Two-dimensional random projection

Please enable javascript in your browser.

Eftekhari, A ; Sharif University of Technology | 2011

854 Viewed

Type of Document: Article
DOI: 10.1016/j.sigpro.2011.01.002
Publisher: 2011
Abstract:
As an alternative to adaptive nonlinear schemes for dimensionality reduction, linear random projection has recently proved to be a reliable means for high-dimensional data processing. Widespread application of conventional random projection in the context of image analysis is, however, mainly impeded by excessive computational and memory requirements. In this paper, a two-dimensional random projection scheme is considered as a remedy to this problem, and the associated key notion of concentration of measure is closely studied. It is then applied in the contexts of image classification and sparse image reconstruction. Finally, theoretical results are validated within a comprehensive set of experiments with synthetic and real images
Keywords:
Concentration of measure ; Dimensionality reduction ; High dimensional data ; Memory requirements ; Random projection ; Random projections ; Real images ; Sparse signal reconstruction ; Theoretical result ; Data handling ; Image analysis ; Image reconstruction ; Signal analysis ; Two dimensional
Source: Signal Processing ; Volume 91, Issue 7 , 2011 , Pages 1589-1603 ; 01651684 (ISSN)
URL: http://www.sciencedirect.com/science/article/pii/S016516841100003X