Generalization to Novel Images in Upright and Inverted Faces
| Abstract | An image of a face depends not only on its shape, but also on the viewpoint, illumination conditions, and facial expression. A face recognition system must overcome the changes in face appearance induced by these factors. This paper investigate two related questions: the capacity of the human visual system to generalize the recognition of faces to novel images, and the level at which this generalization occurs. We approach this problems by comparing the identi cation and generalization capacity for upright and inverted faces. For upright faces, we found remarkably good generalization to novel conditions. For inverted faces, the generalization to novel views was signi cantly worse for both new illumination and viewpoint, although the performance on the training images was similar to the upright condition. Our results indicate that at least some of the processes that support generalization across viewpoint and illumination are neither universal (because subjects did not generalize as easily for inverted faces as for upright ones), nor strictly objectspeci c (because in upright faces nearly perfect generalization was possible from a single view, by itself insu cient for building a complete object-speci c model). We propose that generalization in face recognition occurs at an intermediate level that is applicable to a class of objects, and that at this level upright and inverted faces initially constitute distinct object classes. | |||||||||
| Keywords | No keywords specified (fix it) | |||||||||
| Categories | No categories specified (fix it) | |||||||||
| Options |
|
|||||||||
Download options| PhilPapers Archive |
Upload a copy of this paper Check publisher's policy on self-archival Papers currently archived: 5,875 |
| External links |
  Try with proxy. Try with proxy. |
| Through your library | Only published papers are available at libraries |
Similar books and articlesT. N. Davies & D. D. Hoffman (2003). Facial Attention and Spacetime Fragments. Axiomathes 13 (3-4):303-327.
Therese Davis (2004). The Face on the Screen: Death, Recognition and Spectatorship. Intellect Books.
Susan Bredlau (2011). Monstrous Faces and a World Transformed: Merleau-Ponty, Dolezal, and the Enactive Approach on Vision Without Inversion of the Retinal Image. Phenomenology and the Cognitive Sciences 10 (4):481-498.
Hagi Kenaan (2011). Facing Images. Angelaki 16 (1):143 - 159.
David Keyt (2007). The Good Man and the Upright Citizen in Aristotle's Ethics and Politics. Social Philosophy and Policy 24 (2):220-240.
Rankin W. McGugin, James W. Tanaka, Sophie Lebrecht, Michael J. Tarr & Isabel Gauthier (2011). Race-Specific Perceptual Discrimination Improvement Following Short Individuation Training With Faces. Cognitive Science 35 (2):330-347.
Douglas Walton (1999). Rethinking the Fallacy of Hasty Generalization. Argumentation 13 (2):161-182.
Carlo Cellucci (2009). The Universal Generalization Problem. Logique and Analyse 52 (205):3-20.
Mariko Moher, Lisa Feigenson & Justin Halberda (2010). A One-to-One Bias and Fast Mapping Support Preschoolers' Learning About Faces and Voices. Cognitive Science 34 (5):719-751.
Dwayne Moore (2010). The Generalization Problem and the Identity Solution. Erkenntnis 72 (1):57 - 72.
Analytics
Monthly downloads |
Added to index2010-12-22Total downloads2 ( #234,650 of 556,837 )Recent downloads (6 months)1 ( #64,847 of 556,837 )How can I increase my downloads? |
My notes
Discussion
