Satellite Cloud Image Retrieval With Grid Based Inscribed Circle Method

DOI

10.2991/icmmita-15.2015.69How to use a DOI?

Keywords

Satellite cloud image; Feature vector; Similarity retrieval; Rotation invariance; Scale invariance

Abstract

Satellite cloud image retrieval can help the forecasters positioning similar weather in the past quickly and improve the reliability of the weather prediction. This article attempts to use the Zernike moment and Grid based method to extract the region-based features of cloud images. First of all, carry out the pretreatment of separating cloud from background, extract effective features and generate the features library of the cloud image library. Then calculate the similarity between a given cloud image and the cloud library. Finally, output the final results according to the order of similarity. After comparing the retrieval results of the two methods, we put forward an improved algorithm named grid based inscribed circle method(GBIC). Experiments show that this method possesses the advantages of the above two methods and can retrieve cloud images with similar visual features from the history cloud image library.

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  - Shiming Xia
AU  - Qian Li
AU  - Jing Zhang
PY  - 2015/11
DA  - 2015/11
TI  - Satellite Cloud Image Retrieval With Grid Based Inscribed Circle Method
BT  - Proceedings of the 2015 3rd International Conference on Machinery, Materials and Information Technology Applications
PB  - Atlantis Press
SP  - 351
EP  - 356
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmita-15.2015.69
DO  - 10.2991/icmmita-15.2015.69
ID  - Xia2015/11
ER  -