Share Email Print
cover

Proceedings Paper

Sequential principal component analysis
Author(s): Charles Hsu; Harold Szu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The Principal Component Analysis (PCA) is an optimal method for approximating a set of vectors or images, which was used in image processing and computer vision for a number of tasks including face and object recognition. The computational complexity and its batch calculation nature have limited its applications. Here we discuss the two different effective solutions to sequentially calculate the principal bases in terms of the eigenvectors with respective eigenvalues using the covariance (or covariance estimate), which is faster in typical applications and is especially advantageous for image sequences. This principal component basis calculation is processed with much lower delay and allows for dynamic updating of image databases.

Paper Details

Date Published: 8 June 2011
PDF: 6 pages
Proc. SPIE 8058, Independent Component Analyses, Wavelets, Neural Networks, Biosystems, and Nanoengineering IX, 80580S (8 June 2011); doi: 10.1117/12.887509
Show Author Affiliations
Charles Hsu, Trident Systems Inc. (United States)
Harold Szu, U.S. Army Night Vision & Electronic Sensors Directorate (United States)


Published in SPIE Proceedings Vol. 8058:
Independent Component Analyses, Wavelets, Neural Networks, Biosystems, and Nanoengineering IX
Harold Szu, Editor(s)

© SPIE. Terms of Use
Back to Top