Abstract
An often noted limitation of computational models of faces operating on two-dimensional pixel intensity representations is that they cannot handle changes in orientation. We show that this limitation can be overcome by the use of multiple views of a given face instead of a single view to represent the face. Specifically, we show that a linear autoassociator trained to reconstruct multiple views of a set of faces is able to recognize the faces from new view angles. An analysis of the internal representation of the memory (i.e., eigenvectors of the between-unit-connection weight matrix) shows a dissociation between two kinds of perceptual information: orientation and identity information.
© 1996 Optical Society of America
Full Article | PDF ArticleMore Like This
A. J. O’Toole, H. Abdi, K. A. Deffenbacher, and D. Valentin
J. Opt. Soc. Am. A 10(3) 405-411 (1993)
Abhijith Punnappurath and Ambasamudram Narayanan Rajagopalan
J. Opt. Soc. Am. A 33(9) 1887-1900 (2016)
Kamran Etemad and Rama Chellappa
J. Opt. Soc. Am. A 14(8) 1724-1733 (1997)