Title :
A comparative analysis of mutual information based feature selection for hyperspectral image classification
Author :
Yuanyuan Fu ; Xiuping Jia ; Wenjiang Huang ; Jihua Wang
Author_Institution :
Inst. of Appl. Remote Sensing & Inf. Technol., Zhejiang Univ., Hangzhou, China
Abstract :
Feature selection is an important task for hyperspectral imagery classification and becomes more critical for the emerging big data analysis. Selection criteria based on mutual information theory have the advantages in terms of distribution free, nonlinearity and low computational load for multiclass cases. However several have been developed and are available to use. In this study, we conduct a comparative analysis on four defined criteria and their performances are evaluated using two hyperspectral data sets with two levels of sample sizes.
Keywords :
Big Data; feature selection; hyperspectral imaging; image classification; Big Data analysis; hyperspectral data sets; hyperspectral image classification; mutual information based feature selection; Accuracy; Educational institutions; Hyperspectral imaging; Mutual information; Training; classification; feature selection; hyperspectral image; mutual information;
Conference_Titel :
Signal and Information Processing (ChinaSIP), 2014 IEEE China Summit & International Conference on
Conference_Location :
Xi´an
Print_ISBN :
978-1-4799-5401-8
DOI :
10.1109/ChinaSIP.2014.6889220
