Texture based Approach for Cloud Classification using SVM

被引：14

作者：

Chethan, H. K. ^{[1
]}

Raghavendra, R. ^{[1
]}

Kumar, Hemantha C. ^{[1
]}

机构：

[1] Univ Mysore, Dept Studies Comp Sci, Mysore 570006, Karnataka, India

来源：

2009 INTERNATIONAL CONFERENCE ON ADVANCES IN RECENT TECHNOLOGIES IN COMMUNICATION AND COMPUTING (ARTCOM 2009) | 2009年

关键词：

D O I：

10.1109/ARTCom.2009.43

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Cloud analysis provides information which is vital to the detection, understanding and prediction of meteorological trends and environmental changes. Cloud classification is needed for the purpose of achieving an automatic extraction of information on cloud occurrence and cloud types. In this work, we propose a method of cloud classification using textural feature based on Gabor transform and classification is carried out using powerful and elegant classifier known as Support Vector Machines(SVM) using Linear, Polynomial and Gaussian-RBF Kernel. Extensive Experiments are carried out on large database of 500 cloud images collected from Kalpana -1 satellite. Experiments have shown the efficacy of the proposed method.

引用

页码：688 / 690

页数：3

共 12 条

[1]

[Anonymous], SATELLITE DATABASE

[2]

[Anonymous], INTRO SVM OTHER KERN

[3]

BANKERT RL, 1994, J APPL METEOROL, V33, P909, DOI 10.1175/1520-0450(1994)033<0909:CCOAII>2.0.CO

[4]

[5]

CHRISTODOULOU C, 2001, ICPR

[6]

GRIFFIN M, 2000, IEEE INT GEOSC REM S, V2, P809

[7]

Hetzheim H, 2000, INT GEOSCI REMOTE SE, P1798, DOI 10.1109/IGARSS.2000.858127

[8]

LAKSHMANAN V, 2000, ICIP

[9]

Pankiewicz GS., 1995, Meteorological Applications, V2, DOI [10.1002/met.5060020309, DOI 10.1002/MET.5060020309]

[10] A study of cloud classification with neural networks using spectral and textural features [J].

Tian, B ;

Shaikh, MA ;

Azimi-Sadjadi, MR ;

Vonder Haar, TH ;

Reinke, DL .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (01) :138-151

← 1 2 →