nonlinear functions; cellular neural nonlinear network; edge detection; gray-scale images; image contour detection; nonlinear function; parameter inequalities; parameter intervals; robustness template CNN design; Cellular neural networks; Cybernetics; Energy management; Gray-scale; Image edge detection; Machine learning; Mathematics; Object detection; Physics; Robot vision systems; Robustness; Roentgenium; Signal design; Cellular neural network; Contour detection; Gray-scale images; Template design;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Machine Learning and Cybernetics, 2006 International Conference on
  • Conference_Location
    Dalian, China
  • Print_ISBN
    1-4244-0061-9
  • Type

    conf

  • DOI
    10.1109/ICMLC.2006.258633
  • Filename
    4028717