Research the Algorithm of Image Classification Based on Gaussian Mixture Model

DOI

10.2991/cisia-15.2015.180How to use a DOI?

Keywords

GMM; EM; image classification

Abstract

Remote sensing image is according to a certain proportion of objective record and reflect electromagnetic radiation of earth surface intensity information, is a form of expression we obtain the remote sensing information. With the development of remote sensing technology, remote sensing image classification is more and more important, and in recent years also appeared some new methods for the classification of remote sensing image. This paper introduces and realizes an unsupervised learning method, an algorithm of imageclassification based on Gaussian mixture model. When solving this model, find that the function is too complex to direct derivation, so we introduce the EM algorithm to solve it. This paper gives the detailed process of EM algorithm, explains the geometric significance of EM algorithm, and provesits convergence, and realizes the EM algorithm for Gaussian mixture model. The image of this experiment is nearby Beijing airport Results show the algorithms’applicability and effectiveness.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Z. Meng
AU  - G.Q Yao
PY  - 2015/06
DA  - 2015/06
TI  - Research the Algorithm of Image Classification Based on Gaussian Mixture Model
BT  - Proceedings of the International Conference on Computer Information Systems and Industrial Applications
PB  - Atlantis Press
SP  - 659
EP  - 662
SN  - 2352-538X
UR  - https://doi.org/10.2991/cisia-15.2015.180
DO  - 10.2991/cisia-15.2015.180
ID  - Meng2015/06
ER  -