A Novel Algorithm for Hyperspectral Image Denoising in Medical Application.

The one of the preprocessing step for hyperspectral imagery is noise reduction. The images are received by the detector and this can be degraded by several factors like atmospherical things and device noises which emit temperature noise, processing noise and explosion noise. There are several strate...

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of Medical Systems Vol. 43; no. 9
Autores principales: Nageswaran, Kirubanandasarathy, Nagarajan, Karthikeyan, Bandiya, Ramasubramanian
Formato: algorithm equations & formulas pictorial research tables/charts Journal Article
Publicado: Springer Nature Sep2019
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=138200099&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 138200099
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        01485598
        4N0
      jtl: Journal of Medical Systems
      issn: 01485598
      maglogo: N
    pubinfo:
      dt: Sep2019
      vid: 43
      iid: 9
      pid: 237
      pub: Springer Nature
      place: New York, New York
    artinfo:
      ui:
        138200099
        138200099
        138200099
        10.1007/s10916-019-1403-5
        138200099
      ppct: 1
      formats:
        fmt:
          – @attributes:
              type: T
          – @attributes:
              type: P
      tig:
        atl: A Novel Algorithm for Hyperspectral Image Denoising in Medical Application.
      aug:
        au:
          Nageswaran, Kirubanandasarathy
          Nagarajan, Karthikeyan
          Bandiya, Ramasubramanian
        affil: Department of Electronics & Communication Engineering, Syed Ammal Engineering College, 623 502, Ramanathapuram, India
      sug:
        subj:
          Algorithms
          Image Processing, Computer Assisted Methods
          Signal Processing, Computer Assisted Methods
          Diagnostic Imaging
          Noise Prevention and Control
          Conceptual Framework
          Hypersensitivity Diagnosis
          Skin Diseases Diagnosis
          Diabetes Mellitus Diagnosis
          Retinal Diseases Diagnosis
          Multiple Linear Regression
          Human
          Descriptive Statistics
      ab: The one of the preprocessing step for hyperspectral imagery is noise reduction. The images are received by the detector and this can be degraded by several factors like atmospherical things and device noises which emit temperature noise, processing noise and explosion noise. There are several strategies are developed already to cut back the signal to noise magnitude relation of the hyperspectral image. However, the stationary noise of the many denoising ways developed cannot be applied on to the gauge boson noise. Thus, the each gauge boson and thermal noise square measure gift within the captured hyperspectral image (HSI). during this paper, we tend to projected a replacement denoising framework known as tensor-based filtering employing a PARAFAC tensor decomposition methodology for scale back each noise. The proposed technique is performs higher in removing noise as compared with different strategies like Multiple linear regression (MLR) algorithm and combined algorithm called multidimensional wavelet transforms with multiway wiener filter (MWPT-MWF) technique. The performance analysis of the new denoising framework has more efficient for reducing signal dependent (PN) and signal independent noise (TN) as compared with other conventional method. Hence this novel denoising approach would be more beneficial for detection of skin allergy and also this algorithm will be very useful for detection of retinal exudates and diagnosis of diabetes mellitus and retinopathy disease in medical application.
      pubtype: Academic Journal
      doctype:
        algorithm
        equations & formulas
        pictorial
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N