Share Email Print

Proceedings Paper

Optimal feature extraction for normally distributed data
Author(s): Chulhee Lee; Euisun Choi; Jaehong Kim
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper, we propose an optimal feature extraction method for normally distributed data. The feature extraction algorithm is optimal in the sense that we search the whole feature space to find a set of features which give the smallest classification error for the Gaussian ML classifier. Initially, we start with an arbitrary feature vector. Assuming that the feature vector is used for classification, we compute the classification error. Then we move the feature vector slightly in the direction so that the classification error decreases most rapidly. This can be done by taking gradient. We propose two search methods, sequential search and global search. In the sequential search, if more features are needed, we try to find an additional feature which gives the best classification accuracy with the already chosen features. In the global search, we are not restricted to use the already chosen features. Experiment results show that the proposed method outperforms the conventional feature extraction algorithms.

Paper Details

Date Published: 2 July 1998
PDF: 10 pages
Proc. SPIE 3372, Algorithms for Multispectral and Hyperspectral Imagery IV, (2 July 1998); doi: 10.1117/12.312603
Show Author Affiliations
Chulhee Lee, Yonsei Univ. (South Korea)
Euisun Choi, Yonsei Univ. (South Korea)
Jaehong Kim, Yonsei Univ. (South Korea)

Published in SPIE Proceedings Vol. 3372:
Algorithms for Multispectral and Hyperspectral Imagery IV
Sylvia S. Shen; Michael R. Descour, Editor(s)

© SPIE. Terms of Use
Back to Top