An empirical study on the effectiveness of hyperspectral image classification algorithms with dimensionality reduction

Authors:
Yang Zhang;Mojia Sun;Chih-Cheng Hung;Edward Jung
Affiliations:
Southern Polytechnic State University, Marietta, GA;Southern Polytechnic State University, Marietta, GA;Southern Polytechnic State University, Marietta, GA;Southern Polytechnic State University, Marietta, GA
Venue:
Proceedings of the 2011 ACM Symposium on Research in Applied Computation
Year:
2011

Citing 5
Cited 0

Fuzzy clustering using scatter matrices

Computational Statistics & Data Analysis - Special issue on classification
Remote Sensing: Digital Image Analysis

Remote Sensing: Digital Image Analysis
Pattern Recognition with Fuzzy Objective Function Algorithms

Pattern Recognition with Fuzzy Objective Function Algorithms
When Is ''Nearest Neighbor'' Meaningful?

ICDT '99 Proceedings of the 7th International Conference on Database Theory
A generalized maximum entropy approach to bregman co-clustering and matrix approximation

Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this study, we explore the effectiveness of some recently developed image classification algorithms on reduced hyperspectral images. The nonparametric weighted feature extraction (NWFE) and principal component analysis (PCA) are used for dimensionality reduction on hyperspectral images. The fuzzy Weighted C-Means algorithm (FWCM) and new weighted fuzzy C-Means algorithm (NW-FCM) which newly devloped are tested for image classification on lower dimensional datasets. The results of fuzzy C-Means algorithm (FCM) also impelemted for the comparison. Preliminary experimental results show that the dimension reduction methods can affect the accuracy of classifying the hyperspectral datasets.