Share Email Print

Proceedings Paper

Nonlinear discriminant analysis
Author(s): Hongbin Zhang; Eric Clarkson; Harrison H. Barrett
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We describe a new nonlinear discriminant analysis method for feature extraction. This method applies a nonsingular transform to the data such that the transformed data have a Gaussian distribution. Then a Bayes likelihood ratio is calculated for the transformed data. The nonsingular transform makes use of wavelet transforms and histogram matching techniques. Wavelet transforms are an effective tool in analyzing data structures. Histogram matching is applied to the wavelet coefficients and the ordinary image pixel values in order to create a transformed image that has the desired Gaussian statistics.

Paper Details

Date Published: 3 July 2001
PDF: 8 pages
Proc. SPIE 4322, Medical Imaging 2001: Image Processing, (3 July 2001); doi: 10.1117/12.431117
Show Author Affiliations
Hongbin Zhang, Univ. of Arizona (United States)
Eric Clarkson, Univ. of Arizona (United States)
Harrison H. Barrett, Univ. of Arizona and Optical Sciences Ctr./Univ. of Arizona (United States)

Published in SPIE Proceedings Vol. 4322:
Medical Imaging 2001: Image Processing
Milan Sonka; Kenneth M. Hanson, Editor(s)

© SPIE. Terms of Use
Back to Top