TY - GEN
T1 - Automatic classification of dayside aurora in all-sky images using a multi-level texture feature representation
AU - Han, Shenmiao
AU - Wu, Zhensen
AU - Wu, Guangli
AU - Tan, Jun
N1 - Copyright:
Copyright 2011 Elsevier B.V., All rights reserved.
PY - 2012
Y1 - 2012
N2 - In this paper, we propose an aurora classification method using a multi-level feature representation aimed to capture both global and local texture information, and to reduce the feature space dimension substantially. First-order and second-order statistics are computed for an input image and its low-frequency scaled images at three lower levels obtained using wavelet decomposition. The features include gray level distribution, co-occurrence matrix features, and run-length matrix features. A support vector machine (SVM) classifier was trained and tested on a Chinese Arctic Yellow River Station dayside aurora image dataset. Classification performance was evaluated and compared with those of k-nearest neighbor (KNN) classifiers and back-propagation neural networks (BPNN). To explore the possibility of using a smaller feature space, we used a Minimum-Redundancy Max-Relevance feature selection strategy. The result shows that there is only indistinct performance decrease by reducing the feature vector from a total of 88 to the most discriminatory 38 features. This proves that our multi-level feature representation is very robust.
AB - In this paper, we propose an aurora classification method using a multi-level feature representation aimed to capture both global and local texture information, and to reduce the feature space dimension substantially. First-order and second-order statistics are computed for an input image and its low-frequency scaled images at three lower levels obtained using wavelet decomposition. The features include gray level distribution, co-occurrence matrix features, and run-length matrix features. A support vector machine (SVM) classifier was trained and tested on a Chinese Arctic Yellow River Station dayside aurora image dataset. Classification performance was evaluated and compared with those of k-nearest neighbor (KNN) classifiers and back-propagation neural networks (BPNN). To explore the possibility of using a smaller feature space, we used a Minimum-Redundancy Max-Relevance feature selection strategy. The result shows that there is only indistinct performance decrease by reducing the feature vector from a total of 88 to the most discriminatory 38 features. This proves that our multi-level feature representation is very robust.
KW - Aurora
KW - Gray level co-occurrence matrix
KW - Run-length
KW - Support vector machine
KW - Wavelet decomposition
UR - http://www.scopus.com/inward/record.url?scp=80054005276&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=80054005276&partnerID=8YFLogxK
U2 - 10.4028/www.scientific.net/AMR.341-342.158
DO - 10.4028/www.scientific.net/AMR.341-342.158
M3 - Conference contribution
AN - SCOPUS:80054005276
SN - 9783037852521
T3 - Advanced Materials Research
SP - 158
EP - 162
BT - Material and Manufacturing Technology II
T2 - 2011 2nd International Conference on Material and Manufacturing Technology, ICMMT 2011
Y2 - 8 July 2011 through 11 July 2011
ER -