• Medientyp: E-Book
  • Titel: View-Based Recognition of Faces in Man and Machine : Re-Visiting Inter-Extra-Ortho
  • Beteiligte: Wallraven, Christian [Verfasser:in]; Schwaninger, Adrian [Sonstige Person, Familie und Körperschaft]; Schuhmacher, Sandra [Sonstige Person, Familie und Körperschaft]; Bülthoff, Heinrich H. [Sonstige Person, Familie und Körperschaft]
  • Erschienen: [S.l.]: SSRN, [2018]
  • Erschienen in: Computer Science Preprint Archive ; Vol. 2002, Issue 11, pp 64-73
  • Umfang: 1 Online-Ressource (10 p)
  • Sprache: Englisch
  • Entstehung:
  • Anmerkungen: Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments November 2002 erstellt
  • Beschreibung: For humans, faces are highly overlearned stimuli, which are encountered in everyday life in all kinds of poses and views. Using psychophysics we investigated the effects of viewpoint on human face recognition. The experimental paradigm is modeled after the inter-extra-ortho experiment using unfamiliar objects by Bülthoff and Edelman [5]. Our results show a strong viewpoint effect for face recognition, which replicates the earlier findings and provides important insights into the biological plausibility of view-based recognition approaches (alignment of a 3D model, linear combination of 2D views and view-interpolation). We then compared human recognition performance to a novel computational view-based approach [29] and discuss improvements of view-based algorithms using local part-based information
  • Zugangsstatus: Freier Zugang