Viewpoint generalization in face recognition: The role of category-speci c processes

The statistical structure of a class of objects such as human faces can be exploited to recognize familiar faces from novel viewpoints and under variable illumination conditions. We present computational and psychophysical data concerning the extent to which class-based learning transfers or generalizes within the class of faces. We rst examine the computational prerequisite for generalization across views of novel faces, namely, the similarity of di erent faces to each other. We next describe two computational models which exploit the similarity structure of the class of faces. The performance of these models constrains hypotheses about the nature of face representation in human vision, and supports the notion that human face processing operates in a class-based fashion. Finally, we relate the computational data to well-established ndings in the human memory literature concerning the relationship between the typicality and recognizability of faces.
Keywords No keywords specified (fix it)
Categories No categories specified
(categorize this paper)
 Save to my reading list
Follow the author(s)
My bibliography
Export citation
Find it on Scholar
Edit this record
Mark as duplicate
Revision history Request removal from index Translate to english
Download options
PhilPapers Archive

Upload a copy of this paper     Check publisher's policy on self-archival     Papers currently archived: 9,360
External links
  •   Try with proxy.
  •   Try with proxy.
  • Through your library Only published papers are available at libraries
    References found in this work BETA

    No references found.

    Citations of this work BETA

    No citations found.

    Similar books and articles
    Tang Yijie & Yan Xin (2008). The Contemporary Significance of Confucianism. Frontiers of Philosophy in China 3 (4):477 - 501.

    Monthly downloads

    Added to index


    Total downloads

    2 ( #258,346 of 1,089,062 )

    Recent downloads (6 months)

    1 ( #69,801 of 1,089,062 )

    How can I increase my downloads?

    My notes
    Sign in to use this feature

    Start a new thread
    There  are no threads in this forum
    Nothing in this forum yet.