Dimensionality reduction and visualisation of hyperspectral ink data using t-SNE.

Ink analysis is an important tool in forensic science and document analysis. Hyperspectral imaging (HSI) captures large number of narrowband images across the electromagnetic spectrum. HSI is one of the non-invasive tools used in forensic document analysis, especially for ink analysis. The substanti...

Full description

Bibliographic Details
Published in:Forensic Science International Vol. 311
Main Authors: Melit Devassy, Binu, George, Sony
Format: Journal Article
Published: Elsevier B.V. Jun2020
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=143310010&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 143310010
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        03790738
        3L0
      jtl: Forensic Science International
      issn: 03790738
      maglogo: N
    pubinfo:
      dt: Jun2020
      vid: 311
      pid: 82545
      pub: Elsevier B.V.
      place: Philadelphia, Pennsylvania
    artinfo:
      ui:
        143310010
        143310010
        NLM32251968
        10.1016/j.forsciint.2020.110194
        NLM32251968
        143310010
      ppct: 1
      formats:
      tig:
        atl: Dimensionality reduction and visualisation of hyperspectral ink data using t-SNE.
      aug:
        au:
          Melit Devassy, Binu
          George, Sony
        affil: Department of Computer Science, Norwegian University of Science and Technology, Gjøvik, Norway
      sug:
      ab: Ink analysis is an important tool in forensic science and document analysis. Hyperspectral imaging (HSI) captures large number of narrowband images across the electromagnetic spectrum. HSI is one of the non-invasive tools used in forensic document analysis, especially for ink analysis. The substantial information from multiple bands in HSI images empowers us to make non-destructive diagnosis and identification of forensic evidence in questioned documents. The presence of numerous band information in HSI data makes processing and storing becomes a computationally challenging task. Therefore, dimensionality reduction and visualization play a vital role in HSI data processing to achieve efficient processing and effortless understanding of the data. In this paper, an advanced approach known as t-Distributed Stochastic Neighbor embedding (t-SNE) algorithm is introduced into the ink analysis problem. t-SNE extracts the non-linear similarity features between spectra to scale them into a lower dimension. This capability of the t-SNE algorithm for ink spectral data is verified visually and quantitatively, the two-dimensional data generated by the t-SNE showed a better visualization and a greater improvement in clustering quality in comparison with Principal Component Analysis (PCA).
      pubtype: Academic Journal
      doctype: Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N