• DocumentCode
    2768900
  • Title

    A Comparison of 2D Moment Based Description Techniques for Classification of Bamboo Plant

  • Author

    Singh, Krishna ; Gupta, Indra ; Gupta, Sangeeta

  • Author_Institution
    Dept. of Electr. Eng., Indian Inst. of Technol. Roorkee, Roorkee, India
  • fYear
    2011
  • fDate
    7-9 Oct. 2011
  • Firstpage
    15
  • Lastpage
    20
  • Abstract
    Generic Fourier descriptor yield spectral features and have better retrieval performance due to multi-resolution analysis in both radial and circular directions of the shape. In the proposed work, an automated bamboo species recognition system based on shape features of bamboo culm sheath has been developed using Generic Fourier Moment and compare the result with Hu moment. The performance of the classifier is compared based on the classifier accuracy and conclude that the Fourier moment have significantly good results compare to Hu moment. The results obtained shows considerable recognition accuracy proving that the techniques used is suitable to be implemented for commercial purposes.
  • Keywords
    Fourier analysis; feature extraction; image classification; image resolution; image retrieval; object recognition; 2D moment based description techniques; Hu moment; automated bamboo species recognition system; bamboo culm sheath; bamboo plant classification; generic Fourier descriptor; generic Fourier moment; multiresolution analysis; retrieval performance; Accuracy; Image color analysis; Image recognition; Pattern recognition; Reliability; Shape; Vectors; Hu moment; confusion matrix; culm sheath; generic Fourier moment;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computational Intelligence and Communication Networks (CICN), 2011 International Conference on
  • Conference_Location
    Gwalior
  • Print_ISBN
    978-1-4577-2033-8
  • Type

    conf

  • DOI
    10.1109/CICN.2011.4
  • Filename
    6112819