Share Email Print
cover

Proceedings Paper

Independent component representations for face recognition
Author(s): Marian Stewart Bartlett; Martin H. Lades; Terrence J. Sejnowski
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In a task such as face recognition, much of the important information may be contained in the high-order relationships among the image pixels. A number of face recognition algorithms employ principal component analysis (PCA), which is based on the second-order statistics of the image set, and does not address high-order statistical dependencies such as the relationships among three or more pixels. Independent component analysis (ICA) is a generalization of PCA which separates the high-order moments of the input in addition to the second-order moments. ICA was performed on a set of face images by an unsupervised learning algorithm derived from the principle of optimal information transfer through sigmoidal neurons. The algorithm maximizes the mutual information between the input and the output, which produces statistically independent outputs under certain conditions. ICA was performed on the face images under two different architectures. The first architecture provided a statistically independent basis set for the face images that can be viewed as a set of independent facial features. The second architecture provided a factorial code, in which the probability of any combination of features can be obtained from the product of their individual probabilities. Both ICA representations were superior to representations based on principal components analysis for recognizing faces across sessions and changes in expression.

Paper Details

Date Published: 17 July 1998
PDF: 12 pages
Proc. SPIE 3299, Human Vision and Electronic Imaging III, (17 July 1998); doi: 10.1117/12.320144
Show Author Affiliations
Marian Stewart Bartlett, Univ. of California/San Diego and The Salk Institute (United States)
Martin H. Lades, Verdant Technologies (United States)
Terrence J. Sejnowski, Univ. of California/San Diego and The Salk Institute (United States)


Published in SPIE Proceedings Vol. 3299:
Human Vision and Electronic Imaging III
Bernice E. Rogowitz; Thrasyvoulos N. Pappas, Editor(s)

© SPIE. Terms of Use
Back to Top