Influence of the amount of context learned for improving object classification when simultaneously learning object and contextual cues.

Humans use visual context to improve object recognition. Yet, many machine vision algorithms still focus on local object features, discarding surrounding features as unwanted clutter. Here we study the impact of learning contextual cues while training an object classifier. In a new image database wi...

Descripción completa

Detalles Bibliográficos
Publicado en:Visual Cognition Vol. 20; no. 4/5; pp. 580 - 603
Autores principales: Marat, Sophie, Itti, Laurent
Formato: Journal Article
Publicado: Taylor & Francis Ltd Apr2012
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=75527967&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 75527967
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        13506285
        BE5
      jtl: Visual Cognition
      issn: 13506285
      maglogo: N
    pubinfo:
      dt: Apr2012
      vid: 20
      iid: 4/5
      pid: 377
      pub: Taylor & Francis Ltd
      place: Philadelphia, Pennsylvania
    artinfo:
      ui:
        75527967
        10.1080/13506285.2012.667007
        75527967
      ppf: 580
      ppct: 23
      formats:
      tig:
        atl: Influence of the amount of context learned for improving object classification when simultaneously learning object and contextual cues.
      aug:
        au:
          Marat, Sophie
          Itti, Laurent
        affil: Department of Computer Science, University of Southern California, Los Angeles, CA, USA
      sug:
      ab: Humans use visual context to improve object recognition. Yet, many machine vision algorithms still focus on local object features, discarding surrounding features as unwanted clutter. Here we study the impact of learning contextual cues while training an object classifier. In a new image database with 10 object categories and 28,800 images, objects were presented in contextual or uniform backgrounds. Both the fraction of contextual backgrounds during training and the spatial extent of context were analysed. Local object features and broader context features were extracted by two biologically inspired algorithms, previously used for object and scene classification, respectively: HMAX, applied to a tight window around every object, and a “Gist” algorithm, applied to a larger yet still localized window. The descriptors from both algorithms were combined and processed by a Support Vector Machine. The recognition rate increased from 29%, without contextual cues, to 43% for objects presented in their context.
      pubtype: Academic Journal
      doctype: Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N