Clustering for HSI hyperspectral image with weighted PCA and ICA

Feature extraction from hyperspectral remote sensing data is an effective method for object classification, and how to classify the object information from hyperspectral remote sensing image has become one of the core technologies of the remote sensing application. Aiming at the characteristics of s...

Full description

Saved in:
Bibliographic Details
Published in:Journal of intelligent & fuzzy systems 2017-01, Vol.32 (5), p.3729-3737
Main Authors: Li, Cheng-Fan, Liu, Lan, Lei, Yong-Mei, Yin, Jing-Yuan, Zhao, Jun-juan, Sun, Xian-Kun
Format: Article
Language:English
Subjects:
Clustering
Detection
Eigenvectors
Feature extraction
Image classification
Image quality
Independent component analysis
Object recognition
Principal components analysis
Remote sensing
Similarity
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Feature extraction from hyperspectral remote sensing data is an effective method for object classification, and how to classify the object information from hyperspectral remote sensing image has become one of the core technologies of the remote sensing application. Aiming at the characteristics of space modulated interference hyperspectral image (HSI) hyperspectral remote sensing image, in this article a new remote sensing clustering method is presented on the basis of analyzing the principal component analysis (PCA) and independent component analysis (ICA), which is able both to extract data’s independent features in terms on the second-order statistics and higher-order statistical information. The proposed method classifies the HSI hyperspectral remote sensing image better than the traditional methods. Firstly, the definition of the feature weighting between PCA and ICA is used in order to calculate the weighted value. Then, similarity measure contains distance similarity and cosine similarity is introduced. Finally, the recognition rule is constructed to classify the hyperspectral remote sensing image. The true HSI hyperspectral remote sensing is used to evaluate the performance of our method. Experimental results indicate that the proposed clustering method outperforms traditional classification methods, and the classification accuracy reaches to 85% under certain conditions with the suitable number of eigenvectors is 12 and weighted values is 0.8. Meanwhile, the image quality of our method is well preserved.
ISSN:1064-1246
1875-8967
DOI:10.3233/JIFS-169305