• DocumentCode
    3237870
  • Title

    The algorithm of image representation and reconstruction based on compressed sensing with composite measurement

  • Author

    Yingbiao Jia ; Feng, Yan ; Yuming Cao ; Changsheng Dou

  • Author_Institution
    Sch. of Electron. & Inf., Northwestern Polytech. Univ., Xi´´an, China
  • fYear
    2011
  • fDate
    27-29 May 2011
  • Firstpage
    404
  • Lastpage
    407
  • Abstract
    Compressed sensing (CS) technology has been shown to be able to reduce the amount of sampled data effectively. In this paper, an algorithm of image representation and reconstruction is proposed based on compressed sensing with composite measurement. Being transformed into the wavelet domain, composite observations could be handled according to the distribution properties of the image wavelet domain representation, which means the wavelet coefficients components could be divided into one dense component and a number of sparse components, and different component can be measured with different noiselet observations. In the image reconstruction process, due to the measurement relation between the original image and the observations is established, we can use the total variation minimization method to reconstruct the original image. Experimental results demonstrate that the proposed algorithm is competitive to the existed similar algorithms with higher quality of image reconstruction.
  • Keywords
    image reconstruction; image representation; wavelet transforms; composite measurement; compressed sensing; image reconstruction; image wavelet domain representation; noiselet observation; total variation minimization method; wavelet coefficient components; wavelet transform; Boats; Discrete wavelet transforms; Image coding; Image reconstruction; TV; Composite Measurement; Compressed Sensing; Noiselet; Total Variation Minimization;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Communication Software and Networks (ICCSN), 2011 IEEE 3rd International Conference on
  • Conference_Location
    Xi´an
  • Print_ISBN
    978-1-61284-485-5
  • Type

    conf

  • DOI
    10.1109/ICCSN.2011.6014595
  • Filename
    6014595