• DocumentCode
    3338961
  • Title

    Detection of skin lesions using diffuse polarisation

  • Author

    Subramaniam, Nitya ; Saman, Gule ; Hancock, Edwin

  • Author_Institution
    Dept. of Comput. Sci., Univ. of York, York, UK
  • fYear
    2010
  • fDate
    26-29 Sept. 2010
  • Firstpage
    3021
  • Lastpage
    3024
  • Abstract
    This paper describes the use of polarisation information for surface inspection. We consider the problem of detecting regions of damage and disease in the skins of different types of fruit and vegetable. We commence by using moments to estimate the components of the polarisation image (mean-intensity, polarisation and phase) from images obtained with multiple polariser angles. Using the polarisation information and the Fresnel theory, we develop a characterisation of the surface reflectance based on spherical harmonic coefficients. We use the normalised cut method to segment surfaces into different regions depending on their surface reflectance properties. Experiments on samples of bruised fruit illustrate the practical utility of the method.
  • Keywords
    diseases; food products; image segmentation; image texture; light polarisation; polarisation; reflectivity; skin; Fresnel theory; diffuse polarisation; fruit; image polarisation; image texture analysis; multiple polariser angle; normalised cut method; skin disease; skin lesion detection; spherical harmonic coefficient; surface inspection; surface reflectance; surface segmentation; vegetable; Azimuth; Harmonic analysis; Image segmentation; Pixel; Refractive index; Skin; Surface morphology; Image region analysis; Image segmentation; Image texture analysis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image Processing (ICIP), 2010 17th IEEE International Conference on
  • Conference_Location
    Hong Kong
  • ISSN
    1522-4880
  • Print_ISBN
    978-1-4244-7992-4
  • Electronic_ISBN
    1522-4880
  • Type

    conf

  • DOI
    10.1109/ICIP.2010.5651786
  • Filename
    5651786