Method for Classification of Remote Sensing Images Based on Multiple Classifiers Combination

Li Jun Shi; Xian Cheng Mao; Zheng Lin Peng

doi:10.4028/www.scientific.net/AMM.263-266.2561

Paper Titles

Research and Analysis of Edge-Detection of Digital Images
p.2538

Automatic White Balance Based on Gaussian Decomposition
p.2542

An Efficient and Fast Iris Location Algorithm
p.2549

Lanna Handwritten Character Recognition on Historical Documents Using Feature Extraction
p.2553

Method for Classification of Remote Sensing Images Based on Multiple Classifiers Combination
p.2561

Phased Array Radar Signal Recognition Method Based on Ant Colony Optimization and SVM
p.2566

Recogniton of a Target under Non-Uniform Illumination and Noisy Conditions
p.2570

The SAS Image Data Classification with Minimum Error Probability Bayes Classifier
p.2576

A Statistical Method Based on the Image of the Ore Partical Size Distribution
p.2581

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 263-266Method for Classification of Remote Sensing Images...

Method for Classification of Remote Sensing Images Based on Multiple Classifiers Combination

Abstract:

This paper presents a new method for classification of remote sensing image based on multiple classifiers combination. In this method, three supervised classifications such as Mahalanobis Distance, Maximum Likelihood and SVM are selected to sever as the sub-classifications. The simple vote classification, maximum probability category method and fuzzy integral method are combined together according to certain rules. And adopted color infrared aerial images of Huairen country as the experimental object. The results show that the overall classification accuracy was improved by 12% and Kappa coefficient was increased by 0.12 compared with SVM classification which has the highest accuracy in single sub-classifications.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 263-266)

Pages:

2561-2565

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.263-266.2561

Citation:

Cite this paper

Online since:

December 2012

Authors:

Li Jun Shi, Xian Cheng Mao, Zheng Lin Peng

Keywords:

IDL, Land Use, Multiple Classifier, Remote Sensing Classification

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] MA Wen-si: A study of pattern recognition based on multiple classifier fusion (Xidian University, China 2002). (in Chinese)

Google Scholar

[2] HAN Hong: Classifier Combination and its application in handwritten numeral recognition (Nanjing University of Science and Technology, China 2000). (in Chinese)

Google Scholar

[3] LU Yue, SHI Peng-fei and ZHAO Yu-ming: Journal of Shanghai Jiaotong University. Forum Vol. 34-5 (2000), pp.680-683 (in Chinese)

Google Scholar

[4] ZHOU Yi and JING Feng-guang: Urban Geotechnical Investigation and Surveying. Forum Vol. 2(2008), pp.56-59 (in Chinese)

Google Scholar

[5] CHEN Zhong: The research of high resolution remote sensing image classification technology (Beijing: Graduate University of Chinese Academy of Sciences, China 2006). (in Chinese)

Google Scholar

[6] PAN Quan, YU Xin and CHENG Yong-mei: Acta Automatica Sinica. Forum Vol. 29-4(2003), pp.599-615 (in Chinese)

Google Scholar

[7] HAN Hong and YANG Jing-yu: Computer Science. Forum Vol. 27-1(2000), pp.58-61 (in Chinese)

Google Scholar