• DocumentCode
    2835893
  • Title

    Method for Automatic Counting Root Nodules Using Digital Images

  • Author

    Barbedo, Jayme Garcia Arnal

  • Author_Institution
    Embrapa Inf. Agropecuaria, Campinas, Brazil
  • fYear
    2012
  • fDate
    18-21 June 2012
  • Firstpage
    159
  • Lastpage
    161
  • Abstract
    This paper presents a method to automatically count nodules that are present in the roots of many legume plants, using digital images captured after the nodules have been removed from the roots. This problem poses a significant challenge due to a number of reasons: the size and shape of the nodules vary greatly, they may appear clustered, and their texture is not uniform. The proposed method exploits well-known morphological operations to discriminate each nodule, making the counting process possible. Tests reveal a good correlation between automatic and manual counting.
  • Keywords
    agriculture; image processing; image texture; object detection; automatic counting root nodule method; counting process; digital images; legume plants; manual counting; morphological operations; Algorithm design and analysis; Correlation; Digital images; Euclidean distance; Manuals; Software; Surface morphology; Digital Images; Object Counting; Root Nodules;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computational Science and Its Applications (ICCSA), 2012 12th International Conference on
  • Conference_Location
    Salvador
  • Print_ISBN
    978-1-4673-1691-0
  • Type

    conf

  • DOI
    10.1109/ICCSA.2012.39
  • Filename
    6257630