World Library  


Add to Book Shelf
Flag as Inappropriate
Email this Book

A Modified Stochastic Neighbor Embedding for Combining Multiple Features for Remote Sensing Image Classification : Volume I-3, Issue 1 (23/07/2012)

By Zhang, L.

Click here to view

Book Id: WPLBN0004013626
Format Type: PDF Article :
File Size: Pages 4
Reproduction Date: 2015

Title: A Modified Stochastic Neighbor Embedding for Combining Multiple Features for Remote Sensing Image Classification : Volume I-3, Issue 1 (23/07/2012)  
Author: Zhang, L.
Volume: Vol. I-3, Issue 1
Language: English
Subject: Science, Isprs, Annals
Collections: Periodicals: Journal and Magazine Collection, Copernicus GmbH
Historic
Publication Date:
2012
Publisher: Copernicus Gmbh, Göttingen, Germany
Member Page: Copernicus Publications

Citation

APA MLA Chicago

Huang, X., Zhang, L., Tao, D., & Zhang, L. (2012). A Modified Stochastic Neighbor Embedding for Combining Multiple Features for Remote Sensing Image Classification : Volume I-3, Issue 1 (23/07/2012). Retrieved from http://www.ebooklibrary.org/


Description
Description: The State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan 430079, China. In remote sensing image interpretation, it is important to combine multiple features of a certain pixel in both spatial and spectral domains to improve the classification accuracy, such as spectral signature, morphological property, and shape feature. Therefore, it is essential to consider the complementary property of different features and combine them in order to obtain an accurate classification rate. In this paper, we introduce a multi-feature dimension reduction algorithm under a probabilistic framework, modified stochastic neighbor embedding (MSNE). For each feature, a probability distribution is constructed based on SNE, and then we alternatively solve SNE and learn the optimal combination coefficients for different features in optimization. Compared with conventional dimension reduction strategies, the suggested algorithm can considers spectral, morphological and shape features of a pixel to achieve a physically meaningful low-dimensional feature representation by automatically learn a combination coefficient for each feature adapted to its contribution to subsequent classification. In experimental section, classification results using hyperspectral remote sensing image (HSI) show that this modified stochastic neighbor embedding can effectively improve classification performance.

Summary
A MODIFIED STOCHASTIC NEIGHBOR EMBEDDING FOR COMBINING MULTIPLE FEATURES FOR REMOTE SENSING IMAGE CLASSIFICATION

 

Click To View

Additional Books


  • Finding a Good Feature Detector-descript... (by )
  • Dense Corresponding Pixel Matching Using... (by )
  • On Data Acquisition of Moving Objects Vi... (by )
  • Real-time Object Detection, Tracking, an... (by )
  • Prototyping a Sensor Enabled 3D Citymode... (by )
  • Clustering Analysis of Officer's Behavio... (by )
  • Urban Object Extraction from Digital Sur... (by )
  • Incorporating Uncertanity Into Markov Ra... (by )
  • Towards Automatic Indoor Reconstruction ... (by )
  • Ontological Standardization for Historic... (by )
  • An Approach to Develop 3D Geo-dbms Topol... (by )
  • Rigorous Strip Adjustment of Airborne La... (by )
Scroll Left
Scroll Right

 



Copyright © World Library Foundation. All rights reserved. eBooks from World eBook Library are sponsored by the World Library Foundation,
a 501c(4) Member's Support Non-Profit Organization, and is NOT affiliated with any governmental agency or department.