June 2004
Volume 4, Issue 8
Vision Sciences Society Annual Meeting Abstract  |   August 2004
Learning and recognition task performance using computer generated facial illustrations and caricatures.
Author Affiliations
  • Bruce S. Gooch
    Northwestern University, USA
  • Sarah Creem-Regehr
    University of Utah, USA
  • Jim Lee
    Medical Imaging Research Laboratory, USA
  • Erik Reinhard
    University of Central Florida, USA
Journal of Vision August 2004, Vol.4, 430. doi:https://doi.org/10.1167/4.8.430
  • Views
  • Share
  • Tools
    • Alerts
      This feature is available to authenticated users only.
      Sign In or Create an Account ×
    • Get Citation

      Bruce S. Gooch, Sarah Creem-Regehr, Jim Lee, Erik Reinhard; Learning and recognition task performance using computer generated facial illustrations and caricatures.. Journal of Vision 2004;4(8):430. doi: https://doi.org/10.1167/4.8.430.

      Download citation file:

      © ARVO (1962-2015); The Authors (2016-present)

  • Supplements

We present a method for creating black-and-white illustrations and caricatures of human faces from source photographs and a series of studies aimed at evaluating the effectiveness of the resulting images relative to photographs. The illustrations are generated by superimposing two images: a thresholded image of the output of a computational brightness model and a thresholded luminance image. In addition, a new interactive technique is demonstrated for deforming images of faces to create caricatures that highlight and exaggerate representative facial features. The photographs and black-and-white illustrations are evaluated to assess speed and accuracy in learning and recognition tasks. These studies show that the facial illustrations and caricatures generated using these techniques are as effective as photographs in the recognition tasks. In the learning studies, tasks involving illustrations or caricatures were performed significantly faster than the same tasks were performed with photographs used as stimulus. The hypothesis is: if the facial illustration and caricature algorithms do not affect the recognition speed and accuracy of familiar faces with respect to photographs, then the information reduction afforded by these algorithms is relatively benign and the resulting images can be substituted in tasks were recognition speed is paramount. To test this hypothesis, three studies were performed that are replications of earlier distinctiveness studies {Stevanage 95}. Although these previous studies assessed the effect of human drawn portraits and caricatures on recognition and learning speed, these same studies are used here to validate the computer-generated illustrations and caricaturing techniques. In addition, the computer generated illustrations and caricatures are compared with the source photographs in terms of recognition and learning speeds.

Gooch, B. S., Creem-Regehr, S., Lee, J., Reinhard, E.(2004). Learning and recognition task performance using computer generated facial illustrations and caricatures[Abstract]. Journal of Vision, 4( 8): 430, 430a, http://journalofvision.org/4/8/430/, doi:10.1167/4.8.430. [CrossRef]

This PDF is available to Subscribers Only

Sign in or purchase a subscription to access this content. ×

You must be signed into an individual account to use this feature.