• DocumentCode
    2776393
  • Title

    Is High Resolution Representation More Effective for Content Based Image Classification?

  • Author

    Chen, Liang ; Tokuda, Naoyuki ; Nagai, Akira ; Chen, Xiaoyu

  • Author_Institution
    Northern British Columbia Univ., Prince George
  • fYear
    0
  • fDate
    0-0 0
  • Firstpage
    4045
  • Lastpage
    4050
  • Abstract
    This paper shows by a mathematical model that, for image classification/recognition purposes, high resolution pictures have lower recognition rate than relatively low resolution pictures. The analysis is based on the matching approach by a simple neural network, but we believe that the conclusion remains valid even when the classification process involves complicated matching schemes such as principal component analysis and Gabor transforms.
  • Keywords
    image classification; image matching; image representation; image resolution; neural nets; principal component analysis; transforms; Gabor transform; content based image classification; image matching; image recognition; image representation; image resolution; mathematical model; neural network; principal component analysis; Digital cameras; Face recognition; Humans; Image classification; Image recognition; Image resolution; Mathematical model; Multi-layer neural network; Neural networks; Pixel;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Neural Networks, 2006. IJCNN '06. International Joint Conference on
  • Conference_Location
    Vancouver, BC
  • Print_ISBN
    0-7803-9490-9
  • Type

    conf

  • DOI
    10.1109/IJCNN.2006.246928
  • Filename
    1716656