• DocumentCode
    3283556
  • Title

    An Adaptive Method for Region of Interest Identification in Images

  • Author

    Agili, Sedig ; Baskaran, Lakshmi P. ; Brinton, Gordon ; Morales, Aldo

  • Author_Institution
    Electr. Eng. Program, Penn State Univ. at Harrisburg, Middletown, PA
  • fYear
    2006
  • fDate
    22-24 March 2006
  • Firstpage
    761
  • Lastpage
    765
  • Abstract
    This paper presents an automatic region of interest (ROI) generation algorithm for images, where the information provided by the wavelets decomposition is re-used to automatically cluster pixels according to their energy values. The clusters are found using the K-means algorithm and then classified as belonging to the ROI depending of their entropy. Results show the benefits of the algorithm.
  • Keywords
    adaptive signal processing; image coding; wavelet transforms; K-means algorithm; adaptive method; image ROI identification; region-of-interest generation algorithm; wavelets decomposition; Algorithm design and analysis; Clustering algorithms; Entropy; Frequency; Image analysis; Image coding; Image segmentation; Performance analysis; Pixel; Wavelet coefficients; Adaptive ROI identification; K-means; image compression; wavelets;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Information Sciences and Systems, 2006 40th Annual Conference on
  • Conference_Location
    Princeton, NJ
  • Print_ISBN
    1-4244-0349-9
  • Electronic_ISBN
    1-4244-0350-2
  • Type

    conf

  • DOI
    10.1109/CISS.2006.286568
  • Filename
    4067909