Teaching Computers with Illusions.

The article focuses on the need to teach computers how to improve their image recognition. It discusses how humans and computers see visual images differently, highlighting the ability of the human brain to interpret motion even there is no actual motion in the image. The failure of machine vision t...

Descripción completa

Detalles Bibliográficos
Publicado en:Communications of the ACM Vol. 58; no. 8; pp. 13 - 16
Autor principal: Shein, Esther
Formato: Artículo
Publicado: Association for Computing Machinery Aug2015
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=108508388&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 108508388
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00010782
        ACM
      jtl: Communications of the ACM
      issn: 00010782
      maglogo: N
    pubinfo:
      dt: Aug2015
      vid: 58
      iid: 8
      pid: 68
      pub: Association for Computing Machinery
    artinfo:
      ui:
        108508388
        10.1145/2788451
      ppf: 13
      ppct: 3
      formats:
      tig:
        atl: Teaching Computers with Illusions.
      aug:
        au: Shein, Esther
      su:
        Image recognition (Computer vision)
        Sensory perception
        Brain
        Computer vision
        Human behavior
        Algorithms
        Computer system failures
        Robots
      sug:
        subj:
          Image recognition (Computer vision)
          Sensory perception
          Brain
          Computer vision
          Human behavior
          Algorithms
          Computer system failures
          Robots
      ab: The article focuses on the need to teach computers how to improve their image recognition. It discusses how humans and computers see visual images differently, highlighting the ability of the human brain to interpret motion even there is no actual motion in the image. The failure of machine vision to recognize behavioral success is explained. In addition, the article mentions different methods that can be used to deceive computer algorithms and the failure of robots when they encounter images that are too different.
      pubtype: Periodical
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      dt:
        @attributes:
          year: 2015
    holdings:
      @attributes:
        islocal: N