By Topic

The Research of Satellite Cloud Image Recognition Base on Variational Method and Texture Feature Analysis

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

4 Author(s)
Wei Shangguan ; School of Automation, Harbin Engineering University, Harbin, 150001, China ; Yanling Hao ; Zhizhong Lu ; Peng Wu

Recently, the development of satellite cloud image processing technology has become very quick; the research aspects concentrate on judge the cloud type and classify the cloud mainly. These image processing methods relate to the subject category like image processing and pattern recognition etc; it has become one of the fields of most quickly development in the research of satellite image processing technology. In satellite cloud image, texture is an very important feature, since satellite cloud image has clear texture structure, the computer texture analysis provide perfect future for study and analyze all kinds of satellite cloud image. Variational method is a new image segmentation method development in recent years, which is adapt to modeling and extract deformable contour of random shape. In satellite cloud image, recognize the target object has great application meaning. In this paper, using computer image texture analysis technology combine with variational theory, extract and analyze the texture feature of familiar cloud and clear sky in satellite cloud image, adopt co-occurrence matrix base on statistic feature, compute the texture parameter like energy, entropy, contrast, correlation and local steady, at last, carry through the automatic recognition experiment which using the active contour model base on variational theory, and acquire better effect of recognition to satellite cloud image.

Published in:

2007 2nd IEEE Conference on Industrial Electronics and Applications

Date of Conference:

23-25 May 2007